{"owner":"DrewThomasson","repo":"ebook2audiobook","hasSkills":true,"totalSkillsCount":2,"totalTokensCount":28756,"categories":["anthropic-skill"],"hasMcp":false,"mcpConfig":null,"found":["tools/readme_i18n/baseline_README.md","tools/readme_i18n/cache.json"],"skills":{"tools/readme_i18n/baseline_README.md":"# 📚 ebook2audiobook (E2A)\n![\"DrewThomasson%2Febook2audiobook](\"https://trendshift.io/api/badge/repositories/12252\")
\n\nCPU/GPU Converter from E-Book to audiobook with chapters and metadata
\nusing advanced TTS engines and much more.
\nSupports voice cloning and 1158 languages!\n> [!IMPORTANT]\n**This tool is intended for use with non-DRM, legally acquired eBooks only.**
\nThe authors are not responsible for any misuse of this software or any resulting legal consequences.
\nUse this tool responsibly and in accordance with all applicable laws.\n\n[](https://discord.gg/63Tv3F65k6)\n\n### Thanks to support ebook2audiobook developers!\n[](https://ko-fi.com/athomasson2) \n\n### Run locally\n\n[](#instructions)\n\n[](https://github.com/DrewThomasson/ebook2audiobook/actions/workflows/Docker-Build.yml) [](https://github.com/DrewThomasson/ebook2audiobook/releases/latest) \n\n\n\n ![\"Platform\"](\"https://img.shields.io/badge/Platform-mac%20|%20linux%20|%20windows-lightgrey\")
\n\n![\"Docker](\"https://img.shields.io/docker/pulls/athomasson2/ebook2audiobook.svg\"/)
\n\n\n### Run Remotely\n[](https://huggingface.co/spaces/drewThomasson/ebook2audiobook)\n[](https://colab.research.google.com/github/DrewThomasson/ebook2audiobook/blob/main/Notebooks/colab_ebook2audiobook.ipynb) [](https://github.com/Rihcus/ebook2audiobookXTTS/blob/main/Notebooks/kaggle-ebook2audiobook.ipynb)\n\n#### GUI Interface\n\n\n\n Click to see images of Web GUI
\n ![\"GUI](\"assets/gui_1.png\")
\n ![\"GUI](\"assets/gui_2.png\")
\n ![\"GUI](\"assets/gui_3.png\")
\n \n\n## Demos\n\n**New Default Voice Demo** \n\nhttps://github.com/user-attachments/assets/750035dc-e355-46f1-9286-05c1d9e88cea \n\n\n More Demos
\n\n**ASMR Voice** \n\nhttps://github.com/user-attachments/assets/68eee9a1-6f71-4903-aacd-47397e47e422\n\n**Rainy Day Voice** \n\nhttps://github.com/user-attachments/assets/d25034d9-c77f-43a9-8f14-0d167172b080 \n\n**Scarlett Voice**\n\nhttps://github.com/user-attachments/assets/b12009ee-ec0d-45ce-a1ef-b3a52b9f8693\n\n**David Attenborough Voice** \n\nhttps://github.com/user-attachments/assets/81c4baad-117e-4db5-ac86-efc2b7fea921\n\n**Example**\n\n\n \n\n## README.md\n\n## Table of Contents\n- [ebook2audiobook](#-ebook2audiobook)\n- [Features](#features)\n- [GUI Interface](#gui-interface)\n- [Demos](#demos)\n- [Supported Languages](#supported-languages)\n- [Minimum Requirements](#hardware-requirements)\n- [Usage](#instructions)\n - [Run Locally](#instructions)\n - [Launching Gradio Web Interface](#instructions)\n - [Basic Headless Usage](#basic-usage)\n - [Headless Custom XTTS Model Usage](#example-of-custom-model-zip-upload)\n - [Help command output](#help-command-output)\n - [Run Remotely](#run-remotely)\n - [Docker](#docker)\n - [Steps to Run](#docker)\n \n- [Cloned Voices](#cloned-voices)\n- [Fine Tuned TTS models](#fine-tuned-tts-models) \n - [Collection of Fine-Tuned TTS Models](#fine-tuned-tts-collection)\n - [Train TTS Model](#fine-tune-your-own-tts-model)\n- [Supported eBook Formats](#supported-ebook-formats)\n- [Output Formats](#output-and-process-formats)\n- [Revert to older Version](#reverting-to-older-versions)\n- [Common Issues](#common-issues)\n- [Special Thanks](#special-thanks)\n- [Table of Contents](#table-of-contents)\n\n\n## Features\n- 🔧 **TTS Engines supported**: `XTTSv2`, `Bark`, `Fairseq`, `VITS`, `Tacotron2`, `Tortoise`, `GlowTTS`, `YourTTS`\n- 📚 **Convert multiple file formats**: `.epub`, `.mobi`, `.azw3`, `.fb2`, `.lrf`, `.rb`, `.snb`, `.tcr`, `.pdf`, `.txt`, `.rtf`, `.doc`, `.docx`, `.html`, `.odt`, `.azw`, `.tiff`, `.tif`, `.png`, `.jpg`, `.jpeg`, `.bmp`, `.zip`\n- 💻 **TextArea** to convert directly a short text in audio\n- 🔍 **OCR scanning** for files with text pages as images\n- 🔊 **High-quality text-to-speech** from near realtime to near real voice\n- 🗣️ **Optional voice cloning** using your own voice file\n- 🌐 **Supports 1158 languages** ([supported languages list](https://dl.fbaipublicfiles.com/mms/tts/all-tts-languages.html))\n- 💻 **Low-resource friendly** — runs on **2 GB RAM / 1 GB VRAM (minimum)**\n- 🎵 **Audiobook output formats**: mono or stereo `aac`, `flac`, `mp3`, `m4b`, `m4a`, `mp4`, `mov`, `ogg`, `wav`, `webm`\n- 🧠 **SML tags supported** — fine-grained control of breaks, pauses, voice switching and more ([see below](#sml-tags-available))\n- 🧩 **Optional custom model** using your own trained model (XTTSv2, VITS, FAIRSEQ, PIPER, others on request)\n- 🎛️ **Fine-tuned preset models** trained by the E2A Team
\n (Contact us if you need additional fine-tuned models, or if you’d like to share yours to the official preset list)\n\n\n## Hardware Requirements\n- 2GB RAM min, 8GB recommended.\n- 1GB VRAM min, 4GB recommended.\n- Virtualization enabled if running on windows (Docker only).\n- CPU, XPU (intel, AMD, ARM)*.\n- CUDA, ROCm, JETSON\n- MPS (Apple Silicon CPU)\n\n* Modern TTS engines are very slow on CPU, so use lower quality TTS like YourTTS, Tacotron2 etc..\n\n## Supported Languages\n| **Arabic (ar)** | **Chinese (zh)** | **English (en)** | **Spanish (es)** |\n|:------------------:|:------------------:|:------------------:|:------------------:|\n| **French (fr)** | **German (de)** | **Italian (it)** | **Portuguese (pt)** |\n| **Polish (pl)** | **Turkish (tr)** | **Russian (ru)** | **Dutch (nl)** |\n| **Czech (cs)** | **Japanese (ja)** | **Hindi (hi)** | **Bengali (bn)** |\n| **Hungarian (hu)** | **Korean (ko)** | **Vietnamese (vi)**| **Swedish (sv)** |\n| **Persian (fa)** | **Yoruba (yo)** | **Swahili (sw)** | **Indonesian (id)**|\n| **Slovak (sk)** | **Croatian (hr)** | **Tamil (ta)** | **Danish (da)** |\n- [**+1130 languages and dialects here**](https://dl.fbaipublicfiles.com/mms/tts/all-tts-languages.html)\n\n\n## Supported eBook Formats\n- `.epub`, `.pdf`, `.mobi`, `.txt`, `.html`, `.rtf`, `.chm`, `.lit`,\n `.pdb`, `.fb2`, `.odt`, `.cbr`, `.cbz`, `.prc`, `.lrf`, `.pml`,\n `.snb`, `.cbc`, `.rb`, `.tcr`\n- **Best results**: `.epub` or `.mobi` for automatic chapter detection\n\n## Output and process Formats\n- `.m4b`, `.m4a`, `.mp4`, `.webm`, `.mov`, `.mp3`, `.flac`, `.wav`, `.ogg`, `.aac`\n- Process format can be changed in lib/conf.py\n\n## SML tags available\n- `[break]` — silence (random range **0.3–0.6 sec.**)\n- `[pause]` — silence (random range **1.0–1.6 sec.**)\n- `[pause:N]` — fixed pause (**N sec.**)\n- `[voice:/path/to/voice/file]...[/voice]` — switch voice from default or selected voice from GUI/CLI\n\n**Check our other repo dedicated to add SML automatically in your ebook -> [E2A-SML](https://github.com/DrewThomasson/E2A-SML)**\n\n> [!IMPORTANT]\n**Before to post an install or bug issue search carefully to the opened and closed issues TAB
\nto be sure your issue does not exist already.**\n\n>[!NOTE]\n**EPUB format lacks any standard structure like what is a chapter, paragraph, preface etc.
\nSo you should first remove manually any text you don't want to be converted in audio.**\n\n\n### Instructions \n1. **Clone repo**\n\t```bash\n\tgit clone https://github.com/DrewThomasson/ebook2audiobook.git\n\tcd ebook2audiobook\n\t```\n\n2. **Install / Run ebook2audiobook**:\n\n - **Linux/MacOS** \n ```bash\n ./ebook2audiobook.command\n ```\n Note for MacOS users: homebrew is installed to install missing programs.\n \n - **Mac Launcher** \n Double click `Mac Ebook2Audiobook Launcher.command`\n\n\n - **Windows** \n ```bash\n ebook2audiobook.cmd\n ```\n or\n Double click `ebook2audiobook.cmd`\n\n Note for Windows users: scoop is installed to install missing programs without administrator privileges.\n \n1. **Open the Web App**: Click the URL provided in the terminal to access the web app and convert eBooks. `http://localhost:7860/`\n2. **For Public Link**:\n `./ebook2audiobook.command --share` (Linux/MacOS)\n `ebook2audiobook.cmd --share` (Windows)\n `python app.py --share` (all OS)\n\n> [!IMPORTANT]\n**If the script is stopped and run again, you need to refresh your gradio GUI interface
\nto let the web page reconnect to the new connection socket.**\n\n### Basic Usage\n - **Linux/MacOS**:\n ```bash\n ./ebook2audiobook.command --headless --ebook --voice --language \n ```\n - **Windows**\n ```bash\n ebook2audiobook.cmd --headless --ebook --voice --language \n ```\n \n - **[--ebook]**: Path to your eBook file\n - **[--voice]**: Voice cloning file path (optional)\n - **[--language]**: Language code in ISO-639-3 (i.e.: ita for italian, eng for english, deu for german...).
\n Default language is eng and --language is optional for default language set in ./lib/lang.py.
\n The ISO-639-1 2 letters codes are also supported.\n\n\n### Example of Custom Model Zip Upload\n (must be a .zip file containing the mandatory model files. Example for XTTSv2: config.json, model.pth, vocab.json and ref.wav)\n - **Linux/MacOS**\n ```bash\n ./ebook2audiobook.command --headless --ebook --language --custom_model \n ```\n - **Windows**\n ```bash\n ebook2audiobook.cmd --headless --ebook --language --custom_model \n ```\n Note: the ref.wav of your custom model is always the voice selected for the conversion\n \n- ****: Path to `model_name.zip` file,\n which must contain (according to the tts engine) all the mandatory files
\n (see ./lib/models.py).\n\n### For Detailed Guide with list of all Parameters to use\n - **Linux/MacOS**\n ```bash\n ./ebook2audiobook.command --help\n ```\n - **Windows**\n ```bash\n ebook2audiobook.cmd --help\n ```\n - **Or for all OS**\n ```python\n app.py --help\n ```\n\n\n```bash\nusage: app.py [-h] [--session SESSION] [--share] [--headless] [--ebook EBOOK] [--ebooks_dir EBOOKS_DIR]\n [--language LANGUAGE] [--voice VOICE] [--voice_map VOICE_MAP] [--device {CPU,CUDA,MPS,ROCM,XPU,JETSON}]\n [--tts_engine {XTTS,BARK,VITS,FAIRSEQ,TACOTRON,YOURTTS,xtts,bark,vits,fairseq,tacotron,yourtts}]\n [--custom_model CUSTOM_MODEL] [--fine_tuned FINE_TUNED] [--output_format OUTPUT_FORMAT]\n [--output_channel OUTPUT_CHANNEL] [--temperature TEMPERATURE] [--length_penalty LENGTH_PENALTY]\n [--num_beams NUM_BEAMS] [--repetition_penalty REPETITION_PENALTY] [--top_k TOP_K] [--top_p TOP_P]\n [--speed SPEED] [--enable_text_splitting] [--text_temp TEXT_TEMP] [--waveform_temp WAVEFORM_TEMP]\n [--output_dir OUTPUT_DIR] [--version]\n\nConvert eBooks to Audiobooks using a Text-to-Speech model. You can either launch the Gradio interface or run the script in headless mode for direct conversion.\n\noptions:\n -h, --help show this help message and exit\n --session SESSION Session to resume the conversion in case of interruption, crash,\n or reuse of custom models and custom cloning voices.\n\n**** The following option is for gradio/gui mode only:\n --share (Optional) Enable a public shareable Gradio link.\n\n**** The following options are for --headless mode only:\n --headless Run the script in headless mode\n --ebook EBOOK Path to the ebook file for conversion. Cannot be used when --ebooks_dir is present.\n --ebooks_dir EBOOKS_DIR\n Relative or absolute path of the directory containing the files to convert.\n Cannot be used when --ebook is present.\n --text TEXT Raw text for conversion. Cannot be used when --ebook or --ebooks_dir is present.\n --language LANGUAGE Language of the e-book. Default language is set\n in ./lib/lang.py sed as default if not present. All compatible language codes are in ./lib/lang.py\n\noptional parameters:\n --translate ISO3 (Optional) Translate ebook to a target language (ISO 639-3 code, e.g. eng, fra, deu) before TTS synthesis.\n Uses argostranslate. The target language becomes the effective TTS language for the run.\n A copy of the source ebook is made with the _ suffix so translated and non-translated\n outputs stay isolated (independent process folder, audio chunks, and final file).\n --voice VOICE (Optional) Path to the voice cloning file for TTS engine.\n Uses the default voice if not present.\n --voice_map VOICE_MAP\n (Optional, --ebooks_dir only) Path to a JSON file mapping ebook path -> voice path.\n Each entry overrides --voice for that specific ebook. Missing/null entries fall back to --voice.\n Keys may be absolute paths or basenames. Example:\n {\"book1.epub\": \"/voices/eng/adult/female/alice.wav\", \"/abs/path/book2.epub\": null}\n --device {CPU,CUDA,MPS,ROCM,XPU,JETSON}\n (Optional) Processor unit type for the conversion.\n Default is set in ./lib/conf.py if not present. Fall back to CPU if CUDA or MPS is not available.\n --tts_engine {XTTS,BARK,VITS,FAIRSEQ,TACOTRON,YOURTTS,xtts,bark,vits,fairseq,tacotron,yourtts}\n (Optional) Preferred TTS engine (available are: ['XTTS', 'BARK', 'VITS', 'FAIRSEQ', 'TACOTRON', 'YOURTTS', 'xtts', 'bark', 'vits', 'fairseq', 'tacotron', 'yourtts'].\n Default depends on the selected language. The tts engine should be compatible with the chosen language\n --custom_model CUSTOM_MODEL\n (Optional) Path to the custom model zip file cntaining mandatory model files.\n Please refer to ./lib/models.py\n --fine_tuned FINE_TUNED\n (Optional) Fine tuned model path. Default is builtin model.\n --output_format OUTPUT_FORMAT\n (Optional) Output audio format. Default is m4b set in ./lib/conf.py\n --output_channel OUTPUT_CHANNEL\n (Optional) Output audio channel. Default is mono set in ./lib/conf.py\n --temperature TEMPERATURE\n (xtts only, optional) Temperature for the model.\n Default to config.json model. Higher temperatures lead to more creative outputs.\n --length_penalty LENGTH_PENALTY\n (xtts only, optional) A length penalty applied to the autoregressive decoder.\n Default to config.json model. Not applied to custom models.\n --num_beams NUM_BEAMS\n (xtts only, optional) Controls how many alternative sequences the model explores. Must be equal or greater than length penalty.\n Default to config.json model.\n --repetition_penalty REPETITION_PENALTY\n (xtts only, optional) A penalty that prevents the autoregressive decoder from repeating itself.\n Default to config.json model.\n --top_k TOP_K (xtts only, optional) Top-k sampling.\n Lower values mean more likely outputs and increased audio generation speed.\n Default to config.json model.\n --top_p TOP_P (xtts only, optional) Top-p sampling.\n Lower values mean more likely outputs and increased audio generation speed. Default to config.json model.\n --speed SPEED (xtts only, optional) Speed factor for the speech generation.\n Default to config.json model.\n --enable_text_splitting\n (xtts only, optional) Enable TTS text splitting. This option is known to not be very efficient.\n Default to config.json model.\n --text_temp TEXT_TEMP\n (bark only, optional) Text Temperature for the model.\n Default to config.json model.\n --waveform_temp WAVEFORM_TEMP\n (bark only, optional) Waveform Temperature for the model.\n Default to config.json model.\n --output_dir OUTPUT_DIR\n (Optional) Path to the output directory. Default is set in ./lib/conf.py\n --abs_url ABS_URL Audiobookshelf server URL (e.g. http://localhost:13378).\n --abs_api_token ABS_API_TOKEN\n Audiobookshelf API token.\n --abs_library ABS_LIBRARY\n Audiobookshelf library ID.\n --enable_interlude Add MusicGen music before the first chapter, between chapters, and at the end of the audiobook. Settings are in ./lib/conf_interlude.py\n --version Show the version of the script and exit\n\nExample usage:\nWindows:\n Gradio/GUI:\n ebook2audiobook.cmd\n Headless mode:\n ebook2audiobook.cmd --headless --ebook '/path/to/file' --language eng\nLinux/Mac:\n Gradio/GUI:\n ./ebook2audiobook.command\n Headless mode:\n ./ebook2audiobook.command --headless --ebook '/path/to/file' --language eng\n\nSML tags available:\n\t[break] — silence (random range **0.3–0.6 sec.**)\n\t[pause] — silence (random range **1.0–1.6 sec.**)\n\t[pause:N] — fixed pause (**N sec.**)\n\t[voice:/path/to/voice/file]...[/voice] — switch voice from default or selected voice from GUI/CLI\n\n```\n\nNOTE: in gradio/gui mode, to cancel a running conversion, just click on the [X] from the ebook upload component.\nTIP: if it needs some more pause, add '[pause:3]' for 3 sec. etc.\n\n### Docker\n1. **Clone the Repository**:\n```bash\n git clone https://github.com/DrewThomasson/ebook2audiobook.git\n cd ebook2audiobook\n```\n2. **Build the container**\n```bash\n Windows:\n Docker:\n ebook2audiobook.cmd --script_mode build_docker\n Docker Compose:\n ebook2audiobook.cmd --script_mode build_docker --docker_mode compose\n Podman Compose:\n ebook2audiobook.cmd --script_mode build_docker --docker_mode podman\n Linux/Mac\n Docker:\n ./ebook2audiobook.command --script_mode build_docker\n Docker Compose\n ./ebook2audiobook.command --script_mode build_docker --docker_mode compose\n Podman Compose:\n ./ebook2audiobook.command --script_mode build_docker --docker_mode podman\n```\n4. **Run the Container:**\n```bash\nDocker run image:\n Gradio/GUI:\n CPU:\n docker run -v \"./ebooks:/app/ebooks\" -v \"./audiobooks:/app/audiobooks\" -v \"./models:/app/models\" -v \"./voices:/app/voices\" -v \"./tmp:/app/tmp\" --rm -it -p 7860:7860 athomasson2/ebook2audiobook:cpu\n CUDA:\n docker run -v \"./ebooks:/app/ebooks\" -v \"./audiobooks:/app/audiobooks\" -v \"./models:/app/models\" -v \"./voices:/app/voices\" -v \"./tmp:/app/tmp\" --gpus all --rm -it -p 7860:7860 athomasson2/ebook2audiobook:cu[118/122/124/126 etc..]\n ROCM:\n docker run -v \"./ebooks:/app/ebooks\" -v \"./audiobooks:/app/audiobooks\" -v \"./models:/app/models\" -v \"./voices:/app/voices\" -v \"./tmp:/app/tmp\" --device=/dev/kfd --device=/dev/dri --rm -it -p 7860:7860 athomasson2/ebook2audiobook:rocm[6.0/6.1/6.4 etc..]\n XPU:\n docker run -v \"./ebooks:/app/ebooks\" -v \"./audiobooks:/app/audiobooks\" -v \"./models:/app/models\" -v \"./voices:/app/voices\" -v \"./tmp:/app/tmp\" --device=/dev/dri --rm -it -p 7860:7860 athomasson2/ebook2audiobook:xpu\n JETSON:\n docker run -v \"./ebooks:/app/ebooks\" -v \"./audiobooks:/app/audiobooks\" -v \"./models:/app/models\" -v \"./voices:/app/voices\" -v \"./tmp:/app/tmp\" --runtime nvidia --rm -it -p 7860:7860 athomasson2/ebook2audiobook:jetson[51/60/61 etc...]\n Headless mode:\n CPU:\n docker run -v \"./ebooks:/app/ebooks\" -v \"./audiobooks:/app/audiobooks\" -v \"./models:/app/models\" -v \"./voices:/app/voices\" -v \"./tmp:/app/tmp\" -v \"/my/real/ebooks/folder/absolute/path:/app/another_ebook_folder\" --rm -it -p 7860:7860 ebook2audiobook:cpu --headless --ebook \"/app/another_ebook_folder/myfile.pdf\" [--voice /app/my/voicepath/voice.mp3 etc..]\n CUDA:\n docker run -v \"./ebooks:/app/ebooks\" -v \"./audiobooks:/app/audiobooks\" -v \"./models:/app/models\" -v \"./voices:/app/voices\" -v \"./tmp:/app/tmp\" -v \"/my/real/ebooks/folder/absolute/path:/app/another_ebook_folder\" --gpus all --rm -it -p 7860:7860 ebook2audiobook:cu[118/122/124/126 etc..] --headless --ebook \"/app/another_ebook_folder/myfile.pdf\" [--voice /app/my/voicepath/voice.mp3 etc..]\n ROCM:\n docker run -v \"./ebooks:/app/ebooks\" -v \"./audiobooks:/app/audiobooks\" -v \"./models:/app/models\" -v \"./voices:/app/voices\" -v \"./tmp:/app/tmp\" -v \"/my/real/ebooks/folder/absolute/path:/app/another_ebook_folder\" --device=/dev/kfd --device=/dev/dri --rm -it -p 7860:7860 ebook2audiobook:rocm[6.0/6.1/6.4 etc.] --headless --ebook \"/app/another_ebook_folder/myfile.pdf\" [--voice /app/my/voicepath/voice.mp3 etc..]\n XPU:\n docker run -v \"./ebooks:/app/ebooks\" -v \"./audiobooks:/app/audiobooks\" -v \"./models:/app/models\" -v \"./voices:/app/voices\" -v \"./tmp:/app/tmp\" -v \"/my/real/ebooks/folder/absolute/path:/app/another_ebook_folder\" --device=/dev/dri --rm -it -p 7860:7860 ebook2audiobook:xpu --headless --ebook \"/app/another_ebook_folder/myfile.pdf\" [--voice /app/my/voicepath/voice.mp3 etc..]\n JETSON:\n docker run -v \"./ebooks:/app/ebooks\" -v \"./audiobooks:/app/audiobooks\" -v \"./models:/app/models\" -v \"./voices:/app/voices\" -v \"./tmp:/app/tmp\" -v \"/my/real/ebooks/folder/absolute/path:/app/another_ebook_folder\" --runtime nvidia --rm -it -p 7860:7860 ebook2audiobook:jetson[51/60/61 etc.] --headless --ebook \"/app/another_ebook_folder/myfile.pdf\" [--voice /app/my/voicepath/voice.mp3 etc..]\nDocker Compose (i.e. cuda 12.8:\n Run Gradio GUI:\n DEVICE_TAG=cu128 docker compose --profile gpu up --no-log-prefix\n Run Headless mode:\n DEVICE_TAG=cu128 docker compose --profile gpu run --rm ebook2audiobook --headless --ebook \"/app/ebooks/myfile.pdf\" --voice /app/voices/eng/adult/female/some_voice.wav etc..\nPodman Compose (i.e. cuda 12.8:\n Run Gradio GUI:\n DEVICE_TAG=cu128 podman-compose -f podman-compose.yml --profile gpu up\n Run Headless mode:\n DEVICE_TAG=cu128 podman-compose -f podman-compose.yml --profile gpu run --rm ebook2audiobook-gpu --headless --ebook \"/app/ebooks/myfile.pdf\" --voice /app/voices/eng/adult/female/some_voice.wav etc..\n```\n- NOTE: MPS is not exposed in docker so CPU must be used\n\n## Cloned Voices\nYou can upload any voice audio in any of the supported audio formats, the ideal duration is around 1 to 5 mn.\nIt doesn't matter if the recording has a noisy background or music playing over it — E2A will clean up the voice for you.\n\nThe built-in cloned voices list is mainly in English. If you need voices in other languages to be officially\nadded to the list, please contact us and we'll add them after review.\n\n## Fine Tuned TTS models\n#### Fine Tune your own TTS model\n\n[Universal_TTS_Finetune](https://github.com/DrewThomasson/Universal_TTS_Finetune)\n\n#### De-noise training data\n\n[](https://huggingface.co/spaces/drewThomasson/DeepFilterNet2_no_limit) [](https://github.com/Rikorose/DeepFilterNet)\n\n\n### Fine Tuned TTS Collection\n\n[](https://huggingface.co/drewThomasson/fineTunedTTSModels/tree/main)\n\nFor an XTTSv2 custom model a ref audio clip of the voice reference is mandatory:\n\n## Your own Ebook2Audiobook customization\nYou are free to modify libs/conf.py to add or remove the settings you wish. If you plan to do it just make\na copy of the original conf.py so on each ebook2audiobook update you will backup your modified conf.py and put\nback the original one. You must plan the same process for models.py. If you wish to make your own custom model\nas an official ebook2audiobook fine tuned model so please contact us and we'll add it to the presets list.\n\n## Reverting to older Versions\nReleases can be found -> [here](https://github.com/DrewThomasson/ebook2audiobook/releases)\n```bash\ngit checkout tags/VERSION_NUM # Locally/Compose -> Example: git checkout tags/v25.7.7\n```\n\n## Common Issues:\n- My NVIDIA/ROCm/XPU/MPS GPU isn't being detected?? -> [GPU ISSUES Wiki Page](https://github.com/DrewThomasson/ebook2audiobook/wiki/GPU-ISSUES)\n- CPU is slow (better on server smp CPU) while GPU can have almost real time conversion.\n [Discussion about this](https://github.com/DrewThomasson/ebook2audiobook/discussions/19#discussioncomment-10879846)\n (It doesn't have zero-shot voice cloning though, and is Siri quality voices, but it is much faster on cpu).\n- \"I'm having dependency issues\" - Just use the docker, its fully self contained and has a headless mode,\n add `--help` parameter at the end of the docker run command for more information.\n- \"I'm getting a truncated audio issue!\" - PLEASE MAKE AN ISSUE OF THIS,\n we don't speak every language and need advise from users to fine tune the sentence splitting logic.😊\n\n## ***** ROADMAP *****\n- All Features open to public Contributions ⭐\n- Any help from people speaking any of the supported languages to help us improve the models ⭐\n- [x] Preview Blocks/Chapters before to start the conversion\n- [x] Edit by sentence converted for surgical text change\n- [x] Generate music intros, interludes, and endings; edit interludes and endings\n- [x] SML tags integration for voice, pause, break, and more changes \n- [x] -h -help parameter info in different languages\n- [x] OCR scanning for PDF / JPG / BMP / PNG / TIFF\n- [x] Notebooks Folder [Talked about here](https://github.com/DrewThomasson/ebook2audiobookXTTS/issues/5#issuecomment-2408773254)\n- [x] Make Chinese text splitting not split words and improve pause timing [Talked about here](https://github.com/DrewThomasson/ebook2audiobookXTTS/issues/18#issuecomment-2401154894)\n- [x] Dockerfile\n- [x] Docker compose\n- [x] Podman compose \n- [x] Kaggle Notebook\n- [x] Google Colab Notebook\n- [x] Audiobookshelf integration\n- [x] Ebook Translation option\n- [x] Output format choices\n- [x] Multiprocessing conversion\n- [x] Batch ebook folder conversion\n- [x] GPU Device detection\n- [x] Denoise any background reference audio for voice cloning upload\n- [x] Custom fine-tuned model upload\n- [ ] [Make a IOS app](https://github.com/DrewThomasson/ebook2audiobook/pull/35#issuecomment-2496495212)\n- [ ] [Make an android app](https://github.com/DrewThomasson/ebook2audiobook/pull/35#issuecomment-2496495212)\n\n#### User Requests\n- [ ] Add European Portuguese language model for xttsv2, fairseq, vits, piper at least (help welcome)\n- [ ] Add Sindhi language model for xttsv2, fairseq, vits, piper at least (help welcome)\n\n#### TTS engines\n- [x] XTTSv2\n- [x] Bark\n- [x] Fairseq\n- [x] VITS\n- [x] Tacotron2\n- [x] YourTTS\n- [x] Tortoise\n- [x] GlowTTS\n- [x] Piper\n- [ ] GPT-SoVITS (https://github.com/RVC-Boss/GPT-SoVITS)\n- [ ] OpenVoice (https://github.com/myshell-ai/OpenVoice)\n- [ ] fish-speech (https://github.com/fishaudio/fish-speech)\n- [ ] ChatTTS (https://github.com/2noise/ChatTTS)\n- [ ] CosyVoice (https://github.com/FunAudioLLM/CosyVoice)\n- [ ] F5-TTS (https://github.com/swivid/f5-tts)\n- [ ] chatterbox (https://github.com/resemble-ai/chatterbox)\n- [ ] Supertonic (https://github.com/supertone-inc/supertonic)\n- [ ] Spark-TTS (https://github.com/sparkaudio/spark-tts)\n- [ ] index-tts (https://github.com/index-tts/index-tts)\n- [ ] MeloTTS (https://github.com/myshell-ai/MeloTTS)\n- [ ] Kokoro-TTS (https://github.com/hexgrad/kokoro)\n- [ ] OmniVoice (https://github.com/k2-fsa/OmniVoice)\n- [ ] Zonos (https://github.com/Zyphra/Zonos)\n- [ ] Style-TTS2 (https://github.com/yl4579/StyleTTS2)\n- [ ] Orpheus-TTS (https://github.com/canopyai/Orpheus-TTS)\n- [ ] NewTTS (https://github.com/neuphonic/neutts?tab=readme-ov-file)\n- [ ] VIbeVoice (https://github.com/vibevoice-community/VibeVoice)\n- [ ] Qwen3-TTS (https://huggingface.co/spaces/Qwen/Qwen3-TTS)\n\n#### Readme Translation\n- [x] Arabic (ara)\n- [x] Chinese (zho)\n- [x] English (eng)\n- [x] Spanish (spa)\n- [x] French (fra)\n- [x] German (deu)\n- [x] Italian (ita)\n- [x] Portuguese (por)\n- [x] Polish (pol)\n- [x] Turkish (tur)\n- [x] Russian (rus)\n- [x] Dutch (nld)\n- [x] Czech (ces)\n- [x] Japanese (jpn)\n- [x] Hindi (hin)\n- [x] Bengali (ben)\n- [x] Hungarian (hun)\n- [x] Korean (kor)\n- [x] Vietnamese (vie)\n- [x] Swedish (swe)\n- [x] Persian (fas)\n- [x] Yoruba (yor)\n- [x] Swahili (swa)\n- [x] Indonesian (ind)\n- [x] Slovak (slk)\n- [x] Croatian (hrv)\n\n#### 🐍 OS Compatibility\n- [x] 🍎 Mac Intel x86\n- [x] 🪟 Windows x86\n- [x] 🐧 Linux x86\n- [x] 🖥️🍏 Apple Silicon Mac\n- [x] 🪟💪 ARM Windows\n- [x] 🐧💪 ARM Linux\n\n**********\n\n## Extra Overkill for training models and such (All supported Coqui-tts models and piper-tts in one easy command) \n- For info about this @DrewThomasson, he is currently working on the development of this, [Universal TTS Finetune](https://github.com/DrewThomasson/Universal_TTS_Finetune)\n- [x] Make a easy to use training gui for all coqui-tts models in the [ljspeech format training recipes](https://github.com/coqui-ai/TTS/tree/dev/recipes/ljspeech) Completed at [Universal TTS Finetune](https://github.com/DrewThomasson/Universal_TTS_Finetune)\n\n\n## Python Code normalization information for contributors\n- no blank line between code, unless between functions and classes.\n- single quote used for all key unless for dict() and json. dict['key'] always called with single quote\n- 4 spaces indentation, not tab at all\n- strict typing for all functions and its arguments declaration and return values\n- no space between the argument and its typing, no space between the function, the \"->\" and the return value\n\nExample:\n\n```python\nimport json\nfrom typing import Optional\n\ndef get_user(user_id:int, users:list[dict])->Optional[dict]:\n for user in users:\n if user['id'] == user_id:\n return user\n return None\n\ndef summarize(user:dict)->str:\n return f\"User {user['name']} is {'active' if user['is_active'] else 'inactive'}.\"\n\ndef to_json(user:dict)->str:\n return json.dumps({\"id\": user['id'], \"name\": user['name'], \"email\": user['email']})\n\nusers:list = [\n dict(id=1, name=\"alice\", email=\"alice@example.com\", role=\"admin\", is_active=True),\n dict(id=2, name=\"bob\", email=\"bob@example.com\", role=\"editor\", is_active=False),\n dict(id=3, name=\"carol\", email=\"carol@example.com\", role=\"viewer\", is_active=True),\n]\nconfig = {\n \"max_users\": 100,\n \"default_role\": \"viewer\",\n \"allow_signup\": True,\n}\nroles = ['admin', 'editor', 'viewer']\nfound = get_user(1, users)\nif found:\n print(summarize(found))\n print(found['email'])\n print(to_json(found))\nif config['default_role'] in roles:\n print(config['default_role'])\n```\n\n## Hardware donation for beta tests wanted\nWe accept any kind of hardware to test our development like:\n- Nvidia supporting cuda >= 11.8\n- XPU intel cards\n- ROCm AMD cards supporting ROCm >=5.7\n\n@DrewThomasson if you want to help out at all! 😃\n\n\n## Special Thanks\nTo all financial and code contributors, each contribution and suggestion helps to improve the quality of E2A.\n","tools/readme_i18n/cache.json":"{\n \"ar|Thanks to support ebook2audiobook developers!\": \"شكرًا لدعمك لمطوّري ebook2audiobook!\",\n \"ar|Run locally\": \"التشغيل محليًا\",\n \"ar|Run Remotely\": \"التشغيل عن بُعد\",\n \"ar|GUI Interface\": \"الواجهة الرسومية (GUI)\",\n \"ar|Click to see images of Web GUI\": \"انقر لرؤية صور واجهة الويب الرسومية\",\n \"ar|Demos\": \"عروض توضيحية\",\n \"ar|**New Default Voice Demo** \": \"**عرض توضيحي للصوت الافتراضي الجديد** \",\n \"ar|More Demos\": \"المزيد من العروض التوضيحية\",\n \"ar|**ASMR Voice** \": \"**صوت ASMR** \",\n \"ar|**Rainy Day Voice** \": \"**صوت يوم ممطر** \",\n \"ar|**Scarlett Voice**\": \"**صوت سكارليت**\",\n \"ar|**David Attenborough Voice** \": \"**صوت ديفيد أتينبورو** \",\n \"ar|**Example**\": \"**مثال**\",\n \"ar|Table of Contents\": \"جدول المحتويات\",\n \"ar|[Features](#features)\": \"[الميزات](#features)\",\n \"ar|[GUI Interface](#gui-interface)\": \"[الواجهة الرسومية](#gui-interface)\",\n \"ar|[Demos](#demos)\": \"[عروض توضيحية](#demos)\",\n \"ar|[Supported Languages](#supported-languages)\": \"[اللغات المدعومة](#supported-languages)\",\n \"ar|[Minimum Requirements](#hardware-requirements)\": \"[الحد الأدنى من المتطلبات](#hardware-requirements)\",\n \"ar|[Usage](#instructions)\": \"[الاستخدام](#instructions)\",\n \"ar|[Run Locally](#instructions)\": \"[التشغيل محليًا](#instructions)\",\n \"ar|[Launching Gradio Web Interface](#instructions)\": \"[تشغيل واجهة الويب Gradio](#instructions)\",\n \"ar|[Basic Headless Usage](#basic-usage)\": \"[الاستخدام الأساسي بدون واجهة](#basic-usage)\",\n \"ar|[Headless Custom XTTS Model Usage](#example-of-custom-model-zip-upload)\": \"[استخدام نموذج XTTS مخصص بدون واجهة](#example-of-custom-model-zip-upload)\",\n \"ar|[Help command output](#help-command-output)\": \"[مخرجات أمر المساعدة](#help-command-output)\",\n \"ar|[Run Remotely](#run-remotely)\": \"[التشغيل عن بُعد](#run-remotely)\",\n \"ar|[Steps to Run](#docker)\": \"[خطوات التشغيل](#docker)\",\n \"ar|[Common Docker Issues](#common-docker-issues)\": \"[مشكلات Docker الشائعة](#common-docker-issues)\",\n \"ar|[Fine Tuned TTS models](#fine-tuned-tts-models)\": \"[نماذج TTS المضبوطة بدقة](#fine-tuned-tts-models)\",\n \"ar|[Collection of Fine-Tuned TTS Models](#fine-tuned-tts-collection)\": \"[مجموعة نماذج TTS المضبوطة بدقة](#fine-tuned-tts-collection)\",\n \"ar|[Train XTTSv2](#fine-tune-your-own-xttsv2-model)\": \"[تدريب XTTSv2](#fine-tune-your-own-xttsv2-model)\",\n \"ar|[Supported eBook Formats](#supported-ebook-formats)\": \"[صيغ الكتب الإلكترونية المدعومة](#supported-ebook-formats)\",\n \"ar|[Output Formats](#output-and-process-formats)\": \"[صيغ الإخراج](#output-and-process-formats)\",\n \"ar|[Revert to older Version](#reverting-to-older-versions)\": \"[العودة إلى إصدار أقدم](#reverting-to-older-versions)\",\n \"ar|[Common Issues](#common-issues)\": \"[المشكلات الشائعة](#common-issues)\",\n \"ar|[Special Thanks](#special-thanks)\": \"[شكر خاص](#special-thanks)\",\n \"ar|[Table of Contents](#table-of-contents)\": \"[جدول المحتويات](#table-of-contents)\",\n \"ar|Features\": \"الميزات\",\n \"ar|🔧 **TTS Engines supported**: `XTTSv2`, `Bark`, `Fairseq`, `VITS`, `Tacotron2`, `Tortoise`, `GlowTTS`, `YourTTS`\": \"🔧 **محركات TTS المدعومة**: `XTTSv2`, `Bark`, `Fairseq`, `VITS`, `Tacotron2`, `Tortoise`, `GlowTTS`, `YourTTS`\",\n \"ar|📚 **Convert multiple file formats**: `.epub`, `.mobi`, `.azw3`, `.fb2`, `.lrf`, `.rb`, `.snb`, `.tcr`, `.pdf`, `.txt`, `.rtf`, `.doc`, `.docx`, `.html`, `.odt`, `.azw`, `.tiff`, `.tif`, `.png`, `.jpg`, `.jpeg`, `.bmp`, `.zip`\": \"📚 **تحويل صيغ ملفات متعددة**: `.epub`, `.mobi`, `.azw3`, `.fb2`, `.lrf`, `.rb`, `.snb`, `.tcr`, `.pdf`, `.txt`, `.rtf`, `.doc`, `.docx`, `.html`, `.odt`, `.azw`, `.tiff`, `.tif`, `.png`, `.jpg`, `.jpeg`, `.bmp`, `.zip`\",\n \"ar|💻 **TextArea** to convert directly a short text in audio\": \"💻 **منطقة نص** لتحويل نص قصير مباشرةً إلى صوت\",\n \"ar|🔍 **OCR scanning** for files with text pages as images\": \"🔍 **مسح OCR** للملفات التي تحتوي على صفحات نصية كصور\",\n \"ar|🔊 **High-quality text-to-speech** from near realtime to near real voice\": \"🔊 **تحويل نص إلى كلام عالي الجودة**، من شبه الوقت الفعلي إلى صوت شبه حقيقي\",\n \"ar|🗣️ **Optional voice cloning** using your own voice file\": \"🗣️ **استنساخ صوت اختياري** باستخدام ملف صوتك الخاص\",\n \"ar|🌐 **Supports 1158 languages** ([supported languages list](https://dl.fbaipublicfiles.com/mms/tts/all-tts-languages.html))\": \"🌐 **يدعم 1158 لغة** ([supported languages list](https://dl.fbaipublicfiles.com/mms/tts/all-tts-languages.html))\",\n \"ar|💻 **Low-resource friendly** — runs on **2 GB RAM / 1 GB VRAM (minimum)**\": \"💻 **صديق للموارد المنخفضة** — يعمل على **2 GB RAM / 1 GB VRAM (الحد الأدنى)**\",\n \"ar|🎵 **Audiobook output formats**: mono or stereo `aac`, `flac`, `mp3`, `m4b`, `m4a`, `mp4`, `mov`, `ogg`, `wav`, `webm`\": \"🎵 **صيغ إخراج الكتاب الصوتي**: mono or stereo `aac`, `flac`, `mp3`, `m4b`, `m4a`, `mp4`, `mov`, `ogg`, `wav`, `webm`\",\n \"ar|🧠 **SML tags supported** — fine-grained control of breaks, pauses, voice switching and more ([see below](#sml-tags-available))\": \"🧠 **وسوم SML مدعومة** — تحكم دقيق في الفواصل والتوقفات وتبديل الصوت والمزيد ([see below](#sml-tags-available))\",\n \"ar|🧩 **Optional custom model** using your own trained model (XTTSv2, VITS, FAIRSEQ, PIPER, others on request)\": \"🧩 **نموذج مخصص اختياري** باستخدام نموذجك المدرّب الخاص (XTTSv2, VITS, FAIRSEQ, PIPER, others on request)\",\n \"ar|🎛️ **Fine-tuned preset models** trained by the E2A Team
\": \"🎛️ **نماذج مُعدّة مسبقًا ومضبوطة بدقة** دُرّبت بواسطة فريق E2A
\",\n \"ar|(Contact us if you need additional fine-tuned models, or if you’d like to share yours to the official preset list)\": \"(تواصل معنا إذا كنت بحاجة إلى نماذج إضافية مضبوطة بدقة، أو إذا كنت ترغب في مشاركة نماذجك في قائمة الإعدادات المسبقة الرسمية)\",\n \"ar|Hardware Requirements\": \"متطلبات العتاد\",\n \"ar|2GB RAM min, 8GB recommended.\": \"2 جيجابايت RAM كحد أدنى، 8 جيجابايت موصى به.\",\n \"ar|1GB VRAM min, 4GB recommended.\": \"1 جيجابايت VRAM كحد أدنى، 4 جيجابايت موصى به.\",\n \"ar|Virtualization enabled if running on windows (Docker only).\": \"المحاكاة الافتراضية مُفعّلة عند التشغيل على windows (Docker فقط).\",\n \"ar|CPU, XPU (intel, AMD, ARM)*.\": \"CPU، XPU (intel، AMD، ARM)*.\",\n \"ar|CUDA, ROCm, JETSON\": \"CUDA، ROCm، JETSON\",\n \"ar|MPS (Apple Silicon CPU)\": \"MPS (معالج Apple Silicon)\",\n \"ar|* Modern TTS engines are very slow on CPU, so use lower quality TTS like YourTTS, Tacotron2 etc..\": \"* محركات TTS الحديثة بطيئة جدًا على CPU، لذا استخدم TTS أقل جودة مثل YourTTS وTacotron2 وما إلى ذلك.\",\n \"ar|Supported Languages\": \"اللغات المدعومة\",\n \"ar|[**+1130 languages and dialects here**](https://dl.fbaipublicfiles.com/mms/tts/all-tts-languages.html)\": \"[**+1130 لغة ولهجة هنا**](https://dl.fbaipublicfiles.com/mms/tts/all-tts-languages.html)\",\n \"ar|Supported eBook Formats\": \"صيغ الكتب الإلكترونية المدعومة\",\n \"ar|**Best results**: `.epub` or `.mobi` for automatic chapter detection\": \"**أفضل النتائج**: `.epub` أو `.mobi` للكشف التلقائي عن الفصول\",\n \"ar|Output and process Formats\": \"صيغ الإخراج والمعالجة\",\n \"ar|Process format can be changed in lib/conf.py\": \"يمكن تغيير صيغة المعالجة في lib/conf.py\",\n \"ar|SML tags available\": \"وسوم SML المتاحة\",\n \"ar|`[break]` — silence (random range **0.3–0.6 sec.**)\": \"`[break]` — صمت (نطاق عشوائي **0.3–0.6 sec.**)\",\n \"ar|`[pause]` — silence (random range **1.0–1.6 sec.**)\": \"`[pause]` — صمت (نطاق عشوائي **1.0–1.6 sec.**)\",\n \"ar|`[pause:N]` — fixed pause (**N sec.**)\": \"`[pause:N]` — توقف ثابت (**N sec.**)\",\n \"ar|`[voice:/path/to/voice/file]...[/voice]` — switch voice from default or selected voice from GUI/CLI\": \"`[voice:/path/to/voice/file]...[/voice]` — تبديل الصوت من الصوت الافتراضي أو المحدد من GUI/CLI\",\n \"ar|**Check our other repo dedicated to add SML automatically in your ebook -> [E2A-SML](./tools/E2A-SML)**\": \"**اطّلع على مستودعنا الآخر المخصص لإضافة SML تلقائيًا في كتابك الإلكتروني -> [E2A-SML](./tools/E2A-SML)**\",\n \"ar|**Before to post an install or bug issue search carefully to the opened and closed issues TAB
\": \"**قبل نشر مشكلة تثبيت أو خطأ، ابحث بعناية في علامة تبويب المشكلات المفتوحة والمغلقة
\",\n \"ar|to be sure your issue does not exist already.**\": \"للتأكد من أن مشكلتك غير موجودة بالفعل.**\",\n \"ar|**EPUB format lacks any standard structure like what is a chapter, paragraph, preface etc.
\": \"**تفتقر صيغة EPUB إلى أي بنية معيارية لما هو الفصل أو الفقرة أو المقدمة وما إلى ذلك.
\",\n \"ar|So you should first remove manually any text you don't want to be converted in audio.**\": \"لذا يجب عليك أولًا أن تزيل يدويًا أي نص لا ترغب في تحويله إلى صوت.**\",\n \"ar|**Install / Run ebook2audiobook**:\": \"**ثبّت / شغّل ebook2audiobook**:\",\n \"ar|**Mac Launcher** \": \"**مشغّل Mac** \",\n \"ar|Double click `Mac Ebook2Audiobook Launcher.command`\": \"انقر نقرًا مزدوجًا على `Mac Ebook2Audiobook Launcher.command`\",\n \"ar|Note for Windows users: scoop is installed to install missing programs without administrator privileges.\": \"ملاحظة لمستخدمي Windows: يتم تثبيت scoop لتثبيت البرامج المفقودة دون امتيازات المسؤول.\",\n \"ar|**Open the Web App**: Click the URL provided in the terminal to access the web app and convert eBooks. `http://localhost:7860/`\": \"**افتح تطبيق الويب**: انقر على الرابط المتوفر في الطرفية للوصول إلى تطبيق الويب وتحويل الكتب الإلكترونية. `http://localhost:7860/`\",\n \"ar|**For Public Link**:\": \"**للحصول على رابط عام**:\",\n \"ar|**If the script is stopped and run again, you need to refresh your gradio GUI interface
\": \"**إذا تم إيقاف السكربت وتشغيله مرة أخرى، فستحتاج إلى تحديث واجهة Gradio الرسومية
\",\n \"ar|to let the web page reconnect to the new connection socket.**\": \"للسماح لصفحة الويب بإعادة الاتصال بمقبس الاتصال الجديد.**\",\n \"ar|**[--ebook]**: Path to your eBook file\": \"**[--ebook]**: مسار ملف كتابك الإلكتروني\",\n \"ar|**[--voice]**: Voice cloning file path (optional)\": \"**[--voice]**: مسار ملف استنساخ الصوت (اختياري)\",\n \"ar|**[--language]**: Language code in ISO-639-3 (i.e.: ita for italian, eng for english, deu for german...).
\": \"**[--language]**: رمز اللغة بصيغة ISO-639-3 (أي: ita للإيطالية، eng للإنجليزية، deu للألمانية...).
\",\n \"ar|Default language is eng and --language is optional for default language set in ./lib/lang.py.
\": \"اللغة الافتراضية هي eng و--language اختياري للغة الافتراضية المحددة في ./lib/lang.py.
\",\n \"ar|The ISO-639-1 2 letters codes are also supported.\": \"كما يتم دعم رموز ISO-639-1 المكونة من حرفين.\",\n \"ar|****: Path to `model_name.zip` file,\": \"****: مسار ملف `model_name.zip`،\",\n \"ar|which must contain (according to the tts engine) all the mandatory files
\": \"الذي يجب أن يحتوي (وفقًا لمحرك tts) على جميع الملفات الإلزامية
\",\n \"ar|(see ./lib/models.py).\": \"(انظر ./lib/models.py).\",\n \"ar|NOTE: in gradio/gui mode, to cancel a running conversion, just click on the [X] from the ebook upload component.\": \"ملاحظة: في وضع gradio/gui، لإلغاء تحويل قيد التشغيل، ما عليك سوى النقر على [X] في مكوّن رفع الكتاب الإلكتروني.\",\n \"ar|TIP: if it needs some more pause, add '[pause:3]' for 3 sec. etc.\": \"نصيحة: إذا كانت هناك حاجة إلى توقف أطول قليلًا، أضف '[pause:3]' لمدة 3 ثوانٍ وما إلى ذلك.\",\n \"ar|Common Docker Issues\": \"مشكلات Docker الشائعة\",\n \"ar|My NVIDIA GPU isn't being detected?? -> [GPU ISSUES Wiki Page](https://github.com/DrewThomasson/ebook2audiobook/wiki/GPU-ISSUES)\": \"لا يتم اكتشاف بطاقة NVIDIA الرسومية لدي؟؟ -> [صفحة Wiki لمشكلات GPU](https://github.com/DrewThomasson/ebook2audiobook/wiki/GPU-ISSUES)\",\n \"ar|Fine Tuned TTS models\": \"نماذج TTS المضبوطة بدقة (fine-tuned)\",\n \"ar|Fine Tune your own XTTSv2 model\": \"اضبط نموذج XTTSv2 الخاص بك بدقة\",\n \"ar|De-noise training data\": \"إزالة الضوضاء من بيانات التدريب\",\n \"ar|Fine Tuned TTS Collection\": \"مجموعة نماذج TTS المضبوطة بدقة\",\n \"ar|For an XTTSv2 custom model a ref audio clip of the voice reference is mandatory:\": \"بالنسبة إلى نموذج XTTSv2 المخصص، يكون مقطع صوتي مرجعي للصوت إلزاميًا:\",\n \"ar|Your own Ebook2Audiobook customization\": \"تخصيصك الخاص لـ Ebook2Audiobook\",\n \"ar|You are free to modify libs/conf.py to add or remove the settings you wish. If you plan to do it just make\": \"أنت حر في تعديل libs/conf.py لإضافة أو إزالة الإعدادات التي تريدها. إذا كنت تخطط للقيام بذلك، فما عليك سوى إنشاء\",\n \"ar|a copy of the original conf.py so on each ebook2audiobook update you will backup your modified conf.py and put\": \"نسخة من conf.py الأصلي بحيث يمكنك في كل تحديث لـ ebook2audiobook عمل نسخة احتياطية من conf.py المعدّل وإعادة\",\n \"ar|back the original one. You must plan the same process for models.py. If you wish to make your own custom model\": \"وضع الأصلي. يجب عليك التخطيط للعملية نفسها بالنسبة لـ models.py. إذا كنت ترغب في جعل نموذجك المخصص\",\n \"ar|as an official ebook2audiobook fine tuned model so please contact us and we'll add it to the presets list.\": \"نموذج ebook2audiobook رسميًا مضبوطًا بدقة، فيرجى الاتصال بنا وسنضيفه إلى قائمة الإعدادات المسبقة.\",\n \"ar|Common Issues:\": \"المشكلات الشائعة:\",\n \"ar|My NVIDIA/ROCm/XPU/MPS GPU isn't being detected?? -> [GPU ISSUES Wiki Page](https://github.com/DrewThomasson/ebook2audiobook/wiki/GPU-ISSUES)\": \"لا يتم اكتشاف بطاقة NVIDIA/ROCm/XPU/MPS الرسومية لدي؟؟ -> [GPU ISSUES Wiki Page](https://github.com/DrewThomasson/ebook2audiobook/wiki/GPU-ISSUES)\",\n \"ar|CPU is slow (better on server smp CPU) while GPU can have almost real time conversion.\": \"المعالج بطيء (أفضل على معالج خادم SMP) بينما يمكن لبطاقة GPU إجراء تحويل شبه فوري.\",\n \"ar|(It doesn't have zero-shot voice cloning though, and is Siri quality voices, but it is much faster on cpu).\": \"(لكنه لا يحتوي على استنساخ صوت zero-shot، وهي أصوات بجودة Siri، لكنه أسرع بكثير على cpu).\",\n \"ar|\\\"I'm having dependency issues\\\" - Just use the docker, its fully self contained and has a headless mode,\": \"\\\"أواجه مشكلات في التبعيات\\\" - ما عليك سوى استخدام docker، فهو مكتفٍ ذاتيًا تمامًا وله وضع بدون واجهة،\",\n \"ar|add `--help` parameter at the end of the docker run command for more information.\": \"أضف المعامل `--help` في نهاية أمر docker run للمزيد من المعلومات.\",\n \"ar|\\\"I'm getting a truncated audio issue!\\\" - PLEASE MAKE AN ISSUE OF THIS,\": \"\\\"أواجه مشكلة في انقطاع الصوت!\\\" - يرجى إنشاء ISSUE حول هذا،\",\n \"ar|we don't speak every language and need advise from users to fine tune the sentence splitting logic.😊\": \"نحن لا نتحدث كل لغة ونحتاج إلى نصيحة من المستخدمين لضبط منطق تقسيم الجمل بدقة.😊\",\n \"ar|***** ROADMAP *****\": \"***** خارطة الطريق *****\",\n \"ar|All Features open to public Contributions ⭐\": \"جميع الميزات مفتوحة للمساهمات العامة ⭐\",\n \"ar|Any help from people speaking any of the supported languages to help us improve the models ⭐\": \"أي مساعدة من أشخاص يتحدثون أيًا من اللغات المدعومة لمساعدتنا في تحسين النماذج ⭐\",\n \"ar|Preview Blocks/Chapters before to start the conversion\": \"معاينة الكتل/الفصول قبل بدء التحويل\",\n \"ar|Edit by sentence converted for surgical text change\": \"التحرير لكل جملة محوّلة لتغيير نصي دقيق\",\n \"ar|SML tags integration for voice, pause, break, and more changes \": \"دمج وسوم SML للصوت والتوقف والفاصل والمزيد من التغييرات \",\n \"ar|-h -help parameter info in different languages\": \"معلومات معاملات -h -help بلغات مختلفة\",\n \"ar|OCR scanning for PDF / JPG / BMP / PNG / TIFF\": \"مسح OCR لملفات PDF / JPG / BMP / PNG / TIFF\",\n \"ar|Notebooks Folder [Talked about here](https://github.com/DrewThomasson/ebook2audiobookXTTS/issues/5#issuecomment-2408773254)\": \"مجلد Notebooks [Talked about here](https://github.com/DrewThomasson/ebook2audiobookXTTS/issues/5#issuecomment-2408773254)\",\n \"ar|Make Chinese text splitting not split words and improve pause timing [Talked about here](https://github.com/DrewThomasson/ebook2audiobookXTTS/issues/18#issuecomment-2401154894)\": \"جعل تقسيم النص الصيني لا يقسم الكلمات وتحسين توقيت الفواصل [Talked about here](https://github.com/DrewThomasson/ebook2audiobookXTTS/issues/18#issuecomment-2401154894)\",\n \"ar|Kaggle Notebook\": \"دفتر Kaggle\",\n \"ar|Google Colab Notebook\": \"دفتر Google Colab\",\n \"ar|[Make a IOS app](https://github.com/DrewThomasson/ebook2audiobook/pull/35#issuecomment-2496495212)\": \"[إنشاء تطبيق iOS](https://github.com/DrewThomasson/ebook2audiobook/pull/35#issuecomment-2496495212)\",\n \"ar|[Make an android app](https://github.com/DrewThomasson/ebook2audiobook/pull/35#issuecomment-2496495212)\": \"[إنشاء تطبيق android](https://github.com/DrewThomasson/ebook2audiobook/pull/35#issuecomment-2496495212)\",\n \"ar|Audiobookshelf integration\": \"دمج Audiobookshelf\",\n \"ar|Extra Options\": \"خيارات إضافية\",\n \"ar|Ebook Translation option\": \"خيار ترجمة الكتاب الإلكتروني\",\n \"ar|Output format choices\": \"خيارات صيغة الإخراج\",\n \"ar|Batch ebook folder\": \"مجلد كتب إلكترونية دفعي\",\n \"ar|Multiprocessing conversion\": \"تحويل متعدد المعالجة\",\n \"ar|Batch ebook folder conversion\": \"تحويل مجلد كتب إلكترونية دفعي\",\n \"ar|GPU Device detection\": \"اكتشاف جهاز GPU\",\n \"ar|Denoise any reference audio for upload voice cloning,\": \"إزالة الضوضاء من أي صوت مرجعي لرفع استنساخ الصوت،\",\n \"ar|Custom model upload (XTTSv2 only for now. more on request)\": \"رفع نموذج مخصص (XTTSv2 فقط حاليًا. المزيد عند الطلب)\",\n \"ar|Add European Portuguese language model for xttsv2, fairseq, vits, piper at least (help welcome)\": \"إضافة نموذج لغة البرتغالية الأوروبية على الأقل لـ xttsv2 وfairseq وvits وpiper (المساعدة مرحب بها)\",\n \"ar|Add Sindhi language model for xttsv2, fairseq, vits, piper at least (help welcome)\": \"إضافة نموذج لغة السندية على الأقل لـ xttsv2 وfairseq وvits وpiper (المساعدة مرحب بها)\",\n \"ar|Readme Translation\": \"ترجمة Readme\",\n \"ar|🐍 OS Compatibility\": \"🐍 توافق نظام التشغيل\",\n \"ar|Extra Overkill for training models and such (All supported Coqui-tts models and piper-tts in one easy command) \": \"مبالغة إضافية لتدريب النماذج وما شابه (جميع نماذج Coqui-tts المدعومة وpiper-tts في أمر واحد سهل) \",\n \"ar|For info about this @DrewThomasson, he is currently working on the development of this, [work-in-progress-repo here](https://github.com/DrewThomasson/Universal_TTS_Finetune)\": \"للمعلومات حول هذا @DrewThomasson، يعمل حاليًا على تطويره، [المستودع قيد العمل هنا](https://github.com/DrewThomasson/Universal_TTS_Finetune)\",\n \"ar|Make a easy to use training gui for all coqui-tts models in the ljspeech format training recipes [here from coqui tts](https://github.com/coqui-ai/TTS/tree/dev/recipes/ljspeech)\": \"إنشاء واجهة تدريب سهلة الاستخدام لجميع نماذج coqui-tts في وصفات التدريب بصيغة ljspeech [هنا من coqui tts](https://github.com/coqui-ai/TTS/tree/dev/recipes/ljspeech)\",\n \"ar|Python Code normalization information for contributors\": \"معلومات تسوية كود Python للمساهمين\",\n \"ar|no blank line between code, unless between functions and classes.\": \"لا سطر فارغ بين الكود، باستثناء بين الدوال والفئات.\",\n \"ar|single quote used for all key unless for dict() and json. dict['key'] always called with single quote\": \"تُستخدم علامات الاقتباس المفردة لجميع المفاتيح باستثناء dict() وjson. يتم استدعاء dict['key'] دائمًا بعلامات اقتباس مفردة\",\n \"ar|4 spaces indentation, not tab at all\": \"مسافة بادئة من 4 مسافات، دون أي علامات جدولة على الإطلاق\",\n \"ar|strict typing for all functions and its arguments declaration and return values\": \"كتابة صارمة للأنواع لجميع الدوال وإعلان وسائطها وقيم إرجاعها\",\n \"ar|no space between the argument and its typing, no space between the function, the \\\"->\\\" and the return value\": \"لا مسافة بين الوسيط وكتابة نوعه، لا مسافة بين الدالة و\\\"->\\\" وقيمة الإرجاع\",\n \"ar|Example:\": \"مثال:\",\n \"ar|Hardware donation for beta tests wanted\": \"مطلوب تبرع بالعتاد لاختبارات بيتا\",\n \"ar|We accept any kind of hardware to test our development like:\": \"نقبل أي نوع من العتاد لاختبار تطويرنا مثل:\",\n \"ar|@DrewThomasson if you want to help out at all! 😃\": \"@DrewThomasson إذا كنت ترغب في المساعدة بأي شكل من الأشكال! 😃\",\n \"ar|Do you need to rent a GPU to boost service from us?\": \"هل تحتاج إلى استئجار GPU لتعزيز خدمتنا؟\",\n \"ar|A poll is open here https://github.com/DrewThomasson/ebook2audiobook/discussions/889\": \"استطلاع رأي مفتوح هنا https://github.com/DrewThomasson/ebook2audiobook/discussions/889\",\n \"ar|Special Thanks\": \"شكر خاص\",\n \"ar|[@shakenbake15 for better chapter saving method](https://github.com/DrewThomasson/ebook2audiobook/issues/8) \": \"[@shakenbake15 لطريقة أفضل لحفظ الفصول](https://github.com/DrewThomasson/ebook2audiobook/issues/8) \",\n \"ar|TTS engines\": \"محركات TTS\",\n \"ar|XTTSv2\": \"XTTSv2\",\n \"ar|Bark\": \"ﺡﺎﺒﻧ\",\n \"ar|Fairseq\": \"فيرسيك\",\n \"ar|VITS\": \"فيتس\",\n \"ar|Tacotron2\": \"تاكوترون 2\",\n \"ar|YourTTS\": \"YourTTS\",\n \"ar|Tortoise\": \"لون السلحفاة\",\n \"ar|GlowTTS\": \"GlowTTS\",\n \"ar|Piper\": \"الفلفل الأسود\",\n \"ar|GPT-SoVITS (https://github.com/RVC-Boss/GPT-SoVITS)\": \"GPT - SoVITS (https://github.com/RVC-Boss/GPT-SoVITS)\",\n \"ar|OpenVoice (https://github.com/myshell-ai/OpenVoice)\": \"OpenVoice (https://github.com/myshell-ai/OpenVoice)\",\n \"ar|fish-speech (https://github.com/fishaudio/fish-speech)\": \"كلام السمكة (https://github.com/fishaudio/fish-speech)\",\n \"ar|ChatTTS (https://github.com/2noise/ChatTTS)\": \"ChatTTS (https://github.com/2noise/ChatTTS)\",\n \"ar|CosyVoice (https://github.com/FunAudioLLM/CosyVoice)\": \"CosyVoice (https://github.com/FunAudioLLM/CosyVoice)\",\n \"ar|F5-TTS (https://github.com/swivid/f5-tts)\": \"F5 - TTS (https://github.com/swivid/f5-tts)\",\n \"ar|chatterbox (https://github.com/resemble-ai/chatterbox)\": \"chatterbox (https://github.com/resemble-ai/chatterbox)\",\n \"ar|Supertonic (https://github.com/supertone-inc/supertonic)\": \"Supertonic (https://github.com/supertone-inc/supertonic)\",\n \"ar|Spark-TTS (https://github.com/sparkaudio/spark-tts)\": \"Spark - TTS (https://github.com/sparkaudio/spark-tts)\",\n \"ar|index-tts (https://github.com/index-tts/index-tts)\": \"index - tts (https://github.com/index-tts/index-tts)\",\n \"ar|MeloTTS (https://github.com/myshell-ai/MeloTTS)\": \"MeloTTS (https://github.com/myshell-ai/MeloTTS)\",\n \"ar|Kokoro-TTS (https://github.com/hexgrad/kokoro)\": \"Kokoro - TTS (https://github.com/hexgrad/kokoro)\",\n \"ar|OmniVoice (https://github.com/k2-fsa/OmniVoice)\": \"OmniVoice (https://github.com/k2-fsa/OmniVoice)\",\n \"ar|Zonos (https://github.com/Zyphra/Zonos)\": \"زونوس (https://github.com/Zyphra/Zonos)\",\n \"ar|Style-TTS2 (https://github.com/yl4579/StyleTTS2)\": \"Style - TTS2 (https://github.com/yl4579/StyleTTS2)\",\n \"ar|Orpheus-TTS (https://github.com/canopyai/Orpheus-TTS)\": \"Orpheus - TTS (https://github.com/canopyai/Orpheus-TTS)\",\n \"ar|NewTTS (https://github.com/neuphonic/neutts?tab=readme-ov-file)\": \"NewTTS (https://github.com/neuphonic/neutts?tab=readme-ov-file)\",\n \"ar|VIbeVoice (https://github.com/vibevoice-community/VibeVoice)\": \"VIbeVoice (https://github.com/vibevoice-community/VibeVoice)\",\n \"ar|Qwen3-TTS (https://huggingface.co/spaces/Qwen/Qwen3-TTS)\": \"Qwen3 - TTS (https://huggingface.co/spaces/Qwen/Qwen3-TTS)\",\n \"zh-CN|CPU/GPU Converter from E-Book to audiobook with chapters and metadata
\": \"将电子书转换为带有章节和元数据的有声书的 CPU/GPU 转换器
\",\n \"zh-CN|using advanced TTS engines and much more.
\": \"使用先进的 TTS 引擎等。
\",\n \"zh-CN|Supports voice cloning and 1158 languages!\": \"支持语音克隆和 1158 种语言！\",\n \"zh-CN|**This tool is intended for use with non-DRM, legally acquired eBooks only.**
\": \"**本工具仅供与合法获取的无 DRM 电子书一起使用。**
\",\n \"zh-CN|The authors are not responsible for any misuse of this software or any resulting legal consequences.
\": \"作者对本软件的任何滥用或由此产生的任何法律后果概不负责。
\",\n \"zh-CN|Use this tool responsibly and in accordance with all applicable laws.\": \"请负责任地使用本工具，并遵守所有适用的法律。\",\n \"zh-CN|Thanks to support ebook2audiobook developers!\": \"感谢您支持 ebook2audiobook 的开发者！\",\n \"zh-CN|Run locally\": \"本地运行\",\n \"zh-CN|Run Remotely\": \"远程运行\",\n \"zh-CN|GUI Interface\": \"图形界面（GUI）\",\n \"zh-CN|Click to see images of Web GUI\": \"点击查看 Web GUI 图像\",\n \"zh-CN|Demos\": \"演示\",\n \"zh-CN|**New Default Voice Demo** \": \"**新默认语音演示** \",\n \"zh-CN|More Demos\": \"更多演示\",\n \"zh-CN|**ASMR Voice** \": \"**ASMR 语音** \",\n \"zh-CN|**Rainy Day Voice** \": \"**雨天语音** \",\n \"zh-CN|**Scarlett Voice**\": \"**斯嘉丽语音**\",\n \"zh-CN|**David Attenborough Voice** \": \"**大卫·阿滕伯勒语音** \",\n \"zh-CN|**Example**\": \"**示例**\",\n \"zh-CN|Table of Contents\": \"目录\",\n \"zh-CN|[Features](#features)\": \"[功能](#features)\",\n \"zh-CN|[GUI Interface](#gui-interface)\": \"[图形界面](#gui-interface)\",\n \"zh-CN|[Demos](#demos)\": \"[演示](#demos)\",\n \"zh-CN|[Supported Languages](#supported-languages)\": \"[支持的语言](#supported-languages)\",\n \"zh-CN|[Minimum Requirements](#hardware-requirements)\": \"[最低要求](#hardware-requirements)\",\n \"zh-CN|[Usage](#instructions)\": \"[用法](#instructions)\",\n \"zh-CN|[Run Locally](#instructions)\": \"[本地运行](#instructions)\",\n \"zh-CN|[Launching Gradio Web Interface](#instructions)\": \"[启动 Gradio Web 界面](#instructions)\",\n \"zh-CN|[Basic Headless Usage](#basic-usage)\": \"[基本 Headless 用法](#basic-usage)\",\n \"zh-CN|[Headless Custom XTTS Model Usage](#example-of-custom-model-zip-upload)\": \"[Headless 自定义 XTTS 模型用法](#example-of-custom-model-zip-upload)\",\n \"zh-CN|[Help command output](#help-command-output)\": \"[帮助命令输出](#help-command-output)\",\n \"zh-CN|[Run Remotely](#run-remotely)\": \"[远程运行](#run-remotely)\",\n \"zh-CN|[Steps to Run](#docker)\": \"[运行步骤](#docker)\",\n \"zh-CN|[Common Docker Issues](#common-docker-issues)\": \"[常见的 Docker 问题](#common-docker-issues)\",\n \"zh-CN|[Fine Tuned TTS models](#fine-tuned-tts-models)\": \"[微调 TTS 模型](#fine-tuned-tts-models)\",\n \"zh-CN|[Collection of Fine-Tuned TTS Models](#fine-tuned-tts-collection)\": \"[微调 TTS 模型集合](#fine-tuned-tts-collection)\",\n \"zh-CN|[Train XTTSv2](#fine-tune-your-own-xttsv2-model)\": \"[训练 XTTSv2](#fine-tune-your-own-xttsv2-model)\",\n \"zh-CN|[Supported eBook Formats](#supported-ebook-formats)\": \"[支持的电子书格式](#supported-ebook-formats)\",\n \"zh-CN|[Output Formats](#output-and-process-formats)\": \"[输出格式](#output-and-process-formats)\",\n \"zh-CN|[Revert to older Version](#reverting-to-older-versions)\": \"[还原到较旧版本](#reverting-to-older-versions)\",\n \"zh-CN|[Common Issues](#common-issues)\": \"[常见问题](#common-issues)\",\n \"zh-CN|[Special Thanks](#special-thanks)\": \"[特别鸣谢](#special-thanks)\",\n \"zh-CN|[Table of Contents](#table-of-contents)\": \"[目录](#table-of-contents)\",\n \"zh-CN|Features\": \"功能\",\n \"zh-CN|🔧 **TTS Engines supported**: `XTTSv2`, `Bark`, `Fairseq`, `VITS`, `Tacotron2`, `Tortoise`, `GlowTTS`, `YourTTS`\": \"🔧 **支持的 TTS 引擎**： `XTTSv2`, `Bark`, `Fairseq`, `VITS`, `Tacotron2`, `Tortoise`, `GlowTTS`, `YourTTS`\",\n \"zh-CN|📚 **Convert multiple file formats**: `.epub`, `.mobi`, `.azw3`, `.fb2`, `.lrf`, `.rb`, `.snb`, `.tcr`, `.pdf`, `.txt`, `.rtf`, `.doc`, `.docx`, `.html`, `.odt`, `.azw`, `.tiff`, `.tif`, `.png`, `.jpg`, `.jpeg`, `.bmp`, `.zip`\": \"📚 **转换多种文件格式**： `.epub`, `.mobi`, `.azw3`, `.fb2`, `.lrf`, `.rb`, `.snb`, `.tcr`, `.pdf`, `.txt`, `.rtf`, `.doc`, `.docx`, `.html`, `.odt`, `.azw`, `.tiff`, `.tif`, `.png`, `.jpg`, `.jpeg`, `.bmp`, `.zip`\",\n \"zh-CN|💻 **TextArea** to convert directly a short text in audio\": \"💻 用于直接将短文本转换为音频的**文本区域**\",\n \"zh-CN|🔍 **OCR scanning** for files with text pages as images\": \"🔍 针对文本页面为图像的文件的 **OCR 扫描**\",\n \"zh-CN|🔊 **High-quality text-to-speech** from near realtime to near real voice\": \"🔊 **高质量文本转语音**，从接近实时到接近真实的语音\",\n \"zh-CN|🗣️ **Optional voice cloning** using your own voice file\": \"🗣️ 使用您自己的语音文件进行**可选的语音克隆**\",\n \"zh-CN|🌐 **Supports 1158 languages** ([supported languages list](https://dl.fbaipublicfiles.com/mms/tts/all-tts-languages.html))\": \"🌐 **支持 1158 种语言** ([supported languages list](https://dl.fbaipublicfiles.com/mms/tts/all-tts-languages.html))\",\n \"zh-CN|💻 **Low-resource friendly** — runs on **2 GB RAM / 1 GB VRAM (minimum)**\": \"💻 **低资源友好** — 可在 **2 GB RAM / 1 GB VRAM（最低）** 上运行\",\n \"zh-CN|🎵 **Audiobook output formats**: mono or stereo `aac`, `flac`, `mp3`, `m4b`, `m4a`, `mp4`, `mov`, `ogg`, `wav`, `webm`\": \"🎵 **有声书输出格式**： mono or stereo `aac`, `flac`, `mp3`, `m4b`, `m4a`, `mp4`, `mov`, `ogg`, `wav`, `webm`\",\n \"zh-CN|🧠 **SML tags supported** — fine-grained control of breaks, pauses, voice switching and more ([see below](#sml-tags-available))\": \"🧠 **支持 SML 标签** — 对中断、停顿、语音切换等进行精细控制 ([see below](#sml-tags-available))\",\n \"zh-CN|🧩 **Optional custom model** using your own trained model (XTTSv2, VITS, FAIRSEQ, PIPER, others on request)\": \"🧩 使用您自己训练的模型的**可选自定义模型** (XTTSv2, VITS, FAIRSEQ, PIPER, others on request)\",\n \"zh-CN|🎛️ **Fine-tuned preset models** trained by the E2A Team
\": \"🎛️ 由 E2A 团队训练的**微调预设模型**
\",\n \"zh-CN|(Contact us if you need additional fine-tuned models, or if you’d like to share yours to the official preset list)\": \"（如果您需要额外的微调模型，或者如果您想在官方预设列表中分享您自己的模型，请联系我们）\",\n \"zh-CN|Hardware Requirements\": \"硬件要求\",\n \"zh-CN|2GB RAM min, 8GB recommended.\": \"RAM 最低 2GB，推荐 8GB。\",\n \"zh-CN|1GB VRAM min, 4GB recommended.\": \"VRAM 最低 1GB，推荐 4GB。\",\n \"zh-CN|Virtualization enabled if running on windows (Docker only).\": \"在 windows 上运行时启用虚拟化（仅限 Docker）。\",\n \"zh-CN|CPU, XPU (intel, AMD, ARM)*.\": \"CPU、XPU（intel、AMD、ARM）*。\",\n \"zh-CN|CUDA, ROCm, JETSON\": \"CUDA、ROCm、JETSON\",\n \"zh-CN|MPS (Apple Silicon CPU)\": \"MPS（Apple Silicon CPU）\",\n \"zh-CN|* Modern TTS engines are very slow on CPU, so use lower quality TTS like YourTTS, Tacotron2 etc..\": \"* 现代 TTS 引擎在 CPU 上非常慢，因此请使用质量较低的 TTS，如 YourTTS、Tacotron2 等。\",\n \"zh-CN|Supported Languages\": \"支持的语言\",\n \"zh-CN|[**+1130 languages and dialects here**](https://dl.fbaipublicfiles.com/mms/tts/all-tts-languages.html)\": \"[**此处有 +1130 种语言和方言**](https://dl.fbaipublicfiles.com/mms/tts/all-tts-languages.html)\",\n \"zh-CN|Supported eBook Formats\": \"支持的电子书格式\",\n \"zh-CN|**Best results**: `.epub` or `.mobi` for automatic chapter detection\": \"**最佳效果**：使用 `.epub` 或 `.mobi` 进行自动章节检测\",\n \"zh-CN|Output and process Formats\": \"输出和处理格式\",\n \"zh-CN|Process format can be changed in lib/conf.py\": \"处理格式可在 lib/conf.py 中更改\",\n \"zh-CN|SML tags available\": \"可用的 SML 标签\",\n \"zh-CN|`[break]` — silence (random range **0.3–0.6 sec.**)\": \"`[break]` — 静音（随机范围 **0.3–0.6 sec.**）\",\n \"zh-CN|`[pause]` — silence (random range **1.0–1.6 sec.**)\": \"`[pause]` — 静音（随机范围 **1.0–1.6 sec.**）\",\n \"zh-CN|`[pause:N]` — fixed pause (**N sec.**)\": \"`[pause:N]` — 固定停顿（**N sec.**）\",\n \"zh-CN|`[voice:/path/to/voice/file]...[/voice]` — switch voice from default or selected voice from GUI/CLI\": \"`[voice:/path/to/voice/file]...[/voice]` — 从默认语音或从 GUI/CLI 选择的语音切换语音\",\n \"zh-CN|**Check our other repo dedicated to add SML automatically in your ebook -> [E2A-SML](./tools/E2A-SML)**\": \"**请查看我们另一个专门用于在电子书中自动添加 SML 的仓库 -> [E2A-SML](./tools/E2A-SML)**\",\n \"zh-CN|**Before to post an install or bug issue search carefully to the opened and closed issues TAB
\": \"**在发布安装或错误问题之前，请仔细搜索打开和已关闭问题的标签页
\",\n \"zh-CN|to be sure your issue does not exist already.**\": \"以确保您的问题尚不存在。**\",\n \"zh-CN|**EPUB format lacks any standard structure like what is a chapter, paragraph, preface etc.
\": \"**EPUB 格式缺乏任何定义什么是章节、段落、前言等的标准结构。
\",\n \"zh-CN|So you should first remove manually any text you don't want to be converted in audio.**\": \"因此，您应该首先手动删除任何不想转换为音频的文本。**\",\n \"zh-CN|**Install / Run ebook2audiobook**:\": \"**安装 / 运行 ebook2audiobook**：\",\n \"zh-CN|**Mac Launcher** \": \"**Mac 启动器** \",\n \"zh-CN|Double click `Mac Ebook2Audiobook Launcher.command`\": \"双击 `Mac Ebook2Audiobook Launcher.command`\",\n \"zh-CN|Note for Windows users: scoop is installed to install missing programs without administrator privileges.\": \"Windows 用户注意：将安装 scoop 以在没有管理员权限的情况下安装缺失的程序。\",\n \"zh-CN|**Open the Web App**: Click the URL provided in the terminal to access the web app and convert eBooks. `http://localhost:7860/`\": \"**打开 Web 应用**：点击终端中提供的 URL，以访问 Web 应用并转换电子书。 `http://localhost:7860/`\",\n \"zh-CN|**For Public Link**:\": \"**获取公共链接**：\",\n \"zh-CN|**If the script is stopped and run again, you need to refresh your gradio GUI interface
\": \"**如果脚本被停止并再次运行，您需要刷新您的 Gradio GUI 界面
\",\n \"zh-CN|to let the web page reconnect to the new connection socket.**\": \"以便网页能够重新连接到新的连接套接字。**\",\n \"zh-CN|**[--ebook]**: Path to your eBook file\": \"**[--ebook]**：电子书文件的路径\",\n \"zh-CN|**[--voice]**: Voice cloning file path (optional)\": \"**[--voice]**：语音克隆文件路径（可选）\",\n \"zh-CN|**[--language]**: Language code in ISO-639-3 (i.e.: ita for italian, eng for english, deu for german...).
\": \"**[--language]**：ISO-639-3 格式的语言代码（即：意大利语为 ita，英语为 eng，德语为 deu...）。
\",\n \"zh-CN|Default language is eng and --language is optional for default language set in ./lib/lang.py.
\": \"默认语言为 eng，对于 ./lib/lang.py 中设置的默认语言，--language 是可选的。
\",\n \"zh-CN|The ISO-639-1 2 letters codes are also supported.\": \"也支持 2 个字母的 ISO-639-1 代码。\",\n \"zh-CN|****: Path to `model_name.zip` file,\": \"****：`model_name.zip` 文件的路径，\",\n \"zh-CN|which must contain (according to the tts engine) all the mandatory files
\": \"该文件必须（根据 tts 引擎）包含所有必需文件
\",\n \"zh-CN|(see ./lib/models.py).\": \"（参见 ./lib/models.py）。\",\n \"zh-CN|NOTE: in gradio/gui mode, to cancel a running conversion, just click on the [X] from the ebook upload component.\": \"注意：在 gradio/gui 模式下，要取消正在进行的转换，只需点击电子书上传组件的 [X] 即可。\",\n \"zh-CN|TIP: if it needs some more pause, add '[pause:3]' for 3 sec. etc.\": \"提示：如果需要稍长的停顿，请添加 '[pause:3]' 表示 3 秒等。\",\n \"zh-CN|Common Docker Issues\": \"常见的 Docker 问题\",\n \"zh-CN|My NVIDIA GPU isn't being detected?? -> [GPU ISSUES Wiki Page](https://github.com/DrewThomasson/ebook2audiobook/wiki/GPU-ISSUES)\": \"未检测到我的 NVIDIA GPU？？ -> [GPU 问题 Wiki 页面](https://github.com/DrewThomasson/ebook2audiobook/wiki/GPU-ISSUES)\",\n \"zh-CN|Fine Tuned TTS models\": \"微调（fine-tuned）TTS 模型\",\n \"zh-CN|Fine Tune your own XTTSv2 model\": \"微调您自己的 XTTSv2 模型\",\n \"zh-CN|De-noise training data\": \"训练数据降噪\",\n \"zh-CN|Fine Tuned TTS Collection\": \"微调 TTS 模型集合\",\n \"zh-CN|For an XTTSv2 custom model a ref audio clip of the voice reference is mandatory:\": \"对于自定义 XTTSv2 模型，必须提供语音的参考音频片段：\",\n \"zh-CN|Your own Ebook2Audiobook customization\": \"您自己的 Ebook2Audiobook 自定义\",\n \"zh-CN|You are free to modify libs/conf.py to add or remove the settings you wish. If you plan to do it just make\": \"您可以自由修改 libs/conf.py 以添加或删除您想要的设置。如果您打算这样做，只需制作\",\n \"zh-CN|a copy of the original conf.py so on each ebook2audiobook update you will backup your modified conf.py and put\": \"原始 conf.py 的副本，这样在每次更新 ebook2audiobook 时，您可以备份修改后的 conf.py 并恢复\",\n \"zh-CN|back the original one. You must plan the same process for models.py. If you wish to make your own custom model\": \"原始文件。您必须为 models.py 计划相同的流程。如果您想将自己的自定义模型\",\n \"zh-CN|as an official ebook2audiobook fine tuned model so please contact us and we'll add it to the presets list.\": \"变成官方微调的 ebook2audiobook 模型，请联系我们，我们会将其添加到预设列表中。\",\n \"zh-CN|Common Issues:\": \"常见问题：\",\n \"zh-CN|My NVIDIA/ROCm/XPU/MPS GPU isn't being detected?? -> [GPU ISSUES Wiki Page](https://github.com/DrewThomasson/ebook2audiobook/wiki/GPU-ISSUES)\": \"未检测到我的 NVIDIA/ROCm/XPU/MPS GPU？？ -> [GPU ISSUES Wiki Page](https://github.com/DrewThomasson/ebook2audiobook/wiki/GPU-ISSUES)\",\n \"zh-CN|CPU is slow (better on server smp CPU) while GPU can have almost real time conversion.\": \"CPU 很慢（在服务器 SMP CPU 上更好），而 GPU 可以实现接近实时的转换。\",\n \"zh-CN|(It doesn't have zero-shot voice cloning though, and is Siri quality voices, but it is much faster on cpu).\": \"（不过它没有 zero-shot 语音克隆，是 Siri 质量的语音，但在 cpu 上快得多）。\",\n \"zh-CN|\\\"I'm having dependency issues\\\" - Just use the docker, its fully self contained and has a headless mode,\": \"“我遇到依赖项问题” - 只需使用 docker，它完全独立并具有 headless 模式，\",\n \"zh-CN|add `--help` parameter at the end of the docker run command for more information.\": \"在 docker run 命令末尾添加 `--help` 参数以获取更多信息。\",\n \"zh-CN|\\\"I'm getting a truncated audio issue!\\\" - PLEASE MAKE AN ISSUE OF THIS,\": \"“我遇到音频被截断的问题！” - 请就此创建一个 ISSUE，\",\n \"zh-CN|we don't speak every language and need advise from users to fine tune the sentence splitting logic.😊\": \"我们不会说每种语言，需要用户的建议来微调句子拆分逻辑。😊\",\n \"zh-CN|***** ROADMAP *****\": \"***** 路线图 *****\",\n \"zh-CN|All Features open to public Contributions ⭐\": \"所有功能均向公众贡献开放 ⭐\",\n \"zh-CN|Any help from people speaking any of the supported languages to help us improve the models ⭐\": \"来自任何说支持语言的人的任何帮助，以帮助我们改进模型 ⭐\",\n \"zh-CN|Preview Blocks/Chapters before to start the conversion\": \"在开始转换之前预览块/章节\",\n \"zh-CN|Edit by sentence converted for surgical text change\": \"按转换后的句子进行编辑，以进行精准的文本更改\",\n \"zh-CN|SML tags integration for voice, pause, break, and more changes \": \"用于语音、停顿、中断及更多更改的 SML 标签集成 \",\n \"zh-CN|-h -help parameter info in different languages\": \"不同语言的 -h -help 参数信息\",\n \"zh-CN|OCR scanning for PDF / JPG / BMP / PNG / TIFF\": \"针对 PDF / JPG / BMP / PNG / TIFF 的 OCR 扫描\",\n \"zh-CN|Notebooks Folder [Talked about here](https://github.com/DrewThomasson/ebook2audiobookXTTS/issues/5#issuecomment-2408773254)\": \"Notebooks 文件夹 [Talked about here](https://github.com/DrewThomasson/ebook2audiobookXTTS/issues/5#issuecomment-2408773254)\",\n \"zh-CN|Make Chinese text splitting not split words and improve pause timing [Talked about here](https://github.com/DrewThomasson/ebook2audiobookXTTS/issues/18#issuecomment-2401154894)\": \"使中文文本拆分不拆分单词并改善停顿时间 [Talked about here](https://github.com/DrewThomasson/ebook2audiobookXTTS/issues/18#issuecomment-2401154894)\",\n \"zh-CN|[Make a IOS app](https://github.com/DrewThomasson/ebook2audiobook/pull/35#issuecomment-2496495212)\": \"[制作 iOS 应用](https://github.com/DrewThomasson/ebook2audiobook/pull/35#issuecomment-2496495212)\",\n \"zh-CN|[Make an android app](https://github.com/DrewThomasson/ebook2audiobook/pull/35#issuecomment-2496495212)\": \"[制作 android 应用](https://github.com/DrewThomasson/ebook2audiobook/pull/35#issuecomment-2496495212)\",\n \"zh-CN|Audiobookshelf integration\": \"Audiobookshelf 集成\",\n \"zh-CN|Extra Options\": \"额外选项\",\n \"zh-CN|Ebook Translation option\": \"电子书翻译选项\",\n \"zh-CN|Output format choices\": \"输出格式选择\",\n \"zh-CN|Batch ebook folder\": \"批量电子书文件夹\",\n \"zh-CN|Multiprocessing conversion\": \"多进程转换\",\n \"zh-CN|Batch ebook folder conversion\": \"批量电子书文件夹转换\",\n \"zh-CN|GPU Device detection\": \"GPU 设备检测\",\n \"zh-CN|Denoise any reference audio for upload voice cloning,\": \"为上传的语音克隆对任何参考音频进行降噪，\",\n \"zh-CN|Custom model upload (XTTSv2 only for now. more on request)\": \"自定义模型上传（目前仅 XTTSv2。更多应需求提供）\",\n \"zh-CN|Add European Portuguese language model for xttsv2, fairseq, vits, piper at least (help welcome)\": \"至少为 xttsv2、fairseq、vits、piper 添加欧洲葡萄牙语语言模型（欢迎帮助）\",\n \"zh-CN|Add Sindhi language model for xttsv2, fairseq, vits, piper at least (help welcome)\": \"至少为 xttsv2、fairseq、vits、piper 添加信德语语言模型（欢迎帮助）\",\n \"zh-CN|Readme Translation\": \"Readme 翻译\",\n \"zh-CN|🐍 OS Compatibility\": \"🐍 操作系统兼容性\",\n \"zh-CN|Extra Overkill for training models and such (All supported Coqui-tts models and piper-tts in one easy command) \": \"用于训练模型等的额外杀手锏（所有支持的 Coqui-tts 模型和 piper-tts 通过一条简单命令） \",\n \"zh-CN|For info about this @DrewThomasson, he is currently working on the development of this, [work-in-progress-repo here](https://github.com/DrewThomasson/Universal_TTS_Finetune)\": \"有关此信息 @DrewThomasson，他目前正在进行其开发，[正在进行中的仓库在此处](https://github.com/DrewThomasson/Universal_TTS_Finetune)\",\n \"zh-CN|Make a easy to use training gui for all coqui-tts models in the ljspeech format training recipes [here from coqui tts](https://github.com/coqui-ai/TTS/tree/dev/recipes/ljspeech)\": \"为 ljspeech 格式训练配方中的所有 coqui-tts 模型创建一个易于使用的训练 gui [此处来自 coqui tts](https://github.com/coqui-ai/TTS/tree/dev/recipes/ljspeech)\",\n \"zh-CN|Python Code normalization information for contributors\": \"面向贡献者的 Python 代码规范化信息\",\n \"zh-CN|no blank line between code, unless between functions and classes.\": \"代码之间没有空行，函数和类之间除外。\",\n \"zh-CN|single quote used for all key unless for dict() and json. dict['key'] always called with single quote\": \"除 dict() 和 json 外，所有键均使用单引号。dict['key'] 始终用单引号调用\",\n \"zh-CN|4 spaces indentation, not tab at all\": \"4 个空格缩进，完全不使用制表符\",\n \"zh-CN|strict typing for all functions and its arguments declaration and return values\": \"对所有函数及其参数和返回值声明进行严格类型标注\",\n \"zh-CN|no space between the argument and its typing, no space between the function, the \\\"->\\\" and the return value\": \"参数与其类型标注之间无空格，函数、“->”和返回值之间无空格\",\n \"zh-CN|Example:\": \"示例：\",\n \"zh-CN|Hardware donation for beta tests wanted\": \"征求用于测试版测试的硬件捐赠\",\n \"zh-CN|We accept any kind of hardware to test our development like:\": \"我们接受任何类型的硬件来测试我们的开发，例如：\",\n \"zh-CN|@DrewThomasson if you want to help out at all! 😃\": \"@DrewThomasson 如果您想以任何方式提供帮助！ 😃\",\n \"zh-CN|Do you need to rent a GPU to boost service from us?\": \"您需要租用 GPU 来增强我们的服务吗？\",\n \"zh-CN|A poll is open here https://github.com/DrewThomasson/ebook2audiobook/discussions/889\": \"此处已开放投票 https://github.com/DrewThomasson/ebook2audiobook/discussions/889\",\n \"zh-CN|Special Thanks\": \"特别鸣谢\",\n \"zh-CN|[@shakenbake15 for better chapter saving method](https://github.com/DrewThomasson/ebook2audiobook/issues/8) \": \"[@shakenbake15 提供了更好的章节保存方法](https://github.com/DrewThomasson/ebook2audiobook/issues/8) \",\n \"zh-CN|TTS engines\": \"TTS引擎\",\n \"zh-CN|XTTSv2\": \"XTTSv2\",\n \"zh-CN|Bark\": \"巴克\",\n \"zh-CN|Fairseq\": \"公平交易\",\n \"zh-CN|VITS\": \"VITS\",\n \"zh-CN|Tacotron2\": \"Tacotron2\",\n \"zh-CN|YourTTS\": \"YourTTS\",\n \"zh-CN|Tortoise\": \"陸龜\",\n \"zh-CN|GlowTTS\": \"GlowTTS\",\n \"zh-CN|Piper\": \"胡椒属\",\n \"zh-CN|GPT-SoVITS (https://github.com/RVC-Boss/GPT-SoVITS)\": \"GPT-SoVITS (https://github.com/RVC-Boss/GPT-SoVITS)\",\n \"zh-CN|OpenVoice (https://github.com/myshell-ai/OpenVoice)\": \"OpenVoice (https://github.com/myshell-ai/OpenVoice)\",\n \"zh-CN|fish-speech (https://github.com/fishaudio/fish-speech)\": \"fish-speech (https://github.com/fishaudio/fish-speech)\",\n \"zh-CN|ChatTTS (https://github.com/2noise/ChatTTS)\": \"ChatTTS (https://github.com/2noise/ChatTTS)\",\n \"zh-CN|CosyVoice (https://github.com/FunAudioLLM/CosyVoice)\": \"CosyVoice (https://github.com/FunAudioLLM/CosyVoice)\",\n \"zh-CN|F5-TTS (https://github.com/swivid/f5-tts)\": \"F5-TTS (https://github.com/swivid/f5-tts)\",\n \"zh-CN|chatterbox (https://github.com/resemble-ai/chatterbox)\": \"chatterbox (https://github.com/resemble-ai/chatterbox)\",\n \"zh-CN|Supertonic (https://github.com/supertone-inc/supertonic)\": \"Supertonic (https://github.com/supertone-inc/supertonic)\",\n \"zh-CN|Spark-TTS (https://github.com/sparkaudio/spark-tts)\": \"Spark-TTS (https://github.com/sparkaudio/spark-tts)\",\n \"zh-CN|index-tts (https://github.com/index-tts/index-tts)\": \"index-tts (https://github.com/index-tts/index-tts)\",\n \"zh-CN|MeloTTS (https://github.com/myshell-ai/MeloTTS)\": \"MeloTTS (https://github.com/myshell-ai/MeloTTS)\",\n \"zh-CN|Kokoro-TTS (https://github.com/hexgrad/kokoro)\": \"Kokoro-TTS (https://github.com/hexgrad/kokoro)\",\n \"zh-CN|OmniVoice (https://github.com/k2-fsa/OmniVoice)\": \"OmniVoice (https://github.com/k2-fsa/OmniVoice)\",\n \"zh-CN|Zonos (https://github.com/Zyphra/Zonos)\": \"Zonos (https://github.com/Zyphra/Zonos)\",\n \"zh-CN|Style-TTS2 (https://github.com/yl4579/StyleTTS2)\": \"样式-TTS2 (https://github.com/yl4579/StyleTTS2)\",\n \"zh-CN|Orpheus-TTS (https://github.com/canopyai/Orpheus-TTS)\": \"Orpheus-TTS (https://github.com/canopyai/Orpheus-TTS)\",\n \"zh-CN|NewTTS (https://github.com/neuphonic/neutts?tab=readme-ov-file)\": \"NewTTS (https://github.com/neuphonic/neutts?tab=readme-ov-file)\",\n \"zh-CN|VIbeVoice (https://github.com/vibevoice-community/VibeVoice)\": \"VIbeVoice (https://github.com/vibevoice-community/VibeVoice)\",\n \"zh-CN|Qwen3-TTS (https://huggingface.co/spaces/Qwen/Qwen3-TTS)\": \"Qwen3-TTS (https://huggingface.co/spaces/Qwen/Qwen3-TTS)\",\n \"es|CPU/GPU Converter from E-Book to audiobook with chapters and metadata
\": \"Conversor CPU/GPU de libro electrónico a audiolibro con capítulos y metadatos
\",\n \"es|using advanced TTS engines and much more.
\": \"usando motores TTS avanzados y mucho más.
\",\n \"es|Supports voice cloning and 1158 languages!\": \"¡Admite clonación de voz y 1158 idiomas!\",\n \"es|**This tool is intended for use with non-DRM, legally acquired eBooks only.**
\": \"**Esta herramienta está destinada a usarse únicamente con libros electrónicos sin DRM y adquiridos legalmente.**
\",\n \"es|The authors are not responsible for any misuse of this software or any resulting legal consequences.
\": \"Los autores no se hacen responsables de ningún uso indebido de este software ni de las consecuencias legales que de ello se deriven.
\",\n \"es|Use this tool responsibly and in accordance with all applicable laws.\": \"Utiliza esta herramienta de forma responsable y conforme a todas las leyes aplicables.\",\n \"es|Thanks to support ebook2audiobook developers!\": \"¡Gracias por apoyar a los desarrolladores de ebook2audiobook!\",\n \"es|Run locally\": \"Ejecución local\",\n \"es|Run Remotely\": \"Ejecución remota\",\n \"es|GUI Interface\": \"Interfaz gráfica (GUI)\",\n \"es|Click to see images of Web GUI\": \"Haz clic para ver imágenes de la GUI web\",\n \"es|**New Default Voice Demo** \": \"**Demo de la nueva voz por defecto** \",\n \"es|More Demos\": \"Más demos\",\n \"es|**ASMR Voice** \": \"**Voz ASMR** \",\n \"es|**Rainy Day Voice** \": \"**Voz de día lluvioso** \",\n \"es|**Scarlett Voice**\": \"**Voz Scarlett**\",\n \"es|**David Attenborough Voice** \": \"**Voz David Attenborough** \",\n \"es|**Example**\": \"**Ejemplo**\",\n \"es|Table of Contents\": \"Tabla de contenidos\",\n \"es|[Features](#features)\": \"[Características](#features)\",\n \"es|[GUI Interface](#gui-interface)\": \"[Interfaz gráfica](#gui-interface)\",\n \"es|[Supported Languages](#supported-languages)\": \"[Idiomas admitidos](#supported-languages)\",\n \"es|[Minimum Requirements](#hardware-requirements)\": \"[Requisitos mínimos](#hardware-requirements)\",\n \"es|[Usage](#instructions)\": \"[Uso](#instructions)\",\n \"es|[Run Locally](#instructions)\": \"[Ejecución local](#instructions)\",\n \"es|[Launching Gradio Web Interface](#instructions)\": \"[Lanzar la interfaz web de Gradio](#instructions)\",\n \"es|[Basic Headless Usage](#basic-usage)\": \"[Uso básico sin interfaz (headless)](#basic-usage)\",\n \"es|[Headless Custom XTTS Model Usage](#example-of-custom-model-zip-upload)\": \"[Uso de modelo XTTS personalizado sin interfaz](#example-of-custom-model-zip-upload)\",\n \"es|[Help command output](#help-command-output)\": \"[Salida del comando de ayuda](#help-command-output)\",\n \"es|[Run Remotely](#run-remotely)\": \"[Ejecución remota](#run-remotely)\",\n \"es|[Steps to Run](#docker)\": \"[Pasos para ejecutar](#docker)\",\n \"es|[Common Docker Issues](#common-docker-issues)\": \"[Problemas habituales con Docker](#common-docker-issues)\",\n \"es|[Fine Tuned TTS models](#fine-tuned-tts-models)\": \"[Modelos TTS ajustados](#fine-tuned-tts-models)\",\n \"es|[Collection of Fine-Tuned TTS Models](#fine-tuned-tts-collection)\": \"[Colección de modelos TTS ajustados](#fine-tuned-tts-collection)\",\n \"es|[Train XTTSv2](#fine-tune-your-own-xttsv2-model)\": \"[Entrenar XTTSv2](#fine-tune-your-own-xttsv2-model)\",\n \"es|[Supported eBook Formats](#supported-ebook-formats)\": \"[Formatos de libro electrónico admitidos](#supported-ebook-formats)\",\n \"es|[Output Formats](#output-and-process-formats)\": \"[Formatos de salida](#output-and-process-formats)\",\n \"es|[Revert to older Version](#reverting-to-older-versions)\": \"[Volver a una versión anterior](#reverting-to-older-versions)\",\n \"es|[Common Issues](#common-issues)\": \"[Problemas habituales](#common-issues)\",\n \"es|[Special Thanks](#special-thanks)\": \"[Agradecimientos especiales](#special-thanks)\",\n \"es|[Table of Contents](#table-of-contents)\": \"[Tabla de contenidos](#table-of-contents)\",\n \"es|Features\": \"Características\",\n \"es|🔧 **TTS Engines supported**: `XTTSv2`, `Bark`, `Fairseq`, `VITS`, `Tacotron2`, `Tortoise`, `GlowTTS`, `YourTTS`\": \"🔧 **Motores TTS admitidos**: `XTTSv2`, `Bark`, `Fairseq`, `VITS`, `Tacotron2`, `Tortoise`, `GlowTTS`, `YourTTS`\",\n \"es|📚 **Convert multiple file formats**: `.epub`, `.mobi`, `.azw3`, `.fb2`, `.lrf`, `.rb`, `.snb`, `.tcr`, `.pdf`, `.txt`, `.rtf`, `.doc`, `.docx`, `.html`, `.odt`, `.azw`, `.tiff`, `.tif`, `.png`, `.jpg`, `.jpeg`, `.bmp`, `.zip`\": \"📚 **Convertir múltiples formatos de archivo**: `.epub`, `.mobi`, `.azw3`, `.fb2`, `.lrf`, `.rb`, `.snb`, `.tcr`, `.pdf`, `.txt`, `.rtf`, `.doc`, `.docx`, `.html`, `.odt`, `.azw`, `.tiff`, `.tif`, `.png`, `.jpg`, `.jpeg`, `.bmp`, `.zip`\",\n \"es|💻 **TextArea** to convert directly a short text in audio\": \"💻 **Área de texto** para convertir directamente un texto corto en audio\",\n \"es|🔍 **OCR scanning** for files with text pages as images\": \"🔍 **Escaneo OCR** para archivos con páginas de texto en forma de imágenes\",\n \"es|🔊 **High-quality text-to-speech** from near realtime to near real voice\": \"🔊 **Texto a voz de alta calidad**, desde casi en tiempo real hasta una voz casi real\",\n \"es|🗣️ **Optional voice cloning** using your own voice file\": \"🗣️ **Clonación de voz opcional** usando tu propio archivo de voz\",\n \"es|🌐 **Supports 1158 languages** ([supported languages list](https://dl.fbaipublicfiles.com/mms/tts/all-tts-languages.html))\": \"🌐 **Admite 1158 idiomas** ([supported languages list](https://dl.fbaipublicfiles.com/mms/tts/all-tts-languages.html))\",\n \"es|💻 **Low-resource friendly** — runs on **2 GB RAM / 1 GB VRAM (minimum)**\": \"💻 **Apto para recursos limitados** — funciona con **2 GB de RAM / 1 GB de VRAM (mínimo)**\",\n \"es|🎵 **Audiobook output formats**: mono or stereo `aac`, `flac`, `mp3`, `m4b`, `m4a`, `mp4`, `mov`, `ogg`, `wav`, `webm`\": \"🎵 **Formatos de salida del audiolibro**: mono or stereo `aac`, `flac`, `mp3`, `m4b`, `m4a`, `mp4`, `mov`, `ogg`, `wav`, `webm`\",\n \"es|🧠 **SML tags supported** — fine-grained control of breaks, pauses, voice switching and more ([see below](#sml-tags-available))\": \"🧠 **Etiquetas SML admitidas** — control preciso de cortes, pausas, cambio de voz y mucho más ([see below](#sml-tags-available))\",\n \"es|🧩 **Optional custom model** using your own trained model (XTTSv2, VITS, FAIRSEQ, PIPER, others on request)\": \"🧩 **Modelo personalizado opcional** usando tu propio modelo entrenado (XTTSv2, VITS, FAIRSEQ, PIPER, others on request)\",\n \"es|🎛️ **Fine-tuned preset models** trained by the E2A Team
\": \"🎛️ **Modelos preajustados y ajustados** entrenados por el equipo de E2A
\",\n \"es|(Contact us if you need additional fine-tuned models, or if you’d like to share yours to the official preset list)\": \"(Contáctanos si necesitas modelos ajustados adicionales, o si quieres compartir los tuyos en la lista oficial de preajustes)\",\n \"es|Hardware Requirements\": \"Requisitos de hardware\",\n \"es|2GB RAM min, 8GB recommended.\": \"2 GB de RAM mín., 8 GB recomendados.\",\n \"es|1GB VRAM min, 4GB recommended.\": \"1 GB de VRAM mín., 4 GB recomendados.\",\n \"es|Virtualization enabled if running on windows (Docker only).\": \"Virtualización habilitada si se ejecuta en Windows (solo Docker).\",\n \"es|MPS (Apple Silicon CPU)\": \"MPS (CPU Apple Silicon)\",\n \"es|* Modern TTS engines are ve"},"files":{"tools/readme_i18n/baseline_README.md":"# 📚 ebook2audiobook (E2A)\n\n\nCPU/GPU Converter from E-Book to audiobook with chapters and metadata
\nusing advanced TTS engines and much more.
\nSupports voice cloning and 1158 languages!\n> [!IMPORTANT]\n**This tool is intended for use with non-DRM, legally acquired eBooks only.**
\nThe authors are not responsible for any misuse of this software or any resulting legal consequences.
\nUse this tool responsibly and in accordance with all applicable laws.\n\n[](https://discord.gg/63Tv3F65k6)\n\n### Thanks to support ebook2audiobook developers!\n[](https://ko-fi.com/athomasson2) \n\n### Run locally\n\n[](#instructions)\n\n[](https://github.com/DrewThomasson/ebook2audiobook/actions/workflows/Docker-Build.yml) [](https://github.com/DrewThomasson/ebook2audiobook/releases/latest) \n\n\n\n \n\n\n\n\n### Run Remotely\n[](https://huggingface.co/spaces/drewThomasson/ebook2audiobook)\n[](https://colab.research.google.com/github/DrewThomasson/ebook2audiobook/blob/main/Notebooks/colab_ebook2audiobook.ipynb) [](https://github.com/Rihcus/ebook2audiobookXTTS/blob/main/Notebooks/kaggle-ebook2audiobook.ipynb)\n\n#### GUI Interface\n\n\n\n Click to see images of Web GUI
\n \n \n \n \n\n## Demos\n\n**New Default Voice Demo** \n\nhttps://github.com/user-attachments/assets/750035dc-e355-46f1-9286-05c1d9e88cea \n\n\n More Demos
\n\n**ASMR Voice** \n\nhttps://github.com/user-attachments/assets/68eee9a1-6f71-4903-aacd-47397e47e422\n\n**Rainy Day Voice** \n\nhttps://github.com/user-attachments/assets/d25034d9-c77f-43a9-8f14-0d167172b080 \n\n**Scarlett Voice**\n\nhttps://github.com/user-attachments/assets/b12009ee-ec0d-45ce-a1ef-b3a52b9f8693\n\n**David Attenborough Voice** \n\nhttps://github.com/user-attachments/assets/81c4baad-117e-4db5-ac86-efc2b7fea921\n\n**Example**\n\n\n \n\n## README.md\n\n## Table of Contents\n- [ebook2audiobook](#-ebook2audiobook)\n- [Features](#features)\n- [GUI Interface](#gui-interface)\n- [Demos](#demos)\n- [Supported Languages](#supported-languages)\n- [Minimum Requirements](#hardware-requirements)\n- [Usage](#instructions)\n - [Run Locally](#instructions)\n - [Launching Gradio Web Interface](#instructions)\n - [Basic Headless Usage](#basic-usage)\n - [Headless Custom XTTS Model Usage](#example-of-custom-model-zip-upload)\n - [Help command output](#help-command-output)\n - [Run Remotely](#run-remotely)\n - [Docker](#docker)\n - [Steps to Run](#docker)\n \n- [Cloned Voices](#cloned-voices)\n- [Fine Tuned TTS models](#fine-tuned-tts-models) \n - [Collection of Fine-Tuned TTS Models](#fine-tuned-tts-collection)\n - [Train TTS Model](#fine-tune-your-own-tts-model)\n- [Supported eBook Formats](#supported-ebook-formats)\n- [Output Formats](#output-and-process-formats)\n- [Revert to older Version](#reverting-to-older-versions)\n- [Common Issues](#common-issues)\n- [Special Thanks](#special-thanks)\n- [Table of Contents](#table-of-contents)\n\n\n## Features\n- 🔧 **TTS Engines supported**: `XTTSv2`, `Bark`, `Fairseq`, `VITS`, `Tacotron2`, `Tortoise`, `GlowTTS`, `YourTTS`\n- 📚 **Convert multiple file formats**: `.epub`, `.mobi`, `.azw3`, `.fb2`, `.lrf`, `.rb`, `.snb`, `.tcr`, `.pdf`, `.txt`, `.rtf`, `.doc`, `.docx`, `.html`, `.odt`, `.azw`, `.tiff`, `.tif`, `.png`, `.jpg`, `.jpeg`, `.bmp`, `.zip`\n- 💻 **TextArea** to convert directly a short text in audio\n- 🔍 **OCR scanning** for files with text pages as images\n- 🔊 **High-quality text-to-speech** from near realtime to near real voice\n- 🗣️ **Optional voice cloning** using your own voice file\n- 🌐 **Supports 1158 languages** ([supported languages list](https://dl.fbaipublicfiles.com/mms/tts/all-tts-languages.html))\n- 💻 **Low-resource friendly** — runs on **2 GB RAM / 1 GB VRAM (minimum)**\n- 🎵 **Audiobook output formats**: mono or stereo `aac`, `flac`, `mp3`, `m4b`, `m4a`, `mp4`, `mov`, `ogg`, `wav`, `webm`\n- 🧠 **SML tags supported** — fine-grained control of breaks, pauses, voice switching and more ([see below](#sml-tags-available))\n- 🧩 **Optional custom model** using your own trained model (XTTSv2, VITS, FAIRSEQ, PIPER, others on request)\n- 🎛️ **Fine-tuned preset models** trained by the E2A Team
\n (Contact us if you need additional fine-tuned models, or if you’d like to share yours to the official preset list)\n\n\n## Hardware Requirements\n- 2GB RAM min, 8GB recommended.\n- 1GB VRAM min, 4GB recommended.\n- Virtualization enabled if running on windows (Docker only).\n- CPU, XPU (intel, AMD, ARM)*.\n- CUDA, ROCm, JETSON\n- MPS (Apple Silicon CPU)\n\n* Modern TTS engines are very slow on CPU, so use lower quality TTS like YourTTS, Tacotron2 etc..\n\n## Supported Languages\n| **Arabic (ar)** | **Chinese (zh)** | **English (en)** | **Spanish (es)** |\n|:------------------:|:------------------:|:------------------:|:------------------:|\n| **French (fr)** | **German (de)** | **Italian (it)** | **Portuguese (pt)** |\n| **Polish (pl)** | **Turkish (tr)** | **Russian (ru)** | **Dutch (nl)** |\n| **Czech (cs)** | **Japanese (ja)** | **Hindi (hi)** | **Bengali (bn)** |\n| **Hungarian (hu)** | **Korean (ko)** | **Vietnamese (vi)**| **Swedish (sv)** |\n| **Persian (fa)** | **Yoruba (yo)** | **Swahili (sw)** | **Indonesian (id)**|\n| **Slovak (sk)** | **Croatian (hr)** | **Tamil (ta)** | **Danish (da)** |\n- [**+1130 languages and dialects here**](https://dl.fbaipublicfiles.com/mms/tts/all-tts-languages.html)\n\n\n## Supported eBook Formats\n- `.epub`, `.pdf`, `.mobi`, `.txt`, `.html`, `.rtf`, `.chm`, `.lit`,\n `.pdb`, `.fb2`, `.odt`, `.cbr`, `.cbz`, `.prc`, `.lrf`, `.pml`,\n `.snb`, `.cbc`, `.rb`, `.tcr`\n- **Best results**: `.epub` or `.mobi` for automatic chapter detection\n\n## Output and process Formats\n- `.m4b`, `.m4a`, `.mp4`, `.webm`, `.mov`, `.mp3`, `.flac`, `.wav`, `.ogg`, `.aac`\n- Process format can be changed in lib/conf.py\n\n## SML tags available\n- `[break]` — silence (random range **0.3–0.6 sec.**)\n- `[pause]` — silence (random range **1.0–1.6 sec.**)\n- `[pause:N]` — fixed pause (**N sec.**)\n- `[voice:/path/to/voice/file]...[/voice]` — switch voice from default or selected voice from GUI/CLI\n\n**Check our other repo dedicated to add SML automatically in your ebook -> [E2A-SML](https://github.com/DrewThomasson/E2A-SML)**\n\n> [!IMPORTANT]\n**Before to post an install or bug issue search carefully to the opened and closed issues TAB
\nto be sure your issue does not exist already.**\n\n>[!NOTE]\n**EPUB format lacks any standard structure like what is a chapter, paragraph, preface etc.
\nSo you should first remove manually any text you don't want to be converted in audio.**\n\n\n### Instructions \n1. **Clone repo**\n\t```bash\n\tgit clone https://github.com/DrewThomasson/ebook2audiobook.git\n\tcd ebook2audiobook\n\t```\n\n2. **Install / Run ebook2audiobook**:\n\n - **Linux/MacOS** \n ```bash\n ./ebook2audiobook.command\n ```\n Note for MacOS users: homebrew is installed to install missing programs.\n \n - **Mac Launcher** \n Double click `Mac Ebook2Audiobook Launcher.command`\n\n\n - **Windows** \n ```bash\n ebook2audiobook.cmd\n ```\n or\n Double click `ebook2audiobook.cmd`\n\n Note for Windows users: scoop is installed to install missing programs without administrator privileges.\n \n1. **Open the Web App**: Click the URL provided in the terminal to access the web app and convert eBooks. `http://localhost:7860/`\n2. **For Public Link**:\n `./ebook2audiobook.command --share` (Linux/MacOS)\n `ebook2audiobook.cmd --share` (Windows)\n `python app.py --share` (all OS)\n\n> [!IMPORTANT]\n**If the script is stopped and run again, you need to refresh your gradio GUI interface
\nto let the web page reconnect to the new connection socket.**\n\n### Basic Usage\n - **Linux/MacOS**:\n ```bash\n ./ebook2audiobook.command --headless --ebook --voice --language \n ```\n - **Windows**\n ```bash\n ebook2audiobook.cmd --headless --ebook --voice --language \n ```\n \n - **[--ebook]**: Path to your eBook file\n - **[--voice]**: Voice cloning file path (optional)\n - **[--language]**: Language code in ISO-639-3 (i.e.: ita for italian, eng for english, deu for german...).
\n Default language is eng and --language is optional for default language set in ./lib/lang.py.
\n The ISO-639-1 2 letters codes are also supported.\n\n\n### Example of Custom Model Zip Upload\n (must be a .zip file containing the mandatory model files. Example for XTTSv2: config.json, model.pth, vocab.json and ref.wav)\n - **Linux/MacOS**\n ```bash\n ./ebook2audiobook.command --headless --ebook --language --custom_model \n ```\n - **Windows**\n ```bash\n ebook2audiobook.cmd --headless --ebook --language --custom_model \n ```\n Note: the ref.wav of your custom model is always the voice selected for the conversion\n \n- ****: Path to `model_name.zip` file,\n which must contain (according to the tts engine) all the mandatory files
\n (see ./lib/models.py).\n\n### For Detailed Guide with list of all Parameters to use\n - **Linux/MacOS**\n ```bash\n ./ebook2audiobook.command --help\n ```\n - **Windows**\n ```bash\n ebook2audiobook.cmd --help\n ```\n - **Or for all OS**\n ```python\n app.py --help\n ```\n\n\n```bash\nusage: app.py [-h] [--session SESSION] [--share] [--headless] [--ebook EBOOK] [--ebooks_dir EBOOKS_DIR]\n [--language LANGUAGE] [--voice VOICE] [--voice_map VOICE_MAP] [--device {CPU,CUDA,MPS,ROCM,XPU,JETSON}]\n [--tts_engine {XTTS,BARK,VITS,FAIRSEQ,TACOTRON,YOURTTS,xtts,bark,vits,fairseq,tacotron,yourtts}]\n [--custom_model CUSTOM_MODEL] [--fine_tuned FINE_TUNED] [--output_format OUTPUT_FORMAT]\n [--output_channel OUTPUT_CHANNEL] [--temperature TEMPERATURE] [--length_penalty LENGTH_PENALTY]\n [--num_beams NUM_BEAMS] [--repetition_penalty REPETITION_PENALTY] [--top_k TOP_K] [--top_p TOP_P]\n [--speed SPEED] [--enable_text_splitting] [--text_temp TEXT_TEMP] [--waveform_temp WAVEFORM_TEMP]\n [--output_dir OUTPUT_DIR] [--version]\n\nConvert eBooks to Audiobooks using a Text-to-Speech model. You can either launch the Gradio interface or run the script in headless mode for direct conversion.\n\noptions:\n -h, --help show this help message and exit\n --session SESSION Session to resume the conversion in case of interruption, crash,\n or reuse of custom models and custom cloning voices.\n\n**** The following option is for gradio/gui mode only:\n --share (Optional) Enable a public shareable Gradio link.\n\n**** The following options are for --headless mode only:\n --headless Run the script in headless mode\n --ebook EBOOK Path to the ebook file for conversion. Cannot be used when --ebooks_dir is present.\n --ebooks_dir EBOOKS_DIR\n Relative or absolute path of the directory containing the files to convert.\n Cannot be used when --ebook is present.\n --text TEXT Raw text for conversion. Cannot be used when --ebook or --ebooks_dir is present.\n --language LANGUAGE Language of the e-book. Default language is set\n in ./lib/lang.py sed as default if not present. All compatible language codes are in ./lib/lang.py\n\noptional parameters:\n --translate ISO3 (Optional) Translate ebook to a target language (ISO 639-3 code, e.g. eng, fra, deu) before TTS synthesis.\n Uses argostranslate. The target language becomes the effective TTS language for the run.\n A copy of the source ebook is made with the _ suffix so translated and non-translated\n outputs stay isolated (independent process folder, audio chunks, and final file).\n --voice VOICE (Optional) Path to the voice cloning file for TTS engine.\n Uses the default voice if not present.\n --voice_map VOICE_MAP\n (Optional, --ebooks_dir only) Path to a JSON file mapping ebook path -> voice path.\n Each entry overrides --voice for that specific ebook. Missing/null entries fall back to --voice.\n Keys may be absolute paths or basenames. Example:\n {\"book1.epub\": \"/voices/eng/adult/female/alice.wav\", \"/abs/path/book2.epub\": null}\n --device {CPU,CUDA,MPS,ROCM,XPU,JETSON}\n (Optional) Processor unit type for the conversion.\n Default is set in ./lib/conf.py if not present. Fall back to CPU if CUDA or MPS is not available.\n --tts_engine {XTTS,BARK,VITS,FAIRSEQ,TACOTRON,YOURTTS,xtts,bark,vits,fairseq,tacotron,yourtts}\n (Optional) Preferred TTS engine (available are: ['XTTS', 'BARK', 'VITS', 'FAIRSEQ', 'TACOTRON', 'YOURTTS', 'xtts', 'bark', 'vits', 'fairseq', 'tacotron', 'yourtts'].\n Default depends on the selected language. The tts engine should be compatible with the chosen language\n --custom_model CUSTOM_MODEL\n (Optional) Path to the custom model zip file cntaining mandatory model files.\n Please refer to ./lib/models.py\n --fine_tuned FINE_TUNED\n (Optional) Fine tuned model path. Default is builtin model.\n --output_format OUTPUT_FORMAT\n (Optional) Output audio format. Default is m4b set in ./lib/conf.py\n --output_channel OUTPUT_CHANNEL\n (Optional) Output audio channel. Default is mono set in ./lib/conf.py\n --temperature TEMPERATURE\n (xtts only, optional) Temperature for the model.\n Default to config.json model. Higher temperatures lead to more creative outputs.\n --length_penalty LENGTH_PENALTY\n (xtts only, optional) A length penalty applied to the autoregressive decoder.\n Default to config.json model. Not applied to custom models.\n --num_beams NUM_BEAMS\n (xtts only, optional) Controls how many alternative sequences the model explores. Must be equal or greater than length penalty.\n Default to config.json model.\n --repetition_penalty REPETITION_PENALTY\n (xtts only, optional) A penalty that prevents the autoregressive decoder from repeating itself.\n Default to config.json model.\n --top_k TOP_K (xtts only, optional) Top-k sampling.\n Lower values mean more likely outputs and increased audio generation speed.\n Default to config.json model.\n --top_p TOP_P (xtts only, optional) Top-p sampling.\n Lower values mean more likely outputs and increased audio generation speed. Default to config.json model.\n --speed SPEED (xtts only, optional) Speed factor for the speech generation.\n Default to config.json model.\n --enable_text_splitting\n (xtts only, optional) Enable TTS text splitting. This option is known to not be very efficient.\n Default to config.json model.\n --text_temp TEXT_TEMP\n (bark only, optional) Text Temperature for the model.\n Default to config.json model.\n --waveform_temp WAVEFORM_TEMP\n (bark only, optional) Waveform Temperature for the model.\n Default to config.json model.\n --output_dir OUTPUT_DIR\n (Optional) Path to the output directory. Default is set in ./lib/conf.py\n --abs_url ABS_URL Audiobookshelf server URL (e.g. http://localhost:13378).\n --abs_api_token ABS_API_TOKEN\n Audiobookshelf API token.\n --abs_library ABS_LIBRARY\n Audiobookshelf library ID.\n --enable_interlude Add MusicGen music before the first chapter, between chapters, and at the end of the audiobook. Settings are in ./lib/conf_interlude.py\n --version Show the version of the script and exit\n\nExample usage:\nWindows:\n Gradio/GUI:\n ebook2audiobook.cmd\n Headless mode:\n ebook2audiobook.cmd --headless --ebook '/path/to/file' --language eng\nLinux/Mac:\n Gradio/GUI:\n ./ebook2audiobook.command\n Headless mode:\n ./ebook2audiobook.command --headless --ebook '/path/to/file' --language eng\n\nSML tags available:\n\t[break] — silence (random range **0.3–0.6 sec.**)\n\t[pause] — silence (random range **1.0–1.6 sec.**)\n\t[pause:N] — fixed pause (**N sec.**)\n\t[voice:/path/to/voice/file]...[/voice] — switch voice from default or selected voice from GUI/CLI\n\n```\n\nNOTE: in gradio/gui mode, to cancel a running conversion, just click on the [X] from the ebook upload component.\nTIP: if it needs some more pause, add '[pause:3]' for 3 sec. etc.\n\n### Docker\n1. **Clone the Repository**:\n```bash\n git clone https://github.com/DrewThomasson/ebook2audiobook.git\n cd ebook2audiobook\n```\n2. **Build the container**\n```bash\n Windows:\n Docker:\n ebook2audiobook.cmd --script_mode build_docker\n Docker Compose:\n ebook2audiobook.cmd --script_mode build_docker --docker_mode compose\n Podman Compose:\n ebook2audiobook.cmd --script_mode build_docker --docker_mode podman\n Linux/Mac\n Docker:\n ./ebook2audiobook.command --script_mode build_docker\n Docker Compose\n ./ebook2audiobook.command --script_mode build_docker --docker_mode compose\n Podman Compose:\n ./ebook2audiobook.command --script_mode build_docker --docker_mode podman\n```\n4. **Run the Container:**\n```bash\nDocker run image:\n Gradio/GUI:\n CPU:\n docker run -v \"./ebooks:/app/ebooks\" -v \"./audiobooks:/app/audiobooks\" -v \"./models:/app/models\" -v \"./voices:/app/voices\" -v \"./tmp:/app/tmp\" --rm -it -p 7860:7860 athomasson2/ebook2audiobook:cpu\n CUDA:\n docker run -v \"./ebooks:/app/ebooks\" -v \"./audiobooks:/app/audiobooks\" -v \"./models:/app/models\" -v \"./voices:/app/voices\" -v \"./tmp:/app/tmp\" --gpus all --rm -it -p 7860:7860 athomasson2/ebook2audiobook:cu[118/122/124/126 etc..]\n ROCM:\n docker run -v \"./ebooks:/app/ebooks\" -v \"./audiobooks:/app/audiobooks\" -v \"./models:/app/models\" -v \"./voices:/app/voices\" -v \"./tmp:/app/tmp\" --device=/dev/kfd --device=/dev/dri --rm -it -p 7860:7860 athomasson2/ebook2audiobook:rocm[6.0/6.1/6.4 etc..]\n XPU:\n docker run -v \"./ebooks:/app/ebooks\" -v \"./audiobooks:/app/audiobooks\" -v \"./models:/app/models\" -v \"./voices:/app/voices\" -v \"./tmp:/app/tmp\" --device=/dev/dri --rm -it -p 7860:7860 athomasson2/ebook2audiobook:xpu\n JETSON:\n docker run -v \"./ebooks:/app/ebooks\" -v \"./audiobooks:/app/audiobooks\" -v \"./models:/app/models\" -v \"./voices:/app/voices\" -v \"./tmp:/app/tmp\" --runtime nvidia --rm -it -p 7860:7860 athomasson2/ebook2audiobook:jetson[51/60/61 etc...]\n Headless mode:\n CPU:\n docker run -v \"./ebooks:/app/ebooks\" -v \"./audiobooks:/app/audiobooks\" -v \"./models:/app/models\" -v \"./voices:/app/voices\" -v \"./tmp:/app/tmp\" -v \"/my/real/ebooks/folder/absolute/path:/app/another_ebook_folder\" --rm -it -p 7860:7860 ebook2audiobook:cpu --headless --ebook \"/app/another_ebook_folder/myfile.pdf\" [--voice /app/my/voicepath/voice.mp3 etc..]\n CUDA:\n docker run -v \"./ebooks:/app/ebooks\" -v \"./audiobooks:/app/audiobooks\" -v \"./models:/app/models\" -v \"./voices:/app/voices\" -v \"./tmp:/app/tmp\" -v \"/my/real/ebooks/folder/absolute/path:/app/another_ebook_folder\" --gpus all --rm -it -p 7860:7860 ebook2audiobook:cu[118/122/124/126 etc..] --headless --ebook \"/app/another_ebook_folder/myfile.pdf\" [--voice /app/my/voicepath/voice.mp3 etc..]\n ROCM:\n docker run -v \"./ebooks:/app/ebooks\" -v \"./audiobooks:/app/audiobooks\" -v \"./models:/app/models\" -v \"./voices:/app/voices\" -v \"./tmp:/app/tmp\" -v \"/my/real/ebooks/folder/absolute/path:/app/another_ebook_folder\" --device=/dev/kfd --device=/dev/dri --rm -it -p 7860:7860 ebook2audiobook:rocm[6.0/6.1/6.4 etc.] --headless --ebook \"/app/another_ebook_folder/myfile.pdf\" [--voice /app/my/voicepath/voice.mp3 etc..]\n XPU:\n docker run -v \"./ebooks:/app/ebooks\" -v \"./audiobooks:/app/audiobooks\" -v \"./models:/app/models\" -v \"./voices:/app/voices\" -v \"./tmp:/app/tmp\" -v \"/my/real/ebooks/folder/absolute/path:/app/another_ebook_folder\" --device=/dev/dri --rm -it -p 7860:7860 ebook2audiobook:xpu --headless --ebook \"/app/another_ebook_folder/myfile.pdf\" [--voice /app/my/voicepath/voice.mp3 etc..]\n JETSON:\n docker run -v \"./ebooks:/app/ebooks\" -v \"./audiobooks:/app/audiobooks\" -v \"./models:/app/models\" -v \"./voices:/app/voices\" -v \"./tmp:/app/tmp\" -v \"/my/real/ebooks/folder/absolute/path:/app/another_ebook_folder\" --runtime nvidia --rm -it -p 7860:7860 ebook2audiobook:jetson[51/60/61 etc.] --headless --ebook \"/app/another_ebook_folder/myfile.pdf\" [--voice /app/my/voicepath/voice.mp3 etc..]\nDocker Compose (i.e. cuda 12.8:\n Run Gradio GUI:\n DEVICE_TAG=cu128 docker compose --profile gpu up --no-log-prefix\n Run Headless mode:\n DEVICE_TAG=cu128 docker compose --profile gpu run --rm ebook2audiobook --headless --ebook \"/app/ebooks/myfile.pdf\" --voice /app/voices/eng/adult/female/some_voice.wav etc..\nPodman Compose (i.e. cuda 12.8:\n Run Gradio GUI:\n DEVICE_TAG=cu128 podman-compose -f podman-compose.yml --profile gpu up\n Run Headless mode:\n DEVICE_TAG=cu128 podman-compose -f podman-compose.yml --profile gpu run --rm ebook2audiobook-gpu --headless --ebook \"/app/ebooks/myfile.pdf\" --voice /app/voices/eng/adult/female/some_voice.wav etc..\n```\n- NOTE: MPS is not exposed in docker so CPU must be used\n\n## Cloned Voices\nYou can upload any voice audio in any of the supported audio formats, the ideal duration is around 1 to 5 mn.\nIt doesn't matter if the recording has a noisy background or music playing over it — E2A will clean up the voice for you.\n\nThe built-in cloned voices list is mainly in English. If you need voices in other languages to be officially\nadded to the list, please contact us and we'll add them after review.\n\n## Fine Tuned TTS models\n#### Fine Tune your own TTS model\n\n[Universal_TTS_Finetune](https://github.com/DrewThomasson/Universal_TTS_Finetune)\n\n#### De-noise training data\n\n[](https://huggingface.co/spaces/drewThomasson/DeepFilterNet2_no_limit) [](https://github.com/Rikorose/DeepFilterNet)\n\n\n### Fine Tuned TTS Collection\n\n[](https://huggingface.co/drewThomasson/fineTunedTTSModels/tree/main)\n\nFor an XTTSv2 custom model a ref audio clip of the voice reference is mandatory:\n\n## Your own Ebook2Audiobook customization\nYou are free to modify libs/conf.py to add or remove the settings you wish. If you plan to do it just make\na copy of the original conf.py so on each ebook2audiobook update you will backup your modified conf.py and put\nback the original one. You must plan the same process for models.py. If you wish to make your own custom model\nas an official ebook2audiobook fine tuned model so please contact us and we'll add it to the presets list.\n\n## Reverting to older Versions\nReleases can be found -> [here](https://github.com/DrewThomasson/ebook2audiobook/releases)\n```bash\ngit checkout tags/VERSION_NUM # Locally/Compose -> Example: git checkout tags/v25.7.7\n```\n\n## Common Issues:\n- My NVIDIA/ROCm/XPU/MPS GPU isn't being detected?? -> [GPU ISSUES Wiki Page](https://github.com/DrewThomasson/ebook2audiobook/wiki/GPU-ISSUES)\n- CPU is slow (better on server smp CPU) while GPU can have almost real time conversion.\n [Discussion about this](https://github.com/DrewThomasson/ebook2audiobook/discussions/19#discussioncomment-10879846)\n (It doesn't have zero-shot voice cloning though, and is Siri quality voices, but it is much faster on cpu).\n- \"I'm having dependency issues\" - Just use the docker, its fully self contained and has a headless mode,\n add `--help` parameter at the end of the docker run command for more information.\n- \"I'm getting a truncated audio issue!\" - PLEASE MAKE AN ISSUE OF THIS,\n we don't speak every language and need advise from users to fine tune the sentence splitting logic.😊\n\n## ***** ROADMAP *****\n- All Features open to public Contributions ⭐\n- Any help from people speaking any of the supported languages to help us improve the models ⭐\n- [x] Preview Blocks/Chapters before to start the conversion\n- [x] Edit by sentence converted for surgical text change\n- [x] Generate music intros, interludes, and endings; edit interludes and endings\n- [x] SML tags integration for voice, pause, break, and more changes \n- [x] -h -help parameter info in different languages\n- [x] OCR scanning for PDF / JPG / BMP / PNG / TIFF\n- [x] Notebooks Folder [Talked about here](https://github.com/DrewThomasson/ebook2audiobookXTTS/issues/5#issuecomment-2408773254)\n- [x] Make Chinese text splitting not split words and improve pause timing [Talked about here](https://github.com/DrewThomasson/ebook2audiobookXTTS/issues/18#issuecomment-2401154894)\n- [x] Dockerfile\n- [x] Docker compose\n- [x] Podman compose \n- [x] Kaggle Notebook\n- [x] Google Colab Notebook\n- [x] Audiobookshelf integration\n- [x] Ebook Translation option\n- [x] Output format choices\n- [x] Multiprocessing conversion\n- [x] Batch ebook folder conversion\n- [x] GPU Device detection\n- [x] Denoise any background reference audio for voice cloning upload\n- [x] Custom fine-tuned model upload\n- [ ] [Make a IOS app](https://github.com/DrewThomasson/ebook2audiobook/pull/35#issuecomment-2496495212)\n- [ ] [Make an android app](https://github.com/DrewThomasson/ebook2audiobook/pull/35#issuecomment-2496495212)\n\n#### User Requests\n- [ ] Add European Portuguese language model for xttsv2, fairseq, vits, piper at least (help welcome)\n- [ ] Add Sindhi language model for xttsv2, fairseq, vits, piper at least (help welcome)\n\n#### TTS engines\n- [x] XTTSv2\n- [x] Bark\n- [x] Fairseq\n- [x] VITS\n- [x] Tacotron2\n- [x] YourTTS\n- [x] Tortoise\n- [x] GlowTTS\n- [x] Piper\n- [ ] GPT-SoVITS (https://github.com/RVC-Boss/GPT-SoVITS)\n- [ ] OpenVoice (https://github.com/myshell-ai/OpenVoice)\n- [ ] fish-speech (https://github.com/fishaudio/fish-speech)\n- [ ] ChatTTS (https://github.com/2noise/ChatTTS)\n- [ ] CosyVoice (https://github.com/FunAudioLLM/CosyVoice)\n- [ ] F5-TTS (https://github.com/swivid/f5-tts)\n- [ ] chatterbox (https://github.com/resemble-ai/chatterbox)\n- [ ] Supertonic (https://github.com/supertone-inc/supertonic)\n- [ ] Spark-TTS (https://github.com/sparkaudio/spark-tts)\n- [ ] index-tts (https://github.com/index-tts/index-tts)\n- [ ] MeloTTS (https://github.com/myshell-ai/MeloTTS)\n- [ ] Kokoro-TTS (https://github.com/hexgrad/kokoro)\n- [ ] OmniVoice (https://github.com/k2-fsa/OmniVoice)\n- [ ] Zonos (https://github.com/Zyphra/Zonos)\n- [ ] Style-TTS2 (https://github.com/yl4579/StyleTTS2)\n- [ ] Orpheus-TTS (https://github.com/canopyai/Orpheus-TTS)\n- [ ] NewTTS (https://github.com/neuphonic/neutts?tab=readme-ov-file)\n- [ ] VIbeVoice (https://github.com/vibevoice-community/VibeVoice)\n- [ ] Qwen3-TTS (https://huggingface.co/spaces/Qwen/Qwen3-TTS)\n\n#### Readme Translation\n- [x] Arabic (ara)\n- [x] Chinese (zho)\n- [x] English (eng)\n- [x] Spanish (spa)\n- [x] French (fra)\n- [x] German (deu)\n- [x] Italian (ita)\n- [x] Portuguese (por)\n- [x] Polish (pol)\n- [x] Turkish (tur)\n- [x] Russian (rus)\n- [x] Dutch (nld)\n- [x] Czech (ces)\n- [x] Japanese (jpn)\n- [x] Hindi (hin)\n- [x] Bengali (ben)\n- [x] Hungarian (hun)\n- [x] Korean (kor)\n- [x] Vietnamese (vie)\n- [x] Swedish (swe)\n- [x] Persian (fas)\n- [x] Yoruba (yor)\n- [x] Swahili (swa)\n- [x] Indonesian (ind)\n- [x] Slovak (slk)\n- [x] Croatian (hrv)\n\n#### 🐍 OS Compatibility\n- [x] 🍎 Mac Intel x86\n- [x] 🪟 Windows x86\n- [x] 🐧 Linux x86\n- [x] 🖥️🍏 Apple Silicon Mac\n- [x] 🪟💪 ARM Windows\n- [x] 🐧💪 ARM Linux\n\n**********\n\n## Extra Overkill for training models and such (All supported Coqui-tts models and piper-tts in one easy command) \n- For info about this @DrewThomasson, he is currently working on the development of this, [Universal TTS Finetune](https://github.com/DrewThomasson/Universal_TTS_Finetune)\n- [x] Make a easy to use training gui for all coqui-tts models in the [ljspeech format training recipes](https://github.com/coqui-ai/TTS/tree/dev/recipes/ljspeech) Completed at [Universal TTS Finetune](https://github.com/DrewThomasson/Universal_TTS_Finetune)\n\n\n## Python Code normalization information for contributors\n- no blank line between code, unless between functions and classes.\n- single quote used for all key unless for dict() and json. dict['key'] always called with single quote\n- 4 spaces indentation, not tab at all\n- strict typing for all functions and its arguments declaration and return values\n- no space between the argument and its typing, no space between the function, the \"->\" and the return value\n\nExample:\n\n```python\nimport json\nfrom typing import Optional\n\ndef get_user(user_id:int, users:list[dict])->Optional[dict]:\n for user in users:\n if user['id'] == user_id:\n return user\n return None\n\ndef summarize(user:dict)->str:\n return f\"User {user['name']} is {'active' if user['is_active'] else 'inactive'}.\"\n\ndef to_json(user:dict)->str:\n return json.dumps({\"id\": user['id'], \"name\": user['name'], \"email\": user['email']})\n\nusers:list = [\n dict(id=1, name=\"alice\", email=\"alice@example.com\", role=\"admin\", is_active=True),\n dict(id=2, name=\"bob\", email=\"bob@example.com\", role=\"editor\", is_active=False),\n dict(id=3, name=\"carol\", email=\"carol@example.com\", role=\"viewer\", is_active=True),\n]\nconfig = {\n \"max_users\": 100,\n \"default_role\": \"viewer\",\n \"allow_signup\": True,\n}\nroles = ['admin', 'editor', 'viewer']\nfound = get_user(1, users)\nif found:\n print(summarize(found))\n print(found['email'])\n print(to_json(found))\nif config['default_role'] in roles:\n print(config['default_role'])\n```\n\n## Hardware donation for beta tests wanted\nWe accept any kind of hardware to test our development like:\n- Nvidia supporting cuda >= 11.8\n- XPU intel cards\n- ROCm AMD cards supporting ROCm >=5.7\n\n@DrewThomasson if you want to help out at all! 😃\n\n\n## Special Thanks\nTo all financial and code contributors, each contribution and suggestion helps to improve the quality of E2A.\n","tools/readme_i18n/cache.json":"{\n \"ar|Thanks to support ebook2audiobook developers!\": \"شكرًا لدعمك لمطوّري ebook2audiobook!\",\n \"ar|Run locally\": \"التشغيل محليًا\",\n \"ar|Run Remotely\": \"التشغيل عن بُعد\",\n \"ar|GUI Interface\": \"الواجهة الرسومية (GUI)\",\n \"ar|Click to see images of Web GUI\": \"انقر لرؤية صور واجهة الويب الرسومية\",\n \"ar|Demos\": \"عروض توضيحية\",\n \"ar|**New Default Voice Demo** \": \"**عرض توضيحي للصوت الافتراضي الجديد** \",\n \"ar|More Demos\": \"المزيد من العروض التوضيحية\",\n \"ar|**ASMR Voice** \": \"**صوت ASMR** \",\n \"ar|**Rainy Day Voice** \": \"**صوت يوم ممطر** \",\n \"ar|**Scarlett Voice**\": \"**صوت سكارليت**\",\n \"ar|**David Attenborough Voice** \": \"**صوت ديفيد أتينبورو** \",\n \"ar|**Example**\": \"**مثال**\",\n \"ar|Table of Contents\": \"جدول المحتويات\",\n \"ar|[Features](#features)\": \"[الميزات](#features)\",\n \"ar|[GUI Interface](#gui-interface)\": \"[الواجهة الرسومية](#gui-interface)\",\n \"ar|[Demos](#demos)\": \"[عروض توضيحية](#demos)\",\n \"ar|[Supported Languages](#supported-languages)\": \"[اللغات المدعومة](#supported-languages)\",\n \"ar|[Minimum Requirements](#hardware-requirements)\": \"[الحد الأدنى من المتطلبات](#hardware-requirements)\",\n \"ar|[Usage](#instructions)\": \"[الاستخدام](#instructions)\",\n \"ar|[Run Locally](#instructions)\": \"[التشغيل محليًا](#instructions)\",\n \"ar|[Launching Gradio Web Interface](#instructions)\": \"[تشغيل واجهة الويب Gradio](#instructions)\",\n \"ar|[Basic Headless Usage](#basic-usage)\": \"[الاستخدام الأساسي بدون واجهة](#basic-usage)\",\n \"ar|[Headless Custom XTTS Model Usage](#example-of-custom-model-zip-upload)\": \"[استخدام نموذج XTTS مخصص بدون واجهة](#example-of-custom-model-zip-upload)\",\n \"ar|[Help command output](#help-command-output)\": \"[مخرجات أمر المساعدة](#help-command-output)\",\n \"ar|[Run Remotely](#run-remotely)\": \"[التشغيل عن بُعد](#run-remotely)\",\n \"ar|[Steps to Run](#docker)\": \"[خطوات التشغيل](#docker)\",\n \"ar|[Common Docker Issues](#common-docker-issues)\": \"[مشكلات Docker الشائعة](#common-docker-issues)\",\n \"ar|[Fine Tuned TTS models](#fine-tuned-tts-models)\": \"[نماذج TTS المضبوطة بدقة](#fine-tuned-tts-models)\",\n \"ar|[Collection of Fine-Tuned TTS Models](#fine-tuned-tts-collection)\": \"[مجموعة نماذج TTS المضبوطة بدقة](#fine-tuned-tts-collection)\",\n \"ar|[Train XTTSv2](#fine-tune-your-own-xttsv2-model)\": \"[تدريب XTTSv2](#fine-tune-your-own-xttsv2-model)\",\n \"ar|[Supported eBook Formats](#supported-ebook-formats)\": \"[صيغ الكتب الإلكترونية المدعومة](#supported-ebook-formats)\",\n \"ar|[Output Formats](#output-and-process-formats)\": \"[صيغ الإخراج](#output-and-process-formats)\",\n \"ar|[Revert to older Version](#reverting-to-older-versions)\": \"[العودة إلى إصدار أقدم](#reverting-to-older-versions)\",\n \"ar|[Common Issues](#common-issues)\": \"[المشكلات الشائعة](#common-issues)\",\n \"ar|[Special Thanks](#special-thanks)\": \"[شكر خاص](#special-thanks)\",\n \"ar|[Table of Contents](#table-of-contents)\": \"[جدول المحتويات](#table-of-contents)\",\n \"ar|Features\": \"الميزات\",\n \"ar|🔧 **TTS Engines supported**: `XTTSv2`, `Bark`, `Fairseq`, `VITS`, `Tacotron2`, `Tortoise`, `GlowTTS`, `YourTTS`\": \"🔧 **محركات TTS المدعومة**: `XTTSv2`, `Bark`, `Fairseq`, `VITS`, `Tacotron2`, `Tortoise`, `GlowTTS`, `YourTTS`\",\n \"ar|📚 **Convert multiple file formats**: `.epub`, `.mobi`, `.azw3`, `.fb2`, `.lrf`, `.rb`, `.snb`, `.tcr`, `.pdf`, `.txt`, `.rtf`, `.doc`, `.docx`, `.html`, `.odt`, `.azw`, `.tiff`, `.tif`, `.png`, `.jpg`, `.jpeg`, `.bmp`, `.zip`\": \"📚 **تحويل صيغ ملفات متعددة**: `.epub`, `.mobi`, `.azw3`, `.fb2`, `.lrf`, `.rb`, `.snb`, `.tcr`, `.pdf`, `.txt`, `.rtf`, `.doc`, `.docx`, `.html`, `.odt`, `.azw`, `.tiff`, `.tif`, `.png`, `.jpg`, `.jpeg`, `.bmp`, `.zip`\",\n \"ar|💻 **TextArea** to convert directly a short text in audio\": \"💻 **منطقة نص** لتحويل نص قصير مباشرةً إلى صوت\",\n \"ar|🔍 **OCR scanning** for files with text pages as images\": \"🔍 **مسح OCR** للملفات التي تحتوي على صفحات نصية كصور\",\n \"ar|🔊 **High-quality text-to-speech** from near realtime to near real voice\": \"🔊 **تحويل نص إلى كلام عالي الجودة**، من شبه الوقت الفعلي إلى صوت شبه حقيقي\",\n \"ar|🗣️ **Optional voice cloning** using your own voice file\": \"🗣️ **استنساخ صوت اختياري** باستخدام ملف صوتك الخاص\",\n \"ar|🌐 **Supports 1158 languages** ([supported languages list](https://dl.fbaipublicfiles.com/mms/tts/all-tts-languages.html))\": \"🌐 **يدعم 1158 لغة** ([supported languages list](https://dl.fbaipublicfiles.com/mms/tts/all-tts-languages.html))\",\n \"ar|💻 **Low-resource friendly** — runs on **2 GB RAM / 1 GB VRAM (minimum)**\": \"💻 **صديق للموارد المنخفضة** — يعمل على **2 GB RAM / 1 GB VRAM (الحد الأدنى)**\",\n \"ar|🎵 **Audiobook output formats**: mono or stereo `aac`, `flac`, `mp3`, `m4b`, `m4a`, `mp4`, `mov`, `ogg`, `wav`, `webm`\": \"🎵 **صيغ إخراج الكتاب الصوتي**: mono or stereo `aac`, `flac`, `mp3`, `m4b`, `m4a`, `mp4`, `mov`, `ogg`, `wav`, `webm`\",\n \"ar|🧠 **SML tags supported** — fine-grained control of breaks, pauses, voice switching and more ([see below](#sml-tags-available))\": \"🧠 **وسوم SML مدعومة** — تحكم دقيق في الفواصل والتوقفات وتبديل الصوت والمزيد ([see below](#sml-tags-available))\",\n \"ar|🧩 **Optional custom model** using your own trained model (XTTSv2, VITS, FAIRSEQ, PIPER, others on request)\": \"🧩 **نموذج مخصص اختياري** باستخدام نموذجك المدرّب الخاص (XTTSv2, VITS, FAIRSEQ, PIPER, others on request)\",\n \"ar|🎛️ **Fine-tuned preset models** trained by the E2A Team
\": \"🎛️ **نماذج مُعدّة مسبقًا ومضبوطة بدقة** دُرّبت بواسطة فريق E2A
\",\n \"ar|(Contact us if you need additional fine-tuned models, or if you’d like to share yours to the official preset list)\": \"(تواصل معنا إذا كنت بحاجة إلى نماذج إضافية مضبوطة بدقة، أو إذا كنت ترغب في مشاركة نماذجك في قائمة الإعدادات المسبقة الرسمية)\",\n \"ar|Hardware Requirements\": \"متطلبات العتاد\",\n \"ar|2GB RAM min, 8GB recommended.\": \"2 جيجابايت RAM كحد أدنى، 8 جيجابايت موصى به.\",\n \"ar|1GB VRAM min, 4GB recommended.\": \"1 جيجابايت VRAM كحد أدنى، 4 جيجابايت موصى به.\",\n \"ar|Virtualization enabled if running on windows (Docker only).\": \"المحاكاة الافتراضية مُفعّلة عند التشغيل على windows (Docker فقط).\",\n \"ar|CPU, XPU (intel, AMD, ARM)*.\": \"CPU، XPU (intel، AMD، ARM)*.\",\n \"ar|CUDA, ROCm, JETSON\": \"CUDA، ROCm، JETSON\",\n \"ar|MPS (Apple Silicon CPU)\": \"MPS (معالج Apple Silicon)\",\n \"ar|* Modern TTS engines are very slow on CPU, so use lower quality TTS like YourTTS, Tacotron2 etc..\": \"* محركات TTS الحديثة بطيئة جدًا على CPU، لذا استخدم TTS أقل جودة مثل YourTTS وTacotron2 وما إلى ذلك.\",\n \"ar|Supported Languages\": \"اللغات المدعومة\",\n \"ar|[**+1130 languages and dialects here**](https://dl.fbaipublicfiles.com/mms/tts/all-tts-languages.html)\": \"[**+1130 لغة ولهجة هنا**](https://dl.fbaipublicfiles.com/mms/tts/all-tts-languages.html)\",\n \"ar|Supported eBook Formats\": \"صيغ الكتب الإلكترونية المدعومة\",\n \"ar|**Best results**: `.epub` or `.mobi` for automatic chapter detection\": \"**أفضل النتائج**: `.epub` أو `.mobi` للكشف التلقائي عن الفصول\",\n \"ar|Output and process Formats\": \"صيغ الإخراج والمعالجة\",\n \"ar|Process format can be changed in lib/conf.py\": \"يمكن تغيير صيغة المعالجة في lib/conf.py\",\n \"ar|SML tags available\": \"وسوم SML المتاحة\",\n \"ar|`[break]` — silence (random range **0.3–0.6 sec.**)\": \"`[break]` — صمت (نطاق عشوائي **0.3–0.6 sec.**)\",\n \"ar|`[pause]` — silence (random range **1.0–1.6 sec.**)\": \"`[pause]` — صمت (نطاق عشوائي **1.0–1.6 sec.**)\",\n \"ar|`[pause:N]` — fixed pause (**N sec.**)\": \"`[pause:N]` — توقف ثابت (**N sec.**)\",\n \"ar|`[voice:/path/to/voice/file]...[/voice]` — switch voice from default or selected voice from GUI/CLI\": \"`[voice:/path/to/voice/file]...[/voice]` — تبديل الصوت من الصوت الافتراضي أو المحدد من GUI/CLI\",\n \"ar|**Check our other repo dedicated to add SML automatically in your ebook -> [E2A-SML](./tools/E2A-SML)**\": \"**اطّلع على مستودعنا الآخر المخصص لإضافة SML تلقائيًا في كتابك الإلكتروني -> [E2A-SML](./tools/E2A-SML)**\",\n \"ar|**Before to post an install or bug issue search carefully to the opened and closed issues TAB
\": \"**قبل نشر مشكلة تثبيت أو خطأ، ابحث بعناية في علامة تبويب المشكلات المفتوحة والمغلقة
\",\n \"ar|to be sure your issue does not exist already.**\": \"للتأكد من أن مشكلتك غير موجودة بالفعل.**\",\n \"ar|**EPUB format lacks any standard structure like what is a chapter, paragraph, preface etc.
\": \"**تفتقر صيغة EPUB إلى أي بنية معيارية لما هو الفصل أو الفقرة أو المقدمة وما إلى ذلك.
\",\n \"ar|So you should first remove manually any text you don't want to be converted in audio.**\": \"لذا يجب عليك أولًا أن تزيل يدويًا أي نص لا ترغب في تحويله إلى صوت.**\",\n \"ar|**Install / Run ebook2audiobook**:\": \"**ثبّت / شغّل ebook2audiobook**:\",\n \"ar|**Mac Launcher** \": \"**مشغّل Mac** \",\n \"ar|Double click `Mac Ebook2Audiobook Launcher.command`\": \"انقر نقرًا مزدوجًا على `Mac Ebook2Audiobook Launcher.command`\",\n \"ar|Note for Windows users: scoop is installed to install missing programs without administrator privileges.\": \"ملاحظة لمستخدمي Windows: يتم تثبيت scoop لتثبيت البرامج المفقودة دون امتيازات المسؤول.\",\n \"ar|**Open the Web App**: Click the URL provided in the terminal to access the web app and convert eBooks. `http://localhost:7860/`\": \"**افتح تطبيق الويب**: انقر على الرابط المتوفر في الطرفية للوصول إلى تطبيق الويب وتحويل الكتب الإلكترونية. `http://localhost:7860/`\",\n \"ar|**For Public Link**:\": \"**للحصول على رابط عام**:\",\n \"ar|**If the script is stopped and run again, you need to refresh your gradio GUI interface
\": \"**إذا تم إيقاف السكربت وتشغيله مرة أخرى، فستحتاج إلى تحديث واجهة Gradio الرسومية
\",\n \"ar|to let the web page reconnect to the new connection socket.**\": \"للسماح لصفحة الويب بإعادة الاتصال بمقبس الاتصال الجديد.**\",\n \"ar|**[--ebook]**: Path to your eBook file\": \"**[--ebook]**: مسار ملف كتابك الإلكتروني\",\n \"ar|**[--voice]**: Voice cloning file path (optional)\": \"**[--voice]**: مسار ملف استنساخ الصوت (اختياري)\",\n \"ar|**[--language]**: Language code in ISO-639-3 (i.e.: ita for italian, eng for english, deu for german...).
\": \"**[--language]**: رمز اللغة بصيغة ISO-639-3 (أي: ita للإيطالية، eng للإنجليزية، deu للألمانية...).
\",\n \"ar|Default language is eng and --language is optional for default language set in ./lib/lang.py.
\": \"اللغة الافتراضية هي eng و--language اختياري للغة الافتراضية المحددة في ./lib/lang.py.
\",\n \"ar|The ISO-639-1 2 letters codes are also supported.\": \"كما يتم دعم رموز ISO-639-1 المكونة من حرفين.\",\n \"ar|****: Path to `model_name.zip` file,\": \"****: مسار ملف `model_name.zip`،\",\n \"ar|which must contain (according to the tts engine) all the mandatory files
\": \"الذي يجب أن يحتوي (وفقًا لمحرك tts) على جميع الملفات الإلزامية
\",\n \"ar|(see ./lib/models.py).\": \"(انظر ./lib/models.py).\",\n \"ar|NOTE: in gradio/gui mode, to cancel a running conversion, just click on the [X] from the ebook upload component.\": \"ملاحظة: في وضع gradio/gui، لإلغاء تحويل قيد التشغيل، ما عليك سوى النقر على [X] في مكوّن رفع الكتاب الإلكتروني.\",\n \"ar|TIP: if it needs some more pause, add '[pause:3]' for 3 sec. etc.\": \"نصيحة: إذا كانت هناك حاجة إلى توقف أطول قليلًا، أضف '[pause:3]' لمدة 3 ثوانٍ وما إلى ذلك.\",\n \"ar|Common Docker Issues\": \"مشكلات Docker الشائعة\",\n \"ar|My NVIDIA GPU isn't being detected?? -> [GPU ISSUES Wiki Page](https://github.com/DrewThomasson/ebook2audiobook/wiki/GPU-ISSUES)\": \"لا يتم اكتشاف بطاقة NVIDIA الرسومية لدي؟؟ -> [صفحة Wiki لمشكلات GPU](https://github.com/DrewThomasson/ebook2audiobook/wiki/GPU-ISSUES)\",\n \"ar|Fine Tuned TTS models\": \"نماذج TTS المضبوطة بدقة (fine-tuned)\",\n \"ar|Fine Tune your own XTTSv2 model\": \"اضبط نموذج XTTSv2 الخاص بك بدقة\",\n \"ar|De-noise training data\": \"إزالة الضوضاء من بيانات التدريب\",\n \"ar|Fine Tuned TTS Collection\": \"مجموعة نماذج TTS المضبوطة بدقة\",\n \"ar|For an XTTSv2 custom model a ref audio clip of the voice reference is mandatory:\": \"بالنسبة إلى نموذج XTTSv2 المخصص، يكون مقطع صوتي مرجعي للصوت إلزاميًا:\",\n \"ar|Your own Ebook2Audiobook customization\": \"تخصيصك الخاص لـ Ebook2Audiobook\",\n \"ar|You are free to modify libs/conf.py to add or remove the settings you wish. If you plan to do it just make\": \"أنت حر في تعديل libs/conf.py لإضافة أو إزالة الإعدادات التي تريدها. إذا كنت تخطط للقيام بذلك، فما عليك سوى إنشاء\",\n \"ar|a copy of the original conf.py so on each ebook2audiobook update you will backup your modified conf.py and put\": \"نسخة من conf.py الأصلي بحيث يمكنك في كل تحديث لـ ebook2audiobook عمل نسخة احتياطية من conf.py المعدّل وإعادة\",\n \"ar|back the original one. You must plan the same process for models.py. If you wish to make your own custom model\": \"وضع الأصلي. يجب عليك التخطيط للعملية نفسها بالنسبة لـ models.py. إذا كنت ترغب في جعل نموذجك المخصص\",\n \"ar|as an official ebook2audiobook fine tuned model so please contact us and we'll add it to the presets list.\": \"نموذج ebook2audiobook رسميًا مضبوطًا بدقة، فيرجى الاتصال بنا وسنضيفه إلى قائمة الإعدادات المسبقة.\",\n \"ar|Common Issues:\": \"المشكلات الشائعة:\",\n \"ar|My NVIDIA/ROCm/XPU/MPS GPU isn't being detected?? -> [GPU ISSUES Wiki Page](https://github.com/DrewThomasson/ebook2audiobook/wiki/GPU-ISSUES)\": \"لا يتم اكتشاف بطاقة NVIDIA/ROCm/XPU/MPS الرسومية لدي؟؟ -> [GPU ISSUES Wiki Page](https://github.com/DrewThomasson/ebook2audiobook/wiki/GPU-ISSUES)\",\n \"ar|CPU is slow (better on server smp CPU) while GPU can have almost real time conversion.\": \"المعالج بطيء (أفضل على معالج خادم SMP) بينما يمكن لبطاقة GPU إجراء تحويل شبه فوري.\",\n \"ar|(It doesn't have zero-shot voice cloning though, and is Siri quality voices, but it is much faster on cpu).\": \"(لكنه لا يحتوي على استنساخ صوت zero-shot، وهي أصوات بجودة Siri، لكنه أسرع بكثير على cpu).\",\n \"ar|\\\"I'm having dependency issues\\\" - Just use the docker, its fully self contained and has a headless mode,\": \"\\\"أواجه مشكلات في التبعيات\\\" - ما عليك سوى استخدام docker، فهو مكتفٍ ذاتيًا تمامًا وله وضع بدون واجهة،\",\n \"ar|add `--help` parameter at the end of the docker run command for more information.\": \"أضف المعامل `--help` في نهاية أمر docker run للمزيد من المعلومات.\",\n \"ar|\\\"I'm getting a truncated audio issue!\\\" - PLEASE MAKE AN ISSUE OF THIS,\": \"\\\"أواجه مشكلة في انقطاع الصوت!\\\" - يرجى إنشاء ISSUE حول هذا،\",\n \"ar|we don't speak every language and need advise from users to fine tune the sentence splitting logic.😊\": \"نحن لا نتحدث كل لغة ونحتاج إلى نصيحة من المستخدمين لضبط منطق تقسيم الجمل بدقة.😊\",\n \"ar|***** ROADMAP *****\": \"***** خارطة الطريق *****\",\n \"ar|All Features open to public Contributions ⭐\": \"جميع الميزات مفتوحة للمساهمات العامة ⭐\",\n \"ar|Any help from people speaking any of the supported languages to help us improve the models ⭐\": \"أي مساعدة من أشخاص يتحدثون أيًا من اللغات المدعومة لمساعدتنا في تحسين النماذج ⭐\",\n \"ar|Preview Blocks/Chapters before to start the conversion\": \"معاينة الكتل/الفصول قبل بدء التحويل\",\n \"ar|Edit by sentence converted for surgical text change\": \"التحرير لكل جملة محوّلة لتغيير نصي دقيق\",\n \"ar|SML tags integration for voice, pause, break, and more changes \": \"دمج وسوم SML للصوت والتوقف والفاصل والمزيد من التغييرات \",\n \"ar|-h -help parameter info in different languages\": \"معلومات معاملات -h -help بلغات مختلفة\",\n \"ar|OCR scanning for PDF / JPG / BMP / PNG / TIFF\": \"مسح OCR لملفات PDF / JPG / BMP / PNG / TIFF\",\n \"ar|Notebooks Folder [Talked about here](https://github.com/DrewThomasson/ebook2audiobookXTTS/issues/5#issuecomment-2408773254)\": \"مجلد Notebooks [Talked about here](https://github.com/DrewThomasson/ebook2audiobookXTTS/issues/5#issuecomment-2408773254)\",\n \"ar|Make Chinese text splitting not split words and improve pause timing [Talked about here](https://github.com/DrewThomasson/ebook2audiobookXTTS/issues/18#issuecomment-2401154894)\": \"جعل تقسيم النص الصيني لا يقسم الكلمات وتحسين توقيت الفواصل [Talked about here](https://github.com/DrewThomasson/ebook2audiobookXTTS/issues/18#issuecomment-2401154894)\",\n \"ar|Kaggle Notebook\": \"دفتر Kaggle\",\n \"ar|Google Colab Notebook\": \"دفتر Google Colab\",\n \"ar|[Make a IOS app](https://github.com/DrewThomasson/ebook2audiobook/pull/35#issuecomment-2496495212)\": \"[إنشاء تطبيق iOS](https://github.com/DrewThomasson/ebook2audiobook/pull/35#issuecomment-2496495212)\",\n \"ar|[Make an android app](https://github.com/DrewThomasson/ebook2audiobook/pull/35#issuecomment-2496495212)\": \"[إنشاء تطبيق android](https://github.com/DrewThomasson/ebook2audiobook/pull/35#issuecomment-2496495212)\",\n \"ar|Audiobookshelf integration\": \"دمج Audiobookshelf\",\n \"ar|Extra Options\": \"خيارات إضافية\",\n \"ar|Ebook Translation option\": \"خيار ترجمة الكتاب الإلكتروني\",\n \"ar|Output format choices\": \"خيارات صيغة الإخراج\",\n \"ar|Batch ebook folder\": \"مجلد كتب إلكترونية دفعي\",\n \"ar|Multiprocessing conversion\": \"تحويل متعدد المعالجة\",\n \"ar|Batch ebook folder conversion\": \"تحويل مجلد كتب إلكترونية دفعي\",\n \"ar|GPU Device detection\": \"اكتشاف جهاز GPU\",\n \"ar|Denoise any reference audio for upload voice cloning,\": \"إزالة الضوضاء من أي صوت مرجعي لرفع استنساخ الصوت،\",\n \"ar|Custom model upload (XTTSv2 only for now. more on request)\": \"رفع نموذج مخصص (XTTSv2 فقط حاليًا. المزيد عند الطلب)\",\n \"ar|Add European Portuguese language model for xttsv2, fairseq, vits, piper at least (help welcome)\": \"إضافة نموذج لغة البرتغالية الأوروبية على الأقل لـ xttsv2 وfairseq وvits وpiper (المساعدة مرحب بها)\",\n \"ar|Add Sindhi language model for xttsv2, fairseq, vits, piper at least (help welcome)\": \"إضافة نموذج لغة السندية على الأقل لـ xttsv2 وfairseq وvits وpiper (المساعدة مرحب بها)\",\n \"ar|Readme Translation\": \"ترجمة Readme\",\n \"ar|🐍 OS Compatibility\": \"🐍 توافق نظام التشغيل\",\n \"ar|Extra Overkill for training models and such (All supported Coqui-tts models and piper-tts in one easy command) \": \"مبالغة إضافية لتدريب النماذج وما شابه (جميع نماذج Coqui-tts المدعومة وpiper-tts في أمر واحد سهل) \",\n \"ar|For info about this @DrewThomasson, he is currently working on the development of this, [work-in-progress-repo here](https://github.com/DrewThomasson/Universal_TTS_Finetune)\": \"للمعلومات حول هذا @DrewThomasson، يعمل حاليًا على تطويره، [المستودع قيد العمل هنا](https://github.com/DrewThomasson/Universal_TTS_Finetune)\",\n \"ar|Make a easy to use training gui for all coqui-tts models in the ljspeech format training recipes [here from coqui tts](https://github.com/coqui-ai/TTS/tree/dev/recipes/ljspeech)\": \"إنشاء واجهة تدريب سهلة الاستخدام لجميع نماذج coqui-tts في وصفات التدريب بصيغة ljspeech [هنا من coqui tts](https://github.com/coqui-ai/TTS/tree/dev/recipes/ljspeech)\",\n \"ar|Python Code normalization information for contributors\": \"معلومات تسوية كود Python للمساهمين\",\n \"ar|no blank line between code, unless between functions and classes.\": \"لا سطر فارغ بين الكود، باستثناء بين الدوال والفئات.\",\n \"ar|single quote used for all key unless for dict() and json. dict['key'] always called with single quote\": \"تُستخدم علامات الاقتباس المفردة لجميع المفاتيح باستثناء dict() وjson. يتم استدعاء dict['key'] دائمًا بعلامات اقتباس مفردة\",\n \"ar|4 spaces indentation, not tab at all\": \"مسافة بادئة من 4 مسافات، دون أي علامات جدولة على الإطلاق\",\n \"ar|strict typing for all functions and its arguments declaration and return values\": \"كتابة صارمة للأنواع لجميع الدوال وإعلان وسائطها وقيم إرجاعها\",\n \"ar|no space between the argument and its typing, no space between the function, the \\\"->\\\" and the return value\": \"لا مسافة بين الوسيط وكتابة نوعه، لا مسافة بين الدالة و\\\"->\\\" وقيمة الإرجاع\",\n \"ar|Example:\": \"مثال:\",\n \"ar|Hardware donation for beta tests wanted\": \"مطلوب تبرع بالعتاد لاختبارات بيتا\",\n \"ar|We accept any kind of hardware to test our development like:\": \"نقبل أي نوع من العتاد لاختبار تطويرنا مثل:\",\n \"ar|@DrewThomasson if you want to help out at all! 😃\": \"@DrewThomasson إذا كنت ترغب في المساعدة بأي شكل من الأشكال! 😃\",\n \"ar|Do you need to rent a GPU to boost service from us?\": \"هل تحتاج إلى استئجار GPU لتعزيز خدمتنا؟\",\n \"ar|A poll is open here https://github.com/DrewThomasson/ebook2audiobook/discussions/889\": \"استطلاع رأي مفتوح هنا https://github.com/DrewThomasson/ebook2audiobook/discussions/889\",\n \"ar|Special Thanks\": \"شكر خاص\",\n \"ar|[@shakenbake15 for better chapter saving method](https://github.com/DrewThomasson/ebook2audiobook/issues/8) \": \"[@shakenbake15 لطريقة أفضل لحفظ الفصول](https://github.com/DrewThomasson/ebook2audiobook/issues/8) \",\n \"ar|TTS engines\": \"محركات TTS\",\n \"ar|XTTSv2\": \"XTTSv2\",\n \"ar|Bark\": \"ﺡﺎﺒﻧ\",\n \"ar|Fairseq\": \"فيرسيك\",\n \"ar|VITS\": \"فيتس\",\n \"ar|Tacotron2\": \"تاكوترون 2\",\n \"ar|YourTTS\": \"YourTTS\",\n \"ar|Tortoise\": \"لون السلحفاة\",\n \"ar|GlowTTS\": \"GlowTTS\",\n \"ar|Piper\": \"الفلفل الأسود\",\n \"ar|GPT-SoVITS (https://github.com/RVC-Boss/GPT-SoVITS)\": \"GPT - SoVITS (https://github.com/RVC-Boss/GPT-SoVITS)\",\n \"ar|OpenVoice (https://github.com/myshell-ai/OpenVoice)\": \"OpenVoice (https://github.com/myshell-ai/OpenVoice)\",\n \"ar|fish-speech (https://github.com/fishaudio/fish-speech)\": \"كلام السمكة (https://github.com/fishaudio/fish-speech)\",\n \"ar|ChatTTS (https://github.com/2noise/ChatTTS)\": \"ChatTTS (https://github.com/2noise/ChatTTS)\",\n \"ar|CosyVoice (https://github.com/FunAudioLLM/CosyVoice)\": \"CosyVoice (https://github.com/FunAudioLLM/CosyVoice)\",\n \"ar|F5-TTS (https://github.com/swivid/f5-tts)\": \"F5 - TTS (https://github.com/swivid/f5-tts)\",\n \"ar|chatterbox (https://github.com/resemble-ai/chatterbox)\": \"chatterbox (https://github.com/resemble-ai/chatterbox)\",\n \"ar|Supertonic (https://github.com/supertone-inc/supertonic)\": \"Supertonic (https://github.com/supertone-inc/supertonic)\",\n \"ar|Spark-TTS (https://github.com/sparkaudio/spark-tts)\": \"Spark - TTS (https://github.com/sparkaudio/spark-tts)\",\n \"ar|index-tts (https://github.com/index-tts/index-tts)\": \"index - tts (https://github.com/index-tts/index-tts)\",\n \"ar|MeloTTS (https://github.com/myshell-ai/MeloTTS)\": \"MeloTTS (https://github.com/myshell-ai/MeloTTS)\",\n \"ar|Kokoro-TTS (https://github.com/hexgrad/kokoro)\": \"Kokoro - TTS (https://github.com/hexgrad/kokoro)\",\n \"ar|OmniVoice (https://github.com/k2-fsa/OmniVoice)\": \"OmniVoice (https://github.com/k2-fsa/OmniVoice)\",\n \"ar|Zonos (https://github.com/Zyphra/Zonos)\": \"زونوس (https://github.com/Zyphra/Zonos)\",\n \"ar|Style-TTS2 (https://github.com/yl4579/StyleTTS2)\": \"Style - TTS2 (https://github.com/yl4579/StyleTTS2)\",\n \"ar|Orpheus-TTS (https://github.com/canopyai/Orpheus-TTS)\": \"Orpheus - TTS (https://github.com/canopyai/Orpheus-TTS)\",\n \"ar|NewTTS (https://github.com/neuphonic/neutts?tab=readme-ov-file)\": \"NewTTS (https://github.com/neuphonic/neutts?tab=readme-ov-file)\",\n \"ar|VIbeVoice (https://github.com/vibevoice-community/VibeVoice)\": \"VIbeVoice (https://github.com/vibevoice-community/VibeVoice)\",\n \"ar|Qwen3-TTS (https://huggingface.co/spaces/Qwen/Qwen3-TTS)\": \"Qwen3 - TTS (https://huggingface.co/spaces/Qwen/Qwen3-TTS)\",\n \"zh-CN|CPU/GPU Converter from E-Book to audiobook with chapters and metadata
\": \"将电子书转换为带有章节和元数据的有声书的 CPU/GPU 转换器
\",\n \"zh-CN|using advanced TTS engines and much more.
\": \"使用先进的 TTS 引擎等。
\",\n \"zh-CN|Supports voice cloning and 1158 languages!\": \"支持语音克隆和 1158 种语言！\",\n \"zh-CN|**This tool is intended for use with non-DRM, legally acquired eBooks only.**
\": \"**本工具仅供与合法获取的无 DRM 电子书一起使用。**
\",\n \"zh-CN|The authors are not responsible for any misuse of this software or any resulting legal consequences.
\": \"作者对本软件的任何滥用或由此产生的任何法律后果概不负责。
\",\n \"zh-CN|Use this tool responsibly and in accordance with all applicable laws.\": \"请负责任地使用本工具，并遵守所有适用的法律。\",\n \"zh-CN|Thanks to support ebook2audiobook developers!\": \"感谢您支持 ebook2audiobook 的开发者！\",\n \"zh-CN|Run locally\": \"本地运行\",\n \"zh-CN|Run Remotely\": \"远程运行\",\n \"zh-CN|GUI Interface\": \"图形界面（GUI）\",\n \"zh-CN|Click to see images of Web GUI\": \"点击查看 Web GUI 图像\",\n \"zh-CN|Demos\": \"演示\",\n \"zh-CN|**New Default Voice Demo** \": \"**新默认语音演示** \",\n \"zh-CN|More Demos\": \"更多演示\",\n \"zh-CN|**ASMR Voice** \": \"**ASMR 语音** \",\n \"zh-CN|**Rainy Day Voice** \": \"**雨天语音** \",\n \"zh-CN|**Scarlett Voice**\": \"**斯嘉丽语音**\",\n \"zh-CN|**David Attenborough Voice** \": \"**大卫·阿滕伯勒语音** \",\n \"zh-CN|**Example**\": \"**示例**\",\n \"zh-CN|Table of Contents\": \"目录\",\n \"zh-CN|[Features](#features)\": \"[功能](#features)\",\n \"zh-CN|[GUI Interface](#gui-interface)\": \"[图形界面](#gui-interface)\",\n \"zh-CN|[Demos](#demos)\": \"[演示](#demos)\",\n \"zh-CN|[Supported Languages](#supported-languages)\": \"[支持的语言](#supported-languages)\",\n \"zh-CN|[Minimum Requirements](#hardware-requirements)\": \"[最低要求](#hardware-requirements)\",\n \"zh-CN|[Usage](#instructions)\": \"[用法](#instructions)\",\n \"zh-CN|[Run Locally](#instructions)\": \"[本地运行](#instructions)\",\n \"zh-CN|[Launching Gradio Web Interface](#instructions)\": \"[启动 Gradio Web 界面](#instructions)\",\n \"zh-CN|[Basic Headless Usage](#basic-usage)\": \"[基本 Headless 用法](#basic-usage)\",\n \"zh-CN|[Headless Custom XTTS Model Usage](#example-of-custom-model-zip-upload)\": \"[Headless 自定义 XTTS 模型用法](#example-of-custom-model-zip-upload)\",\n \"zh-CN|[Help command output](#help-command-output)\": \"[帮助命令输出](#help-command-output)\",\n \"zh-CN|[Run Remotely](#run-remotely)\": \"[远程运行](#run-remotely)\",\n \"zh-CN|[Steps to Run](#docker)\": \"[运行步骤](#docker)\",\n \"zh-CN|[Common Docker Issues](#common-docker-issues)\": \"[常见的 Docker 问题](#common-docker-issues)\",\n \"zh-CN|[Fine Tuned TTS models](#fine-tuned-tts-models)\": \"[微调 TTS 模型](#fine-tuned-tts-models)\",\n \"zh-CN|[Collection of Fine-Tuned TTS Models](#fine-tuned-tts-collection)\": \"[微调 TTS 模型集合](#fine-tuned-tts-collection)\",\n \"zh-CN|[Train XTTSv2](#fine-tune-your-own-xttsv2-model)\": \"[训练 XTTSv2](#fine-tune-your-own-xttsv2-model)\",\n \"zh-CN|[Supported eBook Formats](#supported-ebook-formats)\": \"[支持的电子书格式](#supported-ebook-formats)\",\n \"zh-CN|[Output Formats](#output-and-process-formats)\": \"[输出格式](#output-and-process-formats)\",\n \"zh-CN|[Revert to older Version](#reverting-to-older-versions)\": \"[还原到较旧版本](#reverting-to-older-versions)\",\n \"zh-CN|[Common Issues](#common-issues)\": \"[常见问题](#common-issues)\",\n \"zh-CN|[Special Thanks](#special-thanks)\": \"[特别鸣谢](#special-thanks)\",\n \"zh-CN|[Table of Contents](#table-of-contents)\": \"[目录](#table-of-contents)\",\n \"zh-CN|Features\": \"功能\",\n \"zh-CN|🔧 **TTS Engines supported**: `XTTSv2`, `Bark`, `Fairseq`, `VITS`, `Tacotron2`, `Tortoise`, `GlowTTS`, `YourTTS`\": \"🔧 **支持的 TTS 引擎**： `XTTSv2`, `Bark`, `Fairseq`, `VITS`, `Tacotron2`, `Tortoise`, `GlowTTS`, `YourTTS`\",\n \"zh-CN|📚 **Convert multiple file formats**: `.epub`, `.mobi`, `.azw3`, `.fb2`, `.lrf`, `.rb`, `.snb`, `.tcr`, `.pdf`, `.txt`, `.rtf`, `.doc`, `.docx`, `.html`, `.odt`, `.azw`, `.tiff`, `.tif`, `.png`, `.jpg`, `.jpeg`, `.bmp`, `.zip`\": \"📚 **转换多种文件格式**： `.epub`, `.mobi`, `.azw3`, `.fb2`, `.lrf`, `.rb`, `.snb`, `.tcr`, `.pdf`, `.txt`, `.rtf`, `.doc`, `.docx`, `.html`, `.odt`, `.azw`, `.tiff`, `.tif`, `.png`, `.jpg`, `.jpeg`, `.bmp`, `.zip`\",\n \"zh-CN|💻 **TextArea** to convert directly a short text in audio\": \"💻 用于直接将短文本转换为音频的**文本区域**\",\n \"zh-CN|🔍 **OCR scanning** for files with text pages as images\": \"🔍 针对文本页面为图像的文件的 **OCR 扫描**\",\n \"zh-CN|🔊 **High-quality text-to-speech** from near realtime to near real voice\": \"🔊 **高质量文本转语音**，从接近实时到接近真实的语音\",\n \"zh-CN|🗣️ **Optional voice cloning** using your own voice file\": \"🗣️ 使用您自己的语音文件进行**可选的语音克隆**\",\n \"zh-CN|🌐 **Supports 1158 languages** ([supported languages list](https://dl.fbaipublicfiles.com/mms/tts/all-tts-languages.html))\": \"🌐 **支持 1158 种语言** ([supported languages list](https://dl.fbaipublicfiles.com/mms/tts/all-tts-languages.html))\",\n \"zh-CN|💻 **Low-resource friendly** — runs on **2 GB RAM / 1 GB VRAM (minimum)**\": \"💻 **低资源友好** — 可在 **2 GB RAM / 1 GB VRAM（最低）** 上运行\",\n \"zh-CN|🎵 **Audiobook output formats**: mono or stereo `aac`, `flac`, `mp3`, `m4b`, `m4a`, `mp4`, `mov`, `ogg`, `wav`, `webm`\": \"🎵 **有声书输出格式**： mono or stereo `aac`, `flac`, `mp3`, `m4b`, `m4a`, `mp4`, `mov`, `ogg`, `wav`, `webm`\",\n \"zh-CN|🧠 **SML tags supported** — fine-grained control of breaks, pauses, voice switching and more ([see below](#sml-tags-available))\": \"🧠 **支持 SML 标签** — 对中断、停顿、语音切换等进行精细控制 ([see below](#sml-tags-available))\",\n \"zh-CN|🧩 **Optional custom model** using your own trained model (XTTSv2, VITS, FAIRSEQ, PIPER, others on request)\": \"🧩 使用您自己训练的模型的**可选自定义模型** (XTTSv2, VITS, FAIRSEQ, PIPER, others on request)\",\n \"zh-CN|🎛️ **Fine-tuned preset models** trained by the E2A Team
\": \"🎛️ 由 E2A 团队训练的**微调预设模型**
\",\n \"zh-CN|(Contact us if you need additional fine-tuned models, or if you’d like to share yours to the official preset list)\": \"（如果您需要额外的微调模型，或者如果您想在官方预设列表中分享您自己的模型，请联系我们）\",\n \"zh-CN|Hardware Requirements\": \"硬件要求\",\n \"zh-CN|2GB RAM min, 8GB recommended.\": \"RAM 最低 2GB，推荐 8GB。\",\n \"zh-CN|1GB VRAM min, 4GB recommended.\": \"VRAM 最低 1GB，推荐 4GB。\",\n \"zh-CN|Virtualization enabled if running on windows (Docker only).\": \"在 windows 上运行时启用虚拟化（仅限 Docker）。\",\n \"zh-CN|CPU, XPU (intel, AMD, ARM)*.\": \"CPU、XPU（intel、AMD、ARM）*。\",\n \"zh-CN|CUDA, ROCm, JETSON\": \"CUDA、ROCm、JETSON\",\n \"zh-CN|MPS (Apple Silicon CPU)\": \"MPS（Apple Silicon CPU）\",\n \"zh-CN|* Modern TTS engines are very slow on CPU, so use lower quality TTS like YourTTS, Tacotron2 etc..\": \"* 现代 TTS 引擎在 CPU 上非常慢，因此请使用质量较低的 TTS，如 YourTTS、Tacotron2 等。\",\n \"zh-CN|Supported Languages\": \"支持的语言\",\n \"zh-CN|[**+1130 languages and dialects here**](https://dl.fbaipublicfiles.com/mms/tts/all-tts-languages.html)\": \"[**此处有 +1130 种语言和方言**](https://dl.fbaipublicfiles.com/mms/tts/all-tts-languages.html)\",\n \"zh-CN|Supported eBook Formats\": \"支持的电子书格式\",\n \"zh-CN|**Best results**: `.epub` or `.mobi` for automatic chapter detection\": \"**最佳效果**：使用 `.epub` 或 `.mobi` 进行自动章节检测\",\n \"zh-CN|Output and process Formats\": \"输出和处理格式\",\n \"zh-CN|Process format can be changed in lib/conf.py\": \"处理格式可在 lib/conf.py 中更改\",\n \"zh-CN|SML tags available\": \"可用的 SML 标签\",\n \"zh-CN|`[break]` — silence (random range **0.3–0.6 sec.**)\": \"`[break]` — 静音（随机范围 **0.3–0.6 sec.**）\",\n \"zh-CN|`[pause]` — silence (random range **1.0–1.6 sec.**)\": \"`[pause]` — 静音（随机范围 **1.0–1.6 sec.**）\",\n \"zh-CN|`[pause:N]` — fixed pause (**N sec.**)\": \"`[pause:N]` — 固定停顿（**N sec.**）\",\n \"zh-CN|`[voice:/path/to/voice/file]...[/voice]` — switch voice from default or selected voice from GUI/CLI\": \"`[voice:/path/to/voice/file]...[/voice]` — 从默认语音或从 GUI/CLI 选择的语音切换语音\",\n \"zh-CN|**Check our other repo dedicated to add SML automatically in your ebook -> [E2A-SML](./tools/E2A-SML)**\": \"**请查看我们另一个专门用于在电子书中自动添加 SML 的仓库 -> [E2A-SML](./tools/E2A-SML)**\",\n \"zh-CN|**Before to post an install or bug issue search carefully to the opened and closed issues TAB
\": \"**在发布安装或错误问题之前，请仔细搜索打开和已关闭问题的标签页
\",\n \"zh-CN|to be sure your issue does not exist already.**\": \"以确保您的问题尚不存在。**\",\n \"zh-CN|**EPUB format lacks any standard structure like what is a chapter, paragraph, preface etc.
\": \"**EPUB 格式缺乏任何定义什么是章节、段落、前言等的标准结构。
\",\n \"zh-CN|So you should first remove manually any text you don't want to be converted in audio.**\": \"因此，您应该首先手动删除任何不想转换为音频的文本。**\",\n \"zh-CN|**Install / Run ebook2audiobook**:\": \"**安装 / 运行 ebook2audiobook**：\",\n \"zh-CN|**Mac Launcher** \": \"**Mac 启动器** \",\n \"zh-CN|Double click `Mac Ebook2Audiobook Launcher.command`\": \"双击 `Mac Ebook2Audiobook Launcher.command`\",\n \"zh-CN|Note for Windows users: scoop is installed to install missing programs without administrator privileges.\": \"Windows 用户注意：将安装 scoop 以在没有管理员权限的情况下安装缺失的程序。\",\n \"zh-CN|**Open the Web App**: Click the URL provided in the terminal to access the web app and convert eBooks. `http://localhost:7860/`\": \"**打开 Web 应用**：点击终端中提供的 URL，以访问 Web 应用并转换电子书。 `http://localhost:7860/`\",\n \"zh-CN|**For Public Link**:\": \"**获取公共链接**：\",\n \"zh-CN|**If the script is stopped and run again, you need to refresh your gradio GUI interface
\": \"**如果脚本被停止并再次运行，您需要刷新您的 Gradio GUI 界面
\",\n \"zh-CN|to let the web page reconnect to the new connection socket.**\": \"以便网页能够重新连接到新的连接套接字。**\",\n \"zh-CN|**[--ebook]**: Path to your eBook file\": \"**[--ebook]**：电子书文件的路径\",\n \"zh-CN|**[--voice]**: Voice cloning file path (optional)\": \"**[--voice]**：语音克隆文件路径（可选）\",\n \"zh-CN|**[--language]**: Language code in ISO-639-3 (i.e.: ita for italian, eng for english, deu for german...).
\": \"**[--language]**：ISO-639-3 格式的语言代码（即：意大利语为 ita，英语为 eng，德语为 deu...）。
\",\n \"zh-CN|Default language is eng and --language is optional for default language set in ./lib/lang.py.
\": \"默认语言为 eng，对于 ./lib/lang.py 中设置的默认语言，--language 是可选的。
\",\n \"zh-CN|The ISO-639-1 2 letters codes are also supported.\": \"也支持 2 个字母的 ISO-639-1 代码。\",\n \"zh-CN|****: Path to `model_name.zip` file,\": \"****：`model_name.zip` 文件的路径，\",\n \"zh-CN|which must contain (according to the tts engine) all the mandatory files
\": \"该文件必须（根据 tts 引擎）包含所有必需文件
\",\n \"zh-CN|(see ./lib/models.py).\": \"（参见 ./lib/models.py）。\",\n \"zh-CN|NOTE: in gradio/gui mode, to cancel a running conversion, just click on the [X] from the ebook upload component.\": \"注意：在 gradio/gui 模式下，要取消正在进行的转换，只需点击电子书上传组件的 [X] 即可。\",\n \"zh-CN|TIP: if it needs some more pause, add '[pause:3]' for 3 sec. etc.\": \"提示：如果需要稍长的停顿，请添加 '[pause:3]' 表示 3 秒等。\",\n \"zh-CN|Common Docker Issues\": \"常见的 Docker 问题\",\n \"zh-CN|My NVIDIA GPU isn't being detected?? -> [GPU ISSUES Wiki Page](https://github.com/DrewThomasson/ebook2audiobook/wiki/GPU-ISSUES)\": \"未检测到我的 NVIDIA GPU？？ -> [GPU 问题 Wiki 页面](https://github.com/DrewThomasson/ebook2audiobook/wiki/GPU-ISSUES)\",\n \"zh-CN|Fine Tuned TTS models\": \"微调（fine-tuned）TTS 模型\",\n \"zh-CN|Fine Tune your own XTTSv2 model\": \"微调您自己的 XTTSv2 模型\",\n \"zh-CN|De-noise training data\": \"训练数据降噪\",\n \"zh-CN|Fine Tuned TTS Collection\": \"微调 TTS 模型集合\",\n \"zh-CN|For an XTTSv2 custom model a ref audio clip of the voice reference is mandatory:\": \"对于自定义 XTTSv2 模型，必须提供语音的参考音频片段：\",\n \"zh-CN|Your own Ebook2Audiobook customization\": \"您自己的 Ebook2Audiobook 自定义\",\n \"zh-CN|You are free to modify libs/conf.py to add or remove the settings you wish. If you plan to do it just make\": \"您可以自由修改 libs/conf.py 以添加或删除您想要的设置。如果您打算这样做，只需制作\",\n \"zh-CN|a copy of the original conf.py so on each ebook2audiobook update you will backup your modified conf.py and put\": \"原始 conf.py 的副本，这样在每次更新 ebook2audiobook 时，您可以备份修改后的 conf.py 并恢复\",\n \"zh-CN|back the original one. You must plan the same process for models.py. If you wish to make your own custom model\": \"原始文件。您必须为 models.py 计划相同的流程。如果您想将自己的自定义模型\",\n \"zh-CN|as an official ebook2audiobook fine tuned model so please contact us and we'll add it to the presets list.\": \"变成官方微调的 ebook2audiobook 模型，请联系我们，我们会将其添加到预设列表中。\",\n \"zh-CN|Common Issues:\": \"常见问题：\",\n \"zh-CN|My NVIDIA/ROCm/XPU/MPS GPU isn't being detected?? -> [GPU ISSUES Wiki Page](https://github.com/DrewThomasson/ebook2audiobook/wiki/GPU-ISSUES)\": \"未检测到我的 NVIDIA/ROCm/XPU/MPS GPU？？ -> [GPU ISSUES Wiki Page](https://github.com/DrewThomasson/ebook2audiobook/wiki/GPU-ISSUES)\",\n \"zh-CN|CPU is slow (better on server smp CPU) while GPU can have almost real time conversion.\": \"CPU 很慢（在服务器 SMP CPU 上更好），而 GPU 可以实现接近实时的转换。\",\n \"zh-CN|(It doesn't have zero-shot voice cloning though, and is Siri quality voices, but it is much faster on cpu).\": \"（不过它没有 zero-shot 语音克隆，是 Siri 质量的语音，但在 cpu 上快得多）。\",\n \"zh-CN|\\\"I'm having dependency issues\\\" - Just use the docker, its fully self contained and has a headless mode,\": \"“我遇到依赖项问题” - 只需使用 docker，它完全独立并具有 headless 模式，\",\n \"zh-CN|add `--help` parameter at the end of the docker run command for more information.\": \"在 docker run 命令末尾添加 `--help` 参数以获取更多信息。\",\n \"zh-CN|\\\"I'm getting a truncated audio issue!\\\" - PLEASE MAKE AN ISSUE OF THIS,\": \"“我遇到音频被截断的问题！” - 请就此创建一个 ISSUE，\",\n \"zh-CN|we don't speak every language and need advise from users to fine tune the sentence splitting logic.😊\": \"我们不会说每种语言，需要用户的建议来微调句子拆分逻辑。😊\",\n \"zh-CN|***** ROADMAP *****\": \"***** 路线图 *****\",\n \"zh-CN|All Features open to public Contributions ⭐\": \"所有功能均向公众贡献开放 ⭐\",\n \"zh-CN|Any help from people speaking any of the supported languages to help us improve the models ⭐\": \"来自任何说支持语言的人的任何帮助，以帮助我们改进模型 ⭐\",\n \"zh-CN|Preview Blocks/Chapters before to start the conversion\": \"在开始转换之前预览块/章节\",\n \"zh-CN|Edit by sentence converted for surgical text change\": \"按转换后的句子进行编辑，以进行精准的文本更改\",\n \"zh-CN|SML tags integration for voice, pause, break, and more changes \": \"用于语音、停顿、中断及更多更改的 SML 标签集成 \",\n \"zh-CN|-h -help parameter info in different languages\": \"不同语言的 -h -help 参数信息\",\n \"zh-CN|OCR scanning for PDF / JPG / BMP / PNG / TIFF\": \"针对 PDF / JPG / BMP / PNG / TIFF 的 OCR 扫描\",\n \"zh-CN|Notebooks Folder [Talked about here](https://github.com/DrewThomasson/ebook2audiobookXTTS/issues/5#issuecomment-2408773254)\": \"Notebooks 文件夹 [Talked about here](https://github.com/DrewThomasson/ebook2audiobookXTTS/issues/5#issuecomment-2408773254)\",\n \"zh-CN|Make Chinese text splitting not split words and improve pause timing [Talked about here](https://github.com/DrewThomasson/ebook2audiobookXTTS/issues/18#issuecomment-2401154894)\": \"使中文文本拆分不拆分单词并改善停顿时间 [Talked about here](https://github.com/DrewThomasson/ebook2audiobookXTTS/issues/18#issuecomment-2401154894)\",\n \"zh-CN|[Make a IOS app](https://github.com/DrewThomasson/ebook2audiobook/pull/35#issuecomment-2496495212)\": \"[制作 iOS 应用](https://github.com/DrewThomasson/ebook2audiobook/pull/35#issuecomment-2496495212)\",\n \"zh-CN|[Make an android app](https://github.com/DrewThomasson/ebook2audiobook/pull/35#issuecomment-2496495212)\": \"[制作 android 应用](https://github.com/DrewThomasson/ebook2audiobook/pull/35#issuecomment-2496495212)\",\n \"zh-CN|Audiobookshelf integration\": \"Audiobookshelf 集成\",\n \"zh-CN|Extra Options\": \"额外选项\",\n \"zh-CN|Ebook Translation option\": \"电子书翻译选项\",\n \"zh-CN|Output format choices\": \"输出格式选择\",\n \"zh-CN|Batch ebook folder\": \"批量电子书文件夹\",\n \"zh-CN|Multiprocessing conversion\": \"多进程转换\",\n \"zh-CN|Batch ebook folder conversion\": \"批量电子书文件夹转换\",\n \"zh-CN|GPU Device detection\": \"GPU 设备检测\",\n \"zh-CN|Denoise any reference audio for upload voice cloning,\": \"为上传的语音克隆对任何参考音频进行降噪，\",\n \"zh-CN|Custom model upload (XTTSv2 only for now. more on request)\": \"自定义模型上传（目前仅 XTTSv2。更多应需求提供）\",\n \"zh-CN|Add European Portuguese language model for xttsv2, fairseq, vits, piper at least (help welcome)\": \"至少为 xttsv2、fairseq、vits、piper 添加欧洲葡萄牙语语言模型（欢迎帮助）\",\n \"zh-CN|Add Sindhi language model for xttsv2, fairseq, vits, piper at least (help welcome)\": \"至少为 xttsv2、fairseq、vits、piper 添加信德语语言模型（欢迎帮助）\",\n \"zh-CN|Readme Translation\": \"Readme 翻译\",\n \"zh-CN|🐍 OS Compatibility\": \"🐍 操作系统兼容性\",\n \"zh-CN|Extra Overkill for training models and such (All supported Coqui-tts models and piper-tts in one easy command) \": \"用于训练模型等的额外杀手锏（所有支持的 Coqui-tts 模型和 piper-tts 通过一条简单命令） \",\n \"zh-CN|For info about this @DrewThomasson, he is currently working on the development of this, [work-in-progress-repo here](https://github.com/DrewThomasson/Universal_TTS_Finetune)\": \"有关此信息 @DrewThomasson，他目前正在进行其开发，[正在进行中的仓库在此处](https://github.com/DrewThomasson/Universal_TTS_Finetune)\",\n \"zh-CN|Make a easy to use training gui for all coqui-tts models in the ljspeech format training recipes [here from coqui tts](https://github.com/coqui-ai/TTS/tree/dev/recipes/ljspeech)\": \"为 ljspeech 格式训练配方中的所有 coqui-tts 模型创建一个易于使用的训练 gui [此处来自 coqui tts](https://github.com/coqui-ai/TTS/tree/dev/recipes/ljspeech)\",\n \"zh-CN|Python Code normalization information for contributors\": \"面向贡献者的 Python 代码规范化信息\",\n \"zh-CN|no blank line between code, unless between functions and classes.\": \"代码之间没有空行，函数和类之间除外。\",\n \"zh-CN|single quote used for all key unless for dict() and json. dict['key'] always called with single quote\": \"除 dict() 和 json 外，所有键均使用单引号。dict['key'] 始终用单引号调用\",\n \"zh-CN|4 spaces indentation, not tab at all\": \"4 个空格缩进，完全不使用制表符\",\n \"zh-CN|strict typing for all functions and its arguments declaration and return values\": \"对所有函数及其参数和返回值声明进行严格类型标注\",\n \"zh-CN|no space between the argument and its typing, no space between the function, the \\\"->\\\" and the return value\": \"参数与其类型标注之间无空格，函数、“->”和返回值之间无空格\",\n \"zh-CN|Example:\": \"示例：\",\n \"zh-CN|Hardware donation for beta tests wanted\": \"征求用于测试版测试的硬件捐赠\",\n \"zh-CN|We accept any kind of hardware to test our development like:\": \"我们接受任何类型的硬件来测试我们的开发，例如：\",\n \"zh-CN|@DrewThomasson if you want to help out at all! 😃\": \"@DrewThomasson 如果您想以任何方式提供帮助！ 😃\",\n \"zh-CN|Do you need to rent a GPU to boost service from us?\": \"您需要租用 GPU 来增强我们的服务吗？\",\n \"zh-CN|A poll is open here https://github.com/DrewThomasson/ebook2audiobook/discussions/889\": \"此处已开放投票 https://github.com/DrewThomasson/ebook2audiobook/discussions/889\",\n \"zh-CN|Special Thanks\": \"特别鸣谢\",\n \"zh-CN|[@shakenbake15 for better chapter saving method](https://github.com/DrewThomasson/ebook2audiobook/issues/8) \": \"[@shakenbake15 提供了更好的章节保存方法](https://github.com/DrewThomasson/ebook2audiobook/issues/8) \",\n \"zh-CN|TTS engines\": \"TTS引擎\",\n \"zh-CN|XTTSv2\": \"XTTSv2\",\n \"zh-CN|Bark\": \"巴克\",\n \"zh-CN|Fairseq\": \"公平交易\",\n \"zh-CN|VITS\": \"VITS\",\n \"zh-CN|Tacotron2\": \"Tacotron2\",\n \"zh-CN|YourTTS\": \"YourTTS\",\n \"zh-CN|Tortoise\": \"陸龜\",\n \"zh-CN|GlowTTS\": \"GlowTTS\",\n \"zh-CN|Piper\": \"胡椒属\",\n \"zh-CN|GPT-SoVITS (https://github.com/RVC-Boss/GPT-SoVITS)\": \"GPT-SoVITS (https://github.com/RVC-Boss/GPT-SoVITS)\",\n \"zh-CN|OpenVoice (https://github.com/myshell-ai/OpenVoice)\": \"OpenVoice (https://github.com/myshell-ai/OpenVoice)\",\n \"zh-CN|fish-speech (https://github.com/fishaudio/fish-speech)\": \"fish-speech (https://github.com/fishaudio/fish-speech)\",\n \"zh-CN|ChatTTS (https://github.com/2noise/ChatTTS)\": \"ChatTTS (https://github.com/2noise/ChatTTS)\",\n \"zh-CN|CosyVoice (https://github.com/FunAudioLLM/CosyVoice)\": \"CosyVoice (https://github.com/FunAudioLLM/CosyVoice)\",\n \"zh-CN|F5-TTS (https://github.com/swivid/f5-tts)\": \"F5-TTS (https://github.com/swivid/f5-tts)\",\n \"zh-CN|chatterbox (https://github.com/resemble-ai/chatterbox)\": \"chatterbox (https://github.com/resemble-ai/chatterbox)\",\n \"zh-CN|Supertonic (https://github.com/supertone-inc/supertonic)\": \"Supertonic (https://github.com/supertone-inc/supertonic)\",\n \"zh-CN|Spark-TTS (https://github.com/sparkaudio/spark-tts)\": \"Spark-TTS (https://github.com/sparkaudio/spark-tts)\",\n \"zh-CN|index-tts (https://github.com/index-tts/index-tts)\": \"index-tts (https://github.com/index-tts/index-tts)\",\n \"zh-CN|MeloTTS (https://github.com/myshell-ai/MeloTTS)\": \"MeloTTS (https://github.com/myshell-ai/MeloTTS)\",\n \"zh-CN|Kokoro-TTS (https://github.com/hexgrad/kokoro)\": \"Kokoro-TTS (https://github.com/hexgrad/kokoro)\",\n \"zh-CN|OmniVoice (https://github.com/k2-fsa/OmniVoice)\": \"OmniVoice (https://github.com/k2-fsa/OmniVoice)\",\n \"zh-CN|Zonos (https://github.com/Zyphra/Zonos)\": \"Zonos (https://github.com/Zyphra/Zonos)\",\n \"zh-CN|Style-TTS2 (https://github.com/yl4579/StyleTTS2)\": \"样式-TTS2 (https://github.com/yl4579/StyleTTS2)\",\n \"zh-CN|Orpheus-TTS (https://github.com/canopyai/Orpheus-TTS)\": \"Orpheus-TTS (https://github.com/canopyai/Orpheus-TTS)\",\n \"zh-CN|NewTTS (https://github.com/neuphonic/neutts?tab=readme-ov-file)\": \"NewTTS (https://github.com/neuphonic/neutts?tab=readme-ov-file)\",\n \"zh-CN|VIbeVoice (https://github.com/vibevoice-community/VibeVoice)\": \"VIbeVoice (https://github.com/vibevoice-community/VibeVoice)\",\n \"zh-CN|Qwen3-TTS (https://huggingface.co/spaces/Qwen/Qwen3-TTS)\": \"Qwen3-TTS (https://huggingface.co/spaces/Qwen/Qwen3-TTS)\",\n \"es|CPU/GPU Converter from E-Book to audiobook with chapters and metadata
\": \"Conversor CPU/GPU de libro electrónico a audiolibro con capítulos y metadatos
\",\n \"es|using advanced TTS engines and much more.
\": \"usando motores TTS avanzados y mucho más.
\",\n \"es|Supports voice cloning and 1158 languages!\": \"¡Admite clonación de voz y 1158 idiomas!\",\n \"es|**This tool is intended for use with non-DRM, legally acquired eBooks only.**
\": \"**Esta herramienta está destinada a usarse únicamente con libros electrónicos sin DRM y adquiridos legalmente.**
\",\n \"es|The authors are not responsible for any misuse of this software or any resulting legal consequences.
\": \"Los autores no se hacen responsables de ningún uso indebido de este software ni de las consecuencias legales que de ello se deriven.
\",\n \"es|Use this tool responsibly and in accordance with all applicable laws.\": \"Utiliza esta herramienta de forma responsable y conforme a todas las leyes aplicables.\",\n \"es|Thanks to support ebook2audiobook developers!\": \"¡Gracias por apoyar a los desarrolladores de ebook2audiobook!\",\n \"es|Run locally\": \"Ejecución local\",\n \"es|Run Remotely\": \"Ejecución remota\",\n \"es|GUI Interface\": \"Interfaz gráfica (GUI)\",\n \"es|Click to see images of Web GUI\": \"Haz clic para ver imágenes de la GUI web\",\n \"es|**New Default Voice Demo** \": \"**Demo de la nueva voz por defecto** \",\n \"es|More Demos\": \"Más demos\",\n \"es|**ASMR Voice** \": \"**Voz ASMR** \",\n \"es|**Rainy Day Voice** \": \"**Voz de día lluvioso** \",\n \"es|**Scarlett Voice**\": \"**Voz Scarlett**\",\n \"es|**David Attenborough Voice** \": \"**Voz David Attenborough** \",\n \"es|**Example**\": \"**Ejemplo**\",\n \"es|Table of Contents\": \"Tabla de contenidos\",\n \"es|[Features](#features)\": \"[Características](#features)\",\n \"es|[GUI Interface](#gui-interface)\": \"[Interfaz gráfica](#gui-interface)\",\n \"es|[Supported Languages](#supported-languages)\": \"[Idiomas admitidos](#supported-languages)\",\n \"es|[Minimum Requirements](#hardware-requirements)\": \"[Requisitos mínimos](#hardware-requirements)\",\n \"es|[Usage](#instructions)\": \"[Uso](#instructions)\",\n \"es|[Run Locally](#instructions)\": \"[Ejecución local](#instructions)\",\n \"es|[Launching Gradio Web Interface](#instructions)\": \"[Lanzar la interfaz web de Gradio](#instructions)\",\n \"es|[Basic Headless Usage](#basic-usage)\": \"[Uso básico sin interfaz (headless)](#basic-usage)\",\n \"es|[Headless Custom XTTS Model Usage](#example-of-custom-model-zip-upload)\": \"[Uso de modelo XTTS personalizado sin interfaz](#example-of-custom-model-zip-upload)\",\n \"es|[Help command output](#help-command-output)\": \"[Salida del comando de ayuda](#help-command-output)\",\n \"es|[Run Remotely](#run-remotely)\": \"[Ejecución remota](#run-remotely)\",\n \"es|[Steps to Run](#docker)\": \"[Pasos para ejecutar](#docker)\",\n \"es|[Common Docker Issues](#common-docker-issues)\": \"[Problemas habituales con Docker](#common-docker-issues)\",\n \"es|[Fine Tuned TTS models](#fine-tuned-tts-models)\": \"[Modelos TTS ajustados](#fine-tuned-tts-models)\",\n \"es|[Collection of Fine-Tuned TTS Models](#fine-tuned-tts-collection)\": \"[Colección de modelos TTS ajustados](#fine-tuned-tts-collection)\",\n \"es|[Train XTTSv2](#fine-tune-your-own-xttsv2-model)\": \"[Entrenar XTTSv2](#fine-tune-your-own-xttsv2-model)\",\n \"es|[Supported eBook Formats](#supported-ebook-formats)\": \"[Formatos de libro electrónico admitidos](#supported-ebook-formats)\",\n \"es|[Output Formats](#output-and-process-formats)\": \"[Formatos de salida](#output-and-process-formats)\",\n \"es|[Revert to older Version](#reverting-to-older-versions)\": \"[Volver a una versión anterior](#reverting-to-older-versions)\",\n \"es|[Common Issues](#common-issues)\": \"[Problemas habituales](#common-issues)\",\n \"es|[Special Thanks](#special-thanks)\": \"[Agradecimientos especiales](#special-thanks)\",\n \"es|[Table of Contents](#table-of-contents)\": \"[Tabla de contenidos](#table-of-contents)\",\n \"es|Features\": \"Características\",\n \"es|🔧 **TTS Engines supported**: `XTTSv2`, `Bark`, `Fairseq`, `VITS`, `Tacotron2`, `Tortoise`, `GlowTTS`, `YourTTS`\": \"🔧 **Motores TTS admitidos**: `XTTSv2`, `Bark`, `Fairseq`, `VITS`, `Tacotron2`, `Tortoise`, `GlowTTS`, `YourTTS`\",\n \"es|📚 **Convert multiple file formats**: `.epub`, `.mobi`, `.azw3`, `.fb2`, `.lrf`, `.rb`, `.snb`, `.tcr`, `.pdf`, `.txt`, `.rtf`, `.doc`, `.docx`, `.html`, `.odt`, `.azw`, `.tiff`, `.tif`, `.png`, `.jpg`, `.jpeg`, `.bmp`, `.zip`\": \"📚 **Convertir múltiples formatos de archivo**: `.epub`, `.mobi`, `.azw3`, `.fb2`, `.lrf`, `.rb`, `.snb`, `.tcr`, `.pdf`, `.txt`, `.rtf`, `.doc`, `.docx`, `.html`, `.odt`, `.azw`, `.tiff`, `.tif`, `.png`, `.jpg`, `.jpeg`, `.bmp`, `.zip`\",\n \"es|💻 **TextArea** to convert directly a short text in audio\": \"💻 **Área de texto** para convertir directamente un texto corto en audio\",\n \"es|🔍 **OCR scanning** for files with text pages as images\": \"🔍 **Escaneo OCR** para archivos con páginas de texto en forma de imágenes\",\n \"es|🔊 **High-quality text-to-speech** from near realtime to near real voice\": \"🔊 **Texto a voz de alta calidad**, desde casi en tiempo real hasta una voz casi real\",\n \"es|🗣️ **Optional voice cloning** using your own voice file\": \"🗣️ **Clonación de voz opcional** usando tu propio archivo de voz\",\n \"es|🌐 **Supports 1158 languages** ([supported languages list](https://dl.fbaipublicfiles.com/mms/tts/all-tts-languages.html))\": \"🌐 **Admite 1158 idiomas** ([supported languages list](https://dl.fbaipublicfiles.com/mms/tts/all-tts-languages.html))\",\n \"es|💻 **Low-resource friendly** — runs on **2 GB RAM / 1 GB VRAM (minimum)**\": \"💻 **Apto para recursos limitados** — funciona con **2 GB de RAM / 1 GB de VRAM (mínimo)**\",\n \"es|🎵 **Audiobook output formats**: mono or stereo `aac`, `flac`, `mp3`, `m4b`, `m4a`, `mp4`, `mov`, `ogg`, `wav`, `webm`\": \"🎵 **Formatos de salida del audiolibro**: mono or stereo `aac`, `flac`, `mp3`, `m4b`, `m4a`, `mp4`, `mov`, `ogg`, `wav`, `webm`\",\n \"es|🧠 **SML tags supported** — fine-grained control of breaks, pauses, voice switching and more ([see below](#sml-tags-available))\": \"🧠 **Etiquetas SML admitidas** — control preciso de cortes, pausas, cambio de voz y mucho más ([see below](#sml-tags-available))\",\n \"es|🧩 **Optional custom model** using your own trained model (XTTSv2, VITS, FAIRSEQ, PIPER, others on request)\": \"🧩 **Modelo personalizado opcional** usando tu propio modelo entrenado (XTTSv2, VITS, FAIRSEQ, PIPER, others on request)\",\n \"es|🎛️ **Fine-tuned preset models** trained by the E2A Team
\": \"🎛️ **Modelos preajustados y ajustados** entrenados por el equipo de E2A
\",\n \"es|(Contact us if you need additional fine-tuned models, or if you’d like to share yours to the official preset list)\": \"(Contáctanos si necesitas modelos ajustados adicionales, o si quieres compartir los tuyos en la lista oficial de preajustes)\",\n \"es|Hardware Requirements\": \"Requisitos de hardware\",\n \"es|2GB RAM min, 8GB recommended.\": \"2 GB de RAM mín., 8 GB recomendados.\",\n \"es|1GB VRAM min, 4GB recommended.\": \"1 GB de VRAM mín., 4 GB recomendados.\",\n \"es|Virtualization enabled if running on windows (Docker only).\": \"Virtualización habilitada si se ejecuta en Windows (solo Docker).\",\n \"es|MPS (Apple Silicon CPU)\": \"MPS (CPU Apple Silicon)\",\n \"es|* Modern TTS engines are ve"},"items":[{"name":"baseline_README.md","path":"tools/readme_i18n/baseline_README.md","rawUrl":"https://raw.githubusercontent.com/DrewThomasson/ebook2audiobook/HEAD/tools/readme_i18n/baseline_README.md","title":"Readme_i18n Skill","category":"anthropic-skill","format":"markdown","content":"# 📚 ebook2audiobook (E2A)\n\n\nCPU/GPU Converter from E-Book to audiobook with chapters and metadata
\nusing advanced TTS engines and much more.
\nSupports voice cloning and 1158 languages!\n> [!IMPORTANT]\n**This tool is intended for use with non-DRM, legally acquired eBooks only.**
\nThe authors are not responsible for any misuse of this software or any resulting legal consequences.
\nUse this tool responsibly and in accordance with all applicable laws.\n\n[](https://discord.gg/63Tv3F65k6)\n\n### Thanks to support ebook2audiobook developers!\n[](https://ko-fi.com/athomasson2) \n\n### Run locally\n\n[](#instructions)\n\n[](https://github.com/DrewThomasson/ebook2audiobook/actions/workflows/Docker-Build.yml) [](https://github.com/DrewThomasson/ebook2audiobook/releases/latest) \n\n\n\n \n\n\n\n\n### Run Remotely\n[](https://huggingface.co/spaces/drewThomasson/ebook2audiobook)\n[](https://colab.research.google.com/github/DrewThomasson/ebook2audiobook/blob/main/Notebooks/colab_ebook2audiobook.ipynb) [](https://github.com/Rihcus/ebook2audiobookXTTS/blob/main/Notebooks/kaggle-ebook2audiobook.ipynb)\n\n#### GUI Interface\n\n\n\n Click to see images of Web GUI
\n \n \n \n \n\n## Demos\n\n**New Default Voice Demo** \n\nhttps://github.com/user-attachments/assets/750035dc-e355-46f1-9286-05c1d9e88cea \n\n\n More Demos
\n\n**ASMR Voice** \n\nhttps://github.com/user-attachments/assets/68eee9a1-6f71-4903-aacd-47397e47e422\n\n**Rainy Day Voice** \n\nhttps://github.com/user-attachments/assets/d25034d9-c77f-43a9-8f14-0d167172b080 \n\n**Scarlett Voice**\n\nhttps://github.com/user-attachments/assets/b12009ee-ec0d-45ce-a1ef-b3a52b9f8693\n\n**David Attenborough Voice** \n\nhttps://github.com/user-attachments/assets/81c4baad-117e-4db5-ac86-efc2b7fea921\n\n**Example**\n\n\n \n\n## README.md\n\n## Table of Contents\n- [ebook2audiobook](#-ebook2audiobook)\n- [Features](#features)\n- [GUI Interface](#gui-interface)\n- [Demos](#demos)\n- [Supported Languages](#supported-languages)\n- [Minimum Requirements](#hardware-requirements)\n- [Usage](#instructions)\n - [Run Locally](#instructions)\n - [Launching Gradio Web Interface](#instructions)\n - [Basic Headless Usage](#basic-usage)\n - [Headless Custom XTTS Model Usage](#example-of-custom-model-zip-upload)\n - [Help command output](#help-command-output)\n - [Run Remotely](#run-remotely)\n - [Docker](#docker)\n - [Steps to Run](#docker)\n \n- [Cloned Voices](#cloned-voices)\n- [Fine Tuned TTS models](#fine-tuned-tts-models) \n - [Collection of Fine-Tuned TTS Models](#fine-tuned-tts-collection)\n - [Train TTS Model](#fine-tune-your-own-tts-model)\n- [Supported eBook Formats](#supported-ebook-formats)\n- [Output Formats](#output-and-process-formats)\n- [Revert to older Version](#reverting-to-older-versions)\n- [Common Issues](#common-issues)\n- [Special Thanks](#special-thanks)\n- [Table of Contents](#table-of-contents)\n\n\n## Features\n- 🔧 **TTS Engines supported**: `XTTSv2`, `Bark`, `Fairseq`, `VITS`, `Tacotron2`, `Tortoise`, `GlowTTS`, `YourTTS`\n- 📚 **Convert multiple file formats**: `.epub`, `.mobi`, `.azw3`, `.fb2`, `.lrf`, `.rb`, `.snb`, `.tcr`, `.pdf`, `.txt`, `.rtf`, `.doc`, `.docx`, `.html`, `.odt`, `.azw`, `.tiff`, `.tif`, `.png`, `.jpg`, `.jpeg`, `.bmp`, `.zip`\n- 💻 **TextArea** to convert directly a short text in audio\n- 🔍 **OCR scanning** for files with text pages as images\n- 🔊 **High-quality text-to-speech** from near realtime to near real voice\n- 🗣️ **Optional voice cloning** using your own voice file\n- 🌐 **Supports 1158 languages** ([supported languages list](https://dl.fbaipublicfiles.com/mms/tts/all-tts-languages.html))\n- 💻 **Low-resource friendly** — runs on **2 GB RAM / 1 GB VRAM (minimum)**\n- 🎵 **Audiobook output formats**: mono or stereo `aac`, `flac`, `mp3`, `m4b`, `m4a`, `mp4`, `mov`, `ogg`, `wav`, `webm`\n- 🧠 **SML tags supported** — fine-grained control of breaks, pauses, voice switching and more ([see below](#sml-tags-available))\n- 🧩 **Optional custom model** using your own trained model (XTTSv2, VITS, FAIRSEQ, PIPER, others on request)\n- 🎛️ **Fine-tuned preset models** trained by the E2A Team
\n (Contact us if you need additional fine-tuned models, or if you’d like to share yours to the official preset list)\n\n\n## Hardware Requirements\n- 2GB RAM min, 8GB recommended.\n- 1GB VRAM min, 4GB recommended.\n- Virtualization enabled if running on windows (Docker only).\n- CPU, XPU (intel, AMD, ARM)*.\n- CUDA, ROCm, JETSON\n- MPS (Apple Silicon CPU)\n\n* Modern TTS engines are very slow on CPU, so use lower quality TTS like YourTTS, Tacotron2 etc..\n\n## Supported Languages\n| **Arabic (ar)** | **Chinese (zh)** | **English (en)** | **Spanish (es)** |\n|:------------------:|:------------------:|:------------------:|:------------------:|\n| **French (fr)** | **German (de)** | **Italian (it)** | **Portuguese (pt)** |\n| **Polish (pl)** | **Turkish (tr)** | **Russian (ru)** | **Dutch (nl)** |\n| **Czech (cs)** | **Japanese (ja)** | **Hindi (hi)** | **Bengali (bn)** |\n| **Hungarian (hu)** | **Korean (ko)** | **Vietnamese (vi)**| **Swedish (sv)** |\n| **Persian (fa)** | **Yoruba (yo)** | **Swahili (sw)** | **Indonesian (id)**|\n| **Slovak (sk)** | **Croatian (hr)** | **Tamil (ta)** | **Danish (da)** |\n- [**+1130 languages and dialects here**](https://dl.fbaipublicfiles.com/mms/tts/all-tts-languages.html)\n\n\n## Supported eBook Formats\n- `.epub`, `.pdf`, `.mobi`, `.txt`, `.html`, `.rtf`, `.chm`, `.lit`,\n `.pdb`, `.fb2`, `.odt`, `.cbr`, `.cbz`, `.prc`, `.lrf`, `.pml`,\n `.snb`, `.cbc`, `.rb`, `.tcr`\n- **Best results**: `.epub` or `.mobi` for automatic chapter detection\n\n## Output and process Formats\n- `.m4b`, `.m4a`, `.mp4`, `.webm`, `.mov`, `.mp3`, `.flac`, `.wav`, `.ogg`, `.aac`\n- Process format can be changed in lib/conf.py\n\n## SML tags available\n- `[break]` — silence (random range **0.3–0.6 sec.**)\n- `[pause]` — silence (random range **1.0–1.6 sec.**)\n- `[pause:N]` — fixed pause (**N sec.**)\n- `[voice:/path/to/voice/file]...[/voice]` — switch voice from default or selected voice from GUI/CLI\n\n**Check our other repo dedicated to add SML automatically in your ebook -> [E2A-SML](https://github.com/DrewThomasson/E2A-SML)**\n\n> [!IMPORTANT]\n**Before to post an install or bug issue search carefully to the opened and closed issues TAB
\nto be sure your issue does not exist already.**\n\n>[!NOTE]\n**EPUB format lacks any standard structure like what is a chapter, paragraph, preface etc.
\nSo you should first remove manually any text you don't want to be converted in audio.**\n\n\n### Instructions \n1. **Clone repo**\n\t```bash\n\tgit clone https://github.com/DrewThomasson/ebook2audiobook.git\n\tcd ebook2audiobook\n\t```\n\n2. **Install / Run ebook2audiobook**:\n\n - **Linux/MacOS** \n ```bash\n ./ebook2audiobook.command\n ```\n Note for MacOS users: homebrew is installed to install missing programs.\n \n - **Mac Launcher** \n Double click `Mac Ebook2Audiobook Launcher.command`\n\n\n - **Windows** \n ```bash\n ebook2audiobook.cmd\n ```\n or\n Double click `ebook2audiobook.cmd`\n\n Note for Windows users: scoop is installed to install missing programs without administrator privileges.\n \n1. **Open the Web App**: Click the URL provided in the terminal to access the web app and convert eBooks. `http://localhost:7860/`\n2. **For Public Link**:\n `./ebook2audiobook.command --share` (Linux/MacOS)\n `ebook2audiobook.cmd --share` (Windows)\n `python app.py --share` (all OS)\n\n> [!IMPORTANT]\n**If the script is stopped and run again, you need to refresh your gradio GUI interface
\nto let the web page reconnect to the new connection socket.**\n\n### Basic Usage\n - **Linux/MacOS**:\n ```bash\n ./ebook2audiobook.command --headless --ebook --voice --language \n ```\n - **Windows**\n ```bash\n ebook2audiobook.cmd --headless --ebook --voice --language \n ```\n \n - **[--ebook]**: Path to your eBook file\n - **[--voice]**: Voice cloning file path (optional)\n - **[--language]**: Language code in ISO-639-3 (i.e.: ita for italian, eng for english, deu for german...).
\n Default language is eng and --language is optional for default language set in ./lib/lang.py.
\n The ISO-639-1 2 letters codes are also supported.\n\n\n### Example of Custom Model Zip Upload\n (must be a .zip file containing the mandatory model files. Example for XTTSv2: config.json, model.pth, vocab.json and ref.wav)\n - **Linux/MacOS**\n ```bash\n ./ebook2audiobook.command --headless --ebook --language --custom_model \n ```\n - **Windows**\n ```bash\n ebook2audiobook.cmd --headless --ebook --language --custom_model \n ```\n Note: the ref.wav of your custom model is always the voice selected for the conversion\n \n- ****: Path to `model_name.zip` file,\n which must contain (according to the tts engine) all the mandatory files
\n (see ./lib/models.py).\n\n### For Detailed Guide with list of all Parameters to use\n - **Linux/MacOS**\n ```bash\n ./ebook2audiobook.command --help\n ```\n - **Windows**\n ```bash\n ebook2audiobook.cmd --help\n ```\n - **Or for all OS**\n ```python\n app.py --help\n ```\n\n\n```bash\nusage: app.py [-h] [--session SESSION] [--share] [--headless] [--ebook EBOOK] [--ebooks_dir EBOOKS_DIR]\n [--language LANGUAGE] [--voice VOICE] [--voice_map VOICE_MAP] [--device {CPU,CUDA,MPS,ROCM,XPU,JETSON}]\n [--tts_engine {XTTS,BARK,VITS,FAIRSEQ,TACOTRON,YOURTTS,xtts,bark,vits,fairseq,tacotron,yourtts}]\n [--custom_model CUSTOM_MODEL] [--fine_tuned FINE_TUNED] [--output_format OUTPUT_FORMAT]\n [--output_channel OUTPUT_CHANNEL] [--temperature TEMPERATURE] [--length_penalty LENGTH_PENALTY]\n [--num_beams NUM_BEAMS] [--repetition_penalty REPETITION_PENALTY] [--top_k TOP_K] [--top_p TOP_P]\n [--speed SPEED] [--enable_text_splitting] [--text_temp TEXT_TEMP] [--waveform_temp WAVEFORM_TEMP]\n [--output_dir OUTPUT_DIR] [--version]\n\nConvert eBooks to Audiobooks using a Text-to-Speech model. You can either launch the Gradio interface or run the script in headless mode for direct conversion.\n\noptions:\n -h, --help show this help message and exit\n --session SESSION Session to resume the conversion in case of interruption, crash,\n or reuse of custom models and custom cloning voices.\n\n**** The following option is for gradio/gui mode only:\n --share (Optional) Enable a public shareable Gradio link.\n\n**** The following options are for --headless mode only:\n --headless Run the script in headless mode\n --ebook EBOOK Path to the ebook file for conversion. Cannot be used when --ebooks_dir is present.\n --ebooks_dir EBOOKS_DIR\n Relative or absolute path of the directory containing the files to convert.\n Cannot be used when --ebook is present.\n --text TEXT Raw text for conversion. Cannot be used when --ebook or --ebooks_dir is present.\n --language LANGUAGE Language of the e-book. Default language is set\n in ./lib/lang.py sed as default if not present. All compatible language codes are in ./lib/lang.py\n\noptional parameters:\n --translate ISO3 (Optional) Translate ebook to a target language (ISO 639-3 code, e.g. eng, fra, deu) before TTS synthesis.\n Uses argostranslate. The target language becomes the effective TTS language for the run.\n A copy of the source ebook is made with the _ suffix so translated and non-translated\n outputs stay isolated (independent process folder, audio chunks, and final file).\n --voice VOICE (Optional) Path to the voice cloning file for TTS engine.\n Uses the default voice if not present.\n --voice_map VOICE_MAP\n (Optional, --ebooks_dir only) Path to a JSON file mapping ebook path -> voice path.\n Each entry overrides --voice for that specific ebook. Missing/null entries fall back to --voice.\n Keys may be absolute paths or basenames. Example:\n {\"book1.epub\": \"/voices/eng/adult/female/alice.wav\", \"/abs/path/book2.epub\": null}\n --device {CPU,CUDA,MPS,ROCM,XPU,JETSON}\n (Optional) Processor unit type for the conversion.\n Default is set in ./lib/conf.py if not present. Fall back to CPU if CUDA or MPS is not available.\n --tts_engine {XTTS,BARK,VITS,FAIRSEQ,TACOTRON,YOURTTS,xtts,bark,vits,fairseq,tacotron,yourtts}\n (Optional) Preferred TTS engine (available are: ['XTTS', 'BARK', 'VITS', 'FAIRSEQ', 'TACOTRON', 'YOURTTS', 'xtts', 'bark', 'vits', 'fairseq', 'tacotron', 'yourtts'].\n Default depends on the selected language. The tts engine should be compatible with the chosen language\n --custom_model CUSTOM_MODEL\n (Optional) Path to the custom model zip file cntaining mandatory model files.\n Please refer to ./lib/models.py\n --fine_tuned FINE_TUNED\n (Optional) Fine tuned model path. Default is builtin model.\n --output_format OUTPUT_FORMAT\n (Optional) Output audio format. Default is m4b set in ./lib/conf.py\n --output_channel OUTPUT_CHANNEL\n (Optional) Output audio channel. Default is mono set in ./lib/conf.py\n --temperature TEMPERATURE\n (xtts only, optional) Temperature for the model.\n Default to config.json model. Higher temperatures lead to more creative outputs.\n --length_penalty LENGTH_PENALTY\n (xtts only, optional) A length penalty applied to the autoregressive decoder.\n Default to config.json model. Not applied to custom models.\n --num_beams NUM_BEAMS\n (xtts only, optional) Controls how many alternative sequences the model explores. Must be equal or greater than length penalty.\n Default to config.json model.\n --repetition_penalty REPETITION_PENALTY\n (xtts only, optional) A penalty that prevents the autoregressive decoder from repeating itself.\n Default to config.json model.\n --top_k TOP_K (xtts only, optional) Top-k sampling.\n Lower values mean more likely outputs and increased audio generation speed.\n Default to config.json model.\n --top_p TOP_P (xtts only, optional) Top-p sampling.\n Lower values mean more likely outputs and increased audio generation speed. Default to config.json model.\n --speed SPEED (xtts only, optional) Speed factor for the speech generation.\n Default to config.json model.\n --enable_text_splitting\n (xtts only, optional) Enable TTS text splitting. This option is known to not be very efficient.\n Default to config.json model.\n --text_temp TEXT_TEMP\n (bark only, optional) Text Temperature for the model.\n Default to config.json model.\n --waveform_temp WAVEFORM_TEMP\n (bark only, optional) Waveform Temperature for the model.\n Default to config.json model.\n --output_dir OUTPUT_DIR\n (Optional) Path to the output directory. Default is set in ./lib/conf.py\n --abs_url ABS_URL Audiobookshelf server URL (e.g. http://localhost:13378).\n --abs_api_token ABS_API_TOKEN\n Audiobookshelf API token.\n --abs_library ABS_LIBRARY\n Audiobookshelf library ID.\n --enable_interlude Add MusicGen music before the first chapter, between chapters, and at the end of the audiobook. Settings are in ./lib/conf_interlude.py\n --version Show the version of the script and exit\n\nExample usage:\nWindows:\n Gradio/GUI:\n ebook2audiobook.cmd\n Headless mode:\n ebook2audiobook.cmd --headless --ebook '/path/to/file' --language eng\nLinux/Mac:\n Gradio/GUI:\n ./ebook2audiobook.command\n Headless mode:\n ./ebook2audiobook.command --headless --ebook '/path/to/file' --language eng\n\nSML tags available:\n\t[break] — silence (random range **0.3–0.6 sec.**)\n\t[pause] — silence (random range **1.0–1.6 sec.**)\n\t[pause:N] — fixed pause (**N sec.**)\n\t[voice:/path/to/voice/file]...[/voice] — switch voice from default or selected voice from GUI/CLI\n\n```\n\nNOTE: in gradio/gui mode, to cancel a running conversion, just click on the [X] from the ebook upload component.\nTIP: if it needs some more pause, add '[pause:3]' for 3 sec. etc.\n\n### Docker\n1. **Clone the Repository**:\n```bash\n git clone https://github.com/DrewThomasson/ebook2audiobook.git\n cd ebook2audiobook\n```\n2. **Build the container**\n```bash\n Windows:\n Docker:\n ebook2audiobook.cmd --script_mode build_docker\n Docker Compose:\n ebook2audiobook.cmd --script_mode build_docker --docker_mode compose\n Podman Compose:\n ebook2audiobook.cmd --script_mode build_docker --docker_mode podman\n Linux/Mac\n Docker:\n ./ebook2audiobook.command --script_mode build_docker\n Docker Compose\n ./ebook2audiobook.command --script_mode build_docker --docker_mode compose\n Podman Compose:\n ./ebook2audiobook.command --script_mode build_docker --docker_mode podman\n```\n4. **Run the Container:**\n```bash\nDocker run image:\n Gradio/GUI:\n CPU:\n docker run -v \"./ebooks:/app/ebooks\" -v \"./audiobooks:/app/audiobooks\" -v \"./models:/app/models\" -v \"./voices:/app/voices\" -v \"./tmp:/app/tmp\" --rm -it -p 7860:7860 athomasson2/ebook2audiobook:cpu\n CUDA:\n docker run -v \"./ebooks:/app/ebooks\" -v \"./audiobooks:/app/audiobooks\" -v \"./models:/app/models\" -v \"./voices:/app/voices\" -v \"./tmp:/app/tmp\" --gpus all --rm -it -p 7860:7860 athomasson2/ebook2audiobook:cu[118/122/124/126 etc..]\n ROCM:\n docker run -v \"./ebooks:/app/ebooks\" -v \"./audiobooks:/app/audiobooks\" -v \"./models:/app/models\" -v \"./voices:/app/voices\" -v \"./tmp:/app/tmp\" --device=/dev/kfd --device=/dev/dri --rm -it -p 7860:7860 athomasson2/ebook2audiobook:rocm[6.0/6.1/6.4 etc..]\n XPU:\n docker run -v \"./ebooks:/app/ebooks\" -v \"./audiobooks:/app/audiobooks\" -v \"./models:/app/models\" -v \"./voices:/app/voices\" -v \"./tmp:/app/tmp\" --device=/dev/dri --rm -it -p 7860:7860 athomasson2/ebook2audiobook:xpu\n JETSON:\n docker run -v \"./ebooks:/app/ebooks\" -v \"./audiobooks:/app/audiobooks\" -v \"./models:/app/models\" -v \"./voices:/app/voices\" -v \"./tmp:/app/tmp\" --runtime nvidia --rm -it -p 7860:7860 athomasson2/ebook2audiobook:jetson[51/60/61 etc...]\n Headless mode:\n CPU:\n docker run -v \"./ebooks:/app/ebooks\" -v \"./audiobooks:/app/audiobooks\" -v \"./models:/app/models\" -v \"./voices:/app/voices\" -v \"./tmp:/app/tmp\" -v \"/my/real/ebooks/folder/absolute/path:/app/another_ebook_folder\" --rm -it -p 7860:7860 ebook2audiobook:cpu --headless --ebook \"/app/another_ebook_folder/myfile.pdf\" [--voice /app/my/voicepath/voice.mp3 etc..]\n CUDA:\n docker run -v \"./ebooks:/app/ebooks\" -v \"./audiobooks:/app/audiobooks\" -v \"./models:/app/models\" -v \"./voices:/app/voices\" -v \"./tmp:/app/tmp\" -v \"/my/real/ebooks/folder/absolute/path:/app/another_ebook_folder\" --gpus all --rm -it -p 7860:7860 ebook2audiobook:cu[118/122/124/126 etc..] --headless --ebook \"/app/another_ebook_folder/myfile.pdf\" [--voice /app/my/voicepath/voice.mp3 etc..]\n ROCM:\n docker run -v \"./ebooks:/app/ebooks\" -v \"./audiobooks:/app/audiobooks\" -v \"./models:/app/models\" -v \"./voices:/app/voices\" -v \"./tmp:/app/tmp\" -v \"/my/real/ebooks/folder/absolute/path:/app/another_ebook_folder\" --device=/dev/kfd --device=/dev/dri --rm -it -p 7860:7860 ebook2audiobook:rocm[6.0/6.1/6.4 etc.] --headless --ebook \"/app/another_ebook_folder/myfile.pdf\" [--voice /app/my/voicepath/voice.mp3 etc..]\n XPU:\n docker run -v \"./ebooks:/app/ebooks\" -v \"./audiobooks:/app/audiobooks\" -v \"./models:/app/models\" -v \"./voices:/app/voices\" -v \"./tmp:/app/tmp\" -v \"/my/real/ebooks/folder/absolute/path:/app/another_ebook_folder\" --device=/dev/dri --rm -it -p 7860:7860 ebook2audiobook:xpu --headless --ebook \"/app/another_ebook_folder/myfile.pdf\" [--voice /app/my/voicepath/voice.mp3 etc..]\n JETSON:\n docker run -v \"./ebooks:/app/ebooks\" -v \"./audiobooks:/app/audiobooks\" -v \"./models:/app/models\" -v \"./voices:/app/voices\" -v \"./tmp:/app/tmp\" -v \"/my/real/ebooks/folder/absolute/path:/app/another_ebook_folder\" --runtime nvidia --rm -it -p 7860:7860 ebook2audiobook:jetson[51/60/61 etc.] --headless --ebook \"/app/another_ebook_folder/myfile.pdf\" [--voice /app/my/voicepath/voice.mp3 etc..]\nDocker Compose (i.e. cuda 12.8:\n Run Gradio GUI:\n DEVICE_TAG=cu128 docker compose --profile gpu up --no-log-prefix\n Run Headless mode:\n DEVICE_TAG=cu128 docker compose --profile gpu run --rm ebook2audiobook --headless --ebook \"/app/ebooks/myfile.pdf\" --voice /app/voices/eng/adult/female/some_voice.wav etc..\nPodman Compose (i.e. cuda 12.8:\n Run Gradio GUI:\n DEVICE_TAG=cu128 podman-compose -f podman-compose.yml --profile gpu up\n Run Headless mode:\n DEVICE_TAG=cu128 podman-compose -f podman-compose.yml --profile gpu run --rm ebook2audiobook-gpu --headless --ebook \"/app/ebooks/myfile.pdf\" --voice /app/voices/eng/adult/female/some_voice.wav etc..\n```\n- NOTE: MPS is not exposed in docker so CPU must be used\n\n## Cloned Voices\nYou can upload any voice audio in any of the supported audio formats, the ideal duration is around 1 to 5 mn.\nIt doesn't matter if the recording has a noisy background or music playing over it — E2A will clean up the voice for you.\n\nThe built-in cloned voices list is mainly in English. If you need voices in other languages to be officially\nadded to the list, please contact us and we'll add them after review.\n\n## Fine Tuned TTS models\n#### Fine Tune your own TTS model\n\n[Universal_TTS_Finetune](https://github.com/DrewThomasson/Universal_TTS_Finetune)\n\n#### De-noise training data\n\n[](https://huggingface.co/spaces/drewThomasson/DeepFilterNet2_no_limit) [](https://github.com/Rikorose/DeepFilterNet)\n\n\n### Fine Tuned TTS Collection\n\n[](https://huggingface.co/drewThomasson/fineTunedTTSModels/tree/main)\n\nFor an XTTSv2 custom model a ref audio clip of the voice reference is mandatory:\n\n## Your own Ebook2Audiobook customization\nYou are free to modify libs/conf.py to add or remove the settings you wish. If you plan to do it just make\na copy of the original conf.py so on each ebook2audiobook update you will backup your modified conf.py and put\nback the original one. You must plan the same process for models.py. If you wish to make your own custom model\nas an official ebook2audiobook fine tuned model so please contact us and we'll add it to the presets list.\n\n## Reverting to older Versions\nReleases can be found -> [here](https://github.com/DrewThomasson/ebook2audiobook/releases)\n```bash\ngit checkout tags/VERSION_NUM # Locally/Compose -> Example: git checkout tags/v25.7.7\n```\n\n## Common Issues:\n- My NVIDIA/ROCm/XPU/MPS GPU isn't being detected?? -> [GPU ISSUES Wiki Page](https://github.com/DrewThomasson/ebook2audiobook/wiki/GPU-ISSUES)\n- CPU is slow (better on server smp CPU) while GPU can have almost real time conversion.\n [Discussion about this](https://github.com/DrewThomasson/ebook2audiobook/discussions/19#discussioncomment-10879846)\n (It doesn't have zero-shot voice cloning though, and is Siri quality voices, but it is much faster on cpu).\n- \"I'm having dependency issues\" - Just use the docker, its fully self contained and has a headless mode,\n add `--help` parameter at the end of the docker run command for more information.\n- \"I'm getting a truncated audio issue!\" - PLEASE MAKE AN ISSUE OF THIS,\n we don't speak every language and need advise from users to fine tune the sentence splitting logic.😊\n\n## ***** ROADMAP *****\n- All Features open to public Contributions ⭐\n- Any help from people speaking any of the supported languages to help us improve the models ⭐\n- [x] Preview Blocks/Chapters before to start the conversion\n- [x] Edit by sentence converted for surgical text change\n- [x] Generate music intros, interludes, and endings; edit interludes and endings\n- [x] SML tags integration for voice, pause, break, and more changes \n- [x] -h -help parameter info in different languages\n- [x] OCR scanning for PDF / JPG / BMP / PNG / TIFF\n- [x] Notebooks Folder [Talked about here](https://github.com/DrewThomasson/ebook2audiobookXTTS/issues/5#issuecomment-2408773254)\n- [x] Make Chinese text splitting not split words and improve pause timing [Talked about here](https://github.com/DrewThomasson/ebook2audiobookXTTS/issues/18#issuecomment-2401154894)\n- [x] Dockerfile\n- [x] Docker compose\n- [x] Podman compose \n- [x] Kaggle Notebook\n- [x] Google Colab Notebook\n- [x] Audiobookshelf integration\n- [x] Ebook Translation option\n- [x] Output format choices\n- [x] Multiprocessing conversion\n- [x] Batch ebook folder conversion\n- [x] GPU Device detection\n- [x] Denoise any background reference audio for voice cloning upload\n- [x] Custom fine-tuned model upload\n- [ ] [Make a IOS app](https://github.com/DrewThomasson/ebook2audiobook/pull/35#issuecomment-2496495212)\n- [ ] [Make an android app](https://github.com/DrewThomasson/ebook2audiobook/pull/35#issuecomment-2496495212)\n\n#### User Requests\n- [ ] Add European Portuguese language model for xttsv2, fairseq, vits, piper at least (help welcome)\n- [ ] Add Sindhi language model for xttsv2, fairseq, vits, piper at least (help welcome)\n\n#### TTS engines\n- [x] XTTSv2\n- [x] Bark\n- [x] Fairseq\n- [x] VITS\n- [x] Tacotron2\n- [x] YourTTS\n- [x] Tortoise\n- [x] GlowTTS\n- [x] Piper\n- [ ] GPT-SoVITS (https://github.com/RVC-Boss/GPT-SoVITS)\n- [ ] OpenVoice (https://github.com/myshell-ai/OpenVoice)\n- [ ] fish-speech (https://github.com/fishaudio/fish-speech)\n- [ ] ChatTTS (https://github.com/2noise/ChatTTS)\n- [ ] CosyVoice (https://github.com/FunAudioLLM/CosyVoice)\n- [ ] F5-TTS (https://github.com/swivid/f5-tts)\n- [ ] chatterbox (https://github.com/resemble-ai/chatterbox)\n- [ ] Supertonic (https://github.com/supertone-inc/supertonic)\n- [ ] Spark-TTS (https://github.com/sparkaudio/spark-tts)\n- [ ] index-tts (https://github.com/index-tts/index-tts)\n- [ ] MeloTTS (https://github.com/myshell-ai/MeloTTS)\n- [ ] Kokoro-TTS (https://github.com/hexgrad/kokoro)\n- [ ] OmniVoice (https://github.com/k2-fsa/OmniVoice)\n- [ ] Zonos (https://github.com/Zyphra/Zonos)\n- [ ] Style-TTS2 (https://github.com/yl4579/StyleTTS2)\n- [ ] Orpheus-TTS (https://github.com/canopyai/Orpheus-TTS)\n- [ ] NewTTS (https://github.com/neuphonic/neutts?tab=readme-ov-file)\n- [ ] VIbeVoice (https://github.com/vibevoice-community/VibeVoice)\n- [ ] Qwen3-TTS (https://huggingface.co/spaces/Qwen/Qwen3-TTS)\n\n#### Readme Translation\n- [x] Arabic (ara)\n- [x] Chinese (zho)\n- [x] English (eng)\n- [x] Spanish (spa)\n- [x] French (fra)\n- [x] German (deu)\n- [x] Italian (ita)\n- [x] Portuguese (por)\n- [x] Polish (pol)\n- [x] Turkish (tur)\n- [x] Russian (rus)\n- [x] Dutch (nld)\n- [x] Czech (ces)\n- [x] Japanese (jpn)\n- [x] Hindi (hin)\n- [x] Bengali (ben)\n- [x] Hungarian (hun)\n- [x] Korean (kor)\n- [x] Vietnamese (vie)\n- [x] Swedish (swe)\n- [x] Persian (fas)\n- [x] Yoruba (yor)\n- [x] Swahili (swa)\n- [x] Indonesian (ind)\n- [x] Slovak (slk)\n- [x] Croatian (hrv)\n\n#### 🐍 OS Compatibility\n- [x] 🍎 Mac Intel x86\n- [x] 🪟 Windows x86\n- [x] 🐧 Linux x86\n- [x] 🖥️🍏 Apple Silicon Mac\n- [x] 🪟💪 ARM Windows\n- [x] 🐧💪 ARM Linux\n\n**********\n\n## Extra Overkill for training models and such (All supported Coqui-tts models and piper-tts in one easy command) \n- For info about this @DrewThomasson, he is currently working on the development of this, [Universal TTS Finetune](https://github.com/DrewThomasson/Universal_TTS_Finetune)\n- [x] Make a easy to use training gui for all coqui-tts models in the [ljspeech format training recipes](https://github.com/coqui-ai/TTS/tree/dev/recipes/ljspeech) Completed at [Universal TTS Finetune](https://github.com/DrewThomasson/Universal_TTS_Finetune)\n\n\n## Python Code normalization information for contributors\n- no blank line between code, unless between functions and classes.\n- single quote used for all key unless for dict() and json. dict['key'] always called with single quote\n- 4 spaces indentation, not tab at all\n- strict typing for all functions and its arguments declaration and return values\n- no space between the argument and its typing, no space between the function, the \"->\" and the return value\n\nExample:\n\n```python\nimport json\nfrom typing import Optional\n\ndef get_user(user_id:int, users:list[dict])->Optional[dict]:\n for user in users:\n if user['id'] == user_id:\n return user\n return None\n\ndef summarize(user:dict)->str:\n return f\"User {user['name']} is {'active' if user['is_active'] else 'inactive'}.\"\n\ndef to_json(user:dict)->str:\n return json.dumps({\"id\": user['id'], \"name\": user['name'], \"email\": user['email']})\n\nusers:list = [\n dict(id=1, name=\"alice\", email=\"alice@example.com\", role=\"admin\", is_active=True),\n dict(id=2, name=\"bob\", email=\"bob@example.com\", role=\"editor\", is_active=False),\n dict(id=3, name=\"carol\", email=\"carol@example.com\", role=\"viewer\", is_active=True),\n]\nconfig = {\n \"max_users\": 100,\n \"default_role\": \"viewer\",\n \"allow_signup\": True,\n}\nroles = ['admin', 'editor', 'viewer']\nfound = get_user(1, users)\nif found:\n print(summarize(found))\n print(found['email'])\n print(to_json(found))\nif config['default_role'] in roles:\n print(config['default_role'])\n```\n\n## Hardware donation for beta tests wanted\nWe accept any kind of hardware to test our development like:\n- Nvidia supporting cuda >= 11.8\n- XPU intel cards\n- ROCm AMD cards supporting ROCm >=5.7\n\n@DrewThomasson if you want to help out at all! 😃\n\n\n## Special Thanks\nTo all financial and code contributors, each contribution and suggestion helps to improve the quality of E2A.\n","isInternal":false,"tokens":9329,"sizeBytes":33009},{"name":"cache.json","path":"tools/readme_i18n/cache.json","rawUrl":"https://raw.githubusercontent.com/DrewThomasson/ebook2audiobook/HEAD/tools/readme_i18n/cache.json","title":"Readme_i18n Skill","category":"anthropic-skill","format":"json","content":"{\n \"ar|Thanks to support ebook2audiobook developers!\": \"شكرًا لدعمك لمطوّري ebook2audiobook!\",\n \"ar|Run locally\": \"التشغيل محليًا\",\n \"ar|Run Remotely\": \"التشغيل عن بُعد\",\n \"ar|GUI Interface\": \"الواجهة الرسومية (GUI)\",\n \"ar|Click to see images of Web GUI\": \"انقر لرؤية صور واجهة الويب الرسومية\",\n \"ar|Demos\": \"عروض توضيحية\",\n \"ar|**New Default Voice Demo** \": \"**عرض توضيحي للصوت الافتراضي الجديد** \",\n \"ar|More Demos\": \"المزيد من العروض التوضيحية\",\n \"ar|**ASMR Voice** \": \"**صوت ASMR** \",\n \"ar|**Rainy Day Voice** \": \"**صوت يوم ممطر** \",\n \"ar|**Scarlett Voice**\": \"**صوت سكارليت**\",\n \"ar|**David Attenborough Voice** \": \"**صوت ديفيد أتينبورو** \",\n \"ar|**Example**\": \"**مثال**\",\n \"ar|Table of Contents\": \"جدول المحتويات\",\n \"ar|[Features](#features)\": \"[الميزات](#features)\",\n \"ar|[GUI Interface](#gui-interface)\": \"[الواجهة الرسومية](#gui-interface)\",\n \"ar|[Demos](#demos)\": \"[عروض توضيحية](#demos)\",\n \"ar|[Supported Languages](#supported-languages)\": \"[اللغات المدعومة](#supported-languages)\",\n \"ar|[Minimum Requirements](#hardware-requirements)\": \"[الحد الأدنى من المتطلبات](#hardware-requirements)\",\n \"ar|[Usage](#instructions)\": \"[الاستخدام](#instructions)\",\n \"ar|[Run Locally](#instructions)\": \"[التشغيل محليًا](#instructions)\",\n \"ar|[Launching Gradio Web Interface](#instructions)\": \"[تشغيل واجهة الويب Gradio](#instructions)\",\n \"ar|[Basic Headless Usage](#basic-usage)\": \"[الاستخدام الأساسي بدون واجهة](#basic-usage)\",\n \"ar|[Headless Custom XTTS Model Usage](#example-of-custom-model-zip-upload)\": \"[استخدام نموذج XTTS مخصص بدون واجهة](#example-of-custom-model-zip-upload)\",\n \"ar|[Help command output](#help-command-output)\": \"[مخرجات أمر المساعدة](#help-command-output)\",\n \"ar|[Run Remotely](#run-remotely)\": \"[التشغيل عن بُعد](#run-remotely)\",\n \"ar|[Steps to Run](#docker)\": \"[خطوات التشغيل](#docker)\",\n \"ar|[Common Docker Issues](#common-docker-issues)\": \"[مشكلات Docker الشائعة](#common-docker-issues)\",\n \"ar|[Fine Tuned TTS models](#fine-tuned-tts-models)\": \"[نماذج TTS المضبوطة بدقة](#fine-tuned-tts-models)\",\n \"ar|[Collection of Fine-Tuned TTS Models](#fine-tuned-tts-collection)\": \"[مجموعة نماذج TTS المضبوطة بدقة](#fine-tuned-tts-collection)\",\n \"ar|[Train XTTSv2](#fine-tune-your-own-xttsv2-model)\": \"[تدريب XTTSv2](#fine-tune-your-own-xttsv2-model)\",\n \"ar|[Supported eBook Formats](#supported-ebook-formats)\": \"[صيغ الكتب الإلكترونية المدعومة](#supported-ebook-formats)\",\n \"ar|[Output Formats](#output-and-process-formats)\": \"[صيغ الإخراج](#output-and-process-formats)\",\n \"ar|[Revert to older Version](#reverting-to-older-versions)\": \"[العودة إلى إصدار أقدم](#reverting-to-older-versions)\",\n \"ar|[Common Issues](#common-issues)\": \"[المشكلات الشائعة](#common-issues)\",\n \"ar|[Special Thanks](#special-thanks)\": \"[شكر خاص](#special-thanks)\",\n \"ar|[Table of Contents](#table-of-contents)\": \"[جدول المحتويات](#table-of-contents)\",\n \"ar|Features\": \"الميزات\",\n \"ar|🔧 **TTS Engines supported**: `XTTSv2`, `Bark`, `Fairseq`, `VITS`, `Tacotron2`, `Tortoise`, `GlowTTS`, `YourTTS`\": \"🔧 **محركات TTS المدعومة**: `XTTSv2`, `Bark`, `Fairseq`, `VITS`, `Tacotron2`, `Tortoise`, `GlowTTS`, `YourTTS`\",\n \"ar|📚 **Convert multiple file formats**: `.epub`, `.mobi`, `.azw3`, `.fb2`, `.lrf`, `.rb`, `.snb`, `.tcr`, `.pdf`, `.txt`, `.rtf`, `.doc`, `.docx`, `.html`, `.odt`, `.azw`, `.tiff`, `.tif`, `.png`, `.jpg`, `.jpeg`, `.bmp`, `.zip`\": \"📚 **تحويل صيغ ملفات متعددة**: `.epub`, `.mobi`, `.azw3`, `.fb2`, `.lrf`, `.rb`, `.snb`, `.tcr`, `.pdf`, `.txt`, `.rtf`, `.doc`, `.docx`, `.html`, `.odt`, `.azw`, `.tiff`, `.tif`, `.png`, `.jpg`, `.jpeg`, `.bmp`, `.zip`\",\n \"ar|💻 **TextArea** to convert directly a short text in audio\": \"💻 **منطقة نص** لتحويل نص قصير مباشرةً إلى صوت\",\n \"ar|🔍 **OCR scanning** for files with text pages as images\": \"🔍 **مسح OCR** للملفات التي تحتوي على صفحات نصية كصور\",\n \"ar|🔊 **High-quality text-to-speech** from near realtime to near real voice\": \"🔊 **تحويل نص إلى كلام عالي الجودة**، من شبه الوقت الفعلي إلى صوت شبه حقيقي\",\n \"ar|🗣️ **Optional voice cloning** using your own voice file\": \"🗣️ **استنساخ صوت اختياري** باستخدام ملف صوتك الخاص\",\n \"ar|🌐 **Supports 1158 languages** ([supported languages list](https://dl.fbaipublicfiles.com/mms/tts/all-tts-languages.html))\": \"🌐 **يدعم 1158 لغة** ([supported languages list](https://dl.fbaipublicfiles.com/mms/tts/all-tts-languages.html))\",\n \"ar|💻 **Low-resource friendly** — runs on **2 GB RAM / 1 GB VRAM (minimum)**\": \"💻 **صديق للموارد المنخفضة** — يعمل على **2 GB RAM / 1 GB VRAM (الحد الأدنى)**\",\n \"ar|🎵 **Audiobook output formats**: mono or stereo `aac`, `flac`, `mp3`, `m4b`, `m4a`, `mp4`, `mov`, `ogg`, `wav`, `webm`\": \"🎵 **صيغ إخراج الكتاب الصوتي**: mono or stereo `aac`, `flac`, `mp3`, `m4b`, `m4a`, `mp4`, `mov`, `ogg`, `wav`, `webm`\",\n \"ar|🧠 **SML tags supported** — fine-grained control of breaks, pauses, voice switching and more ([see below](#sml-tags-available))\": \"🧠 **وسوم SML مدعومة** — تحكم دقيق في الفواصل والتوقفات وتبديل الصوت والمزيد ([see below](#sml-tags-available))\",\n \"ar|🧩 **Optional custom model** using your own trained model (XTTSv2, VITS, FAIRSEQ, PIPER, others on request)\": \"🧩 **نموذج مخصص اختياري** باستخدام نموذجك المدرّب الخاص (XTTSv2, VITS, FAIRSEQ, PIPER, others on request)\",\n \"ar|🎛️ **Fine-tuned preset models** trained by the E2A Team
\": \"🎛️ **نماذج مُعدّة مسبقًا ومضبوطة بدقة** دُرّبت بواسطة فريق E2A
\",\n \"ar|(Contact us if you need additional fine-tuned models, or if you’d like to share yours to the official preset list)\": \"(تواصل معنا إذا كنت بحاجة إلى نماذج إضافية مضبوطة بدقة، أو إذا كنت ترغب في مشاركة نماذجك في قائمة الإعدادات المسبقة الرسمية)\",\n \"ar|Hardware Requirements\": \"متطلبات العتاد\",\n \"ar|2GB RAM min, 8GB recommended.\": \"2 جيجابايت RAM كحد أدنى، 8 جيجابايت موصى به.\",\n \"ar|1GB VRAM min, 4GB recommended.\": \"1 جيجابايت VRAM كحد أدنى، 4 جيجابايت موصى به.\",\n \"ar|Virtualization enabled if running on windows (Docker only).\": \"المحاكاة الافتراضية مُفعّلة عند التشغيل على windows (Docker فقط).\",\n \"ar|CPU, XPU (intel, AMD, ARM)*.\": \"CPU، XPU (intel، AMD، ARM)*.\",\n \"ar|CUDA, ROCm, JETSON\": \"CUDA، ROCm، JETSON\",\n \"ar|MPS (Apple Silicon CPU)\": \"MPS (معالج Apple Silicon)\",\n \"ar|* Modern TTS engines are very slow on CPU, so use lower quality TTS like YourTTS, Tacotron2 etc..\": \"* محركات TTS الحديثة بطيئة جدًا على CPU، لذا استخدم TTS أقل جودة مثل YourTTS وTacotron2 وما إلى ذلك.\",\n \"ar|Supported Languages\": \"اللغات المدعومة\",\n \"ar|[**+1130 languages and dialects here**](https://dl.fbaipublicfiles.com/mms/tts/all-tts-languages.html)\": \"[**+1130 لغة ولهجة هنا**](https://dl.fbaipublicfiles.com/mms/tts/all-tts-languages.html)\",\n \"ar|Supported eBook Formats\": \"صيغ الكتب الإلكترونية المدعومة\",\n \"ar|**Best results**: `.epub` or `.mobi` for automatic chapter detection\": \"**أفضل النتائج**: `.epub` أو `.mobi` للكشف التلقائي عن الفصول\",\n \"ar|Output and process Formats\": \"صيغ الإخراج والمعالجة\",\n \"ar|Process format can be changed in lib/conf.py\": \"يمكن تغيير صيغة المعالجة في lib/conf.py\",\n \"ar|SML tags available\": \"وسوم SML المتاحة\",\n \"ar|`[break]` — silence (random range **0.3–0.6 sec.**)\": \"`[break]` — صمت (نطاق عشوائي **0.3–0.6 sec.**)\",\n \"ar|`[pause]` — silence (random range **1.0–1.6 sec.**)\": \"`[pause]` — صمت (نطاق عشوائي **1.0–1.6 sec.**)\",\n \"ar|`[pause:N]` — fixed pause (**N sec.**)\": \"`[pause:N]` — توقف ثابت (**N sec.**)\",\n \"ar|`[voice:/path/to/voice/file]...[/voice]` — switch voice from default or selected voice from GUI/CLI\": \"`[voice:/path/to/voice/file]...[/voice]` — تبديل الصوت من الصوت الافتراضي أو المحدد من GUI/CLI\",\n \"ar|**Check our other repo dedicated to add SML automatically in your ebook -> [E2A-SML](./tools/E2A-SML)**\": \"**اطّلع على مستودعنا الآخر المخصص لإضافة SML تلقائيًا في كتابك الإلكتروني -> [E2A-SML](./tools/E2A-SML)**\",\n \"ar|**Before to post an install or bug issue search carefully to the opened and closed issues TAB
\": \"**قبل نشر مشكلة تثبيت أو خطأ، ابحث بعناية في علامة تبويب المشكلات المفتوحة والمغلقة
\",\n \"ar|to be sure your issue does not exist already.**\": \"للتأكد من أن مشكلتك غير موجودة بالفعل.**\",\n \"ar|**EPUB format lacks any standard structure like what is a chapter, paragraph, preface etc.
\": \"**تفتقر صيغة EPUB إلى أي بنية معيارية لما هو الفصل أو الفقرة أو المقدمة وما إلى ذلك.
\",\n \"ar|So you should first remove manually any text you don't want to be converted in audio.**\": \"لذا يجب عليك أولًا أن تزيل يدويًا أي نص لا ترغب في تحويله إلى صوت.**\",\n \"ar|**Install / Run ebook2audiobook**:\": \"**ثبّت / شغّل ebook2audiobook**:\",\n \"ar|**Mac Launcher** \": \"**مشغّل Mac** \",\n \"ar|Double click `Mac Ebook2Audiobook Launcher.command`\": \"انقر نقرًا مزدوجًا على `Mac Ebook2Audiobook Launcher.command`\",\n \"ar|Note for Windows users: scoop is installed to install missing programs without administrator privileges.\": \"ملاحظة لمستخدمي Windows: يتم تثبيت scoop لتثبيت البرامج المفقودة دون امتيازات المسؤول.\",\n \"ar|**Open the Web App**: Click the URL provided in the terminal to access the web app and convert eBooks. `http://localhost:7860/`\": \"**افتح تطبيق الويب**: انقر على الرابط المتوفر في الطرفية للوصول إلى تطبيق الويب وتحويل الكتب الإلكترونية. `http://localhost:7860/`\",\n \"ar|**For Public Link**:\": \"**للحصول على رابط عام**:\",\n \"ar|**If the script is stopped and run again, you need to refresh your gradio GUI interface
\": \"**إذا تم إيقاف السكربت وتشغيله مرة أخرى، فستحتاج إلى تحديث واجهة Gradio الرسومية
\",\n \"ar|to let the web page reconnect to the new connection socket.**\": \"للسماح لصفحة الويب بإعادة الاتصال بمقبس الاتصال الجديد.**\",\n \"ar|**[--ebook]**: Path to your eBook file\": \"**[--ebook]**: مسار ملف كتابك الإلكتروني\",\n \"ar|**[--voice]**: Voice cloning file path (optional)\": \"**[--voice]**: مسار ملف استنساخ الصوت (اختياري)\",\n \"ar|**[--language]**: Language code in ISO-639-3 (i.e.: ita for italian, eng for english, deu for german...).
\": \"**[--language]**: رمز اللغة بصيغة ISO-639-3 (أي: ita للإيطالية، eng للإنجليزية، deu للألمانية...).
\",\n \"ar|Default language is eng and --language is optional for default language set in ./lib/lang.py.
\": \"اللغة الافتراضية هي eng و--language اختياري للغة الافتراضية المحددة في ./lib/lang.py.
\",\n \"ar|The ISO-639-1 2 letters codes are also supported.\": \"كما يتم دعم رموز ISO-639-1 المكونة من حرفين.\",\n \"ar|****: Path to `model_name.zip` file,\": \"****: مسار ملف `model_name.zip`،\",\n \"ar|which must contain (according to the tts engine) all the mandatory files
\": \"الذي يجب أن يحتوي (وفقًا لمحرك tts) على جميع الملفات الإلزامية
\",\n \"ar|(see ./lib/models.py).\": \"(انظر ./lib/models.py).\",\n \"ar|NOTE: in gradio/gui mode, to cancel a running conversion, just click on the [X] from the ebook upload component.\": \"ملاحظة: في وضع gradio/gui، لإلغاء تحويل قيد التشغيل، ما عليك سوى النقر على [X] في مكوّن رفع الكتاب الإلكتروني.\",\n \"ar|TIP: if it needs some more pause, add '[pause:3]' for 3 sec. etc.\": \"نصيحة: إذا كانت هناك حاجة إلى توقف أطول قليلًا، أضف '[pause:3]' لمدة 3 ثوانٍ وما إلى ذلك.\",\n \"ar|Common Docker Issues\": \"مشكلات Docker الشائعة\",\n \"ar|My NVIDIA GPU isn't being detected?? -> [GPU ISSUES Wiki Page](https://github.com/DrewThomasson/ebook2audiobook/wiki/GPU-ISSUES)\": \"لا يتم اكتشاف بطاقة NVIDIA الرسومية لدي؟؟ -> [صفحة Wiki لمشكلات GPU](https://github.com/DrewThomasson/ebook2audiobook/wiki/GPU-ISSUES)\",\n \"ar|Fine Tuned TTS models\": \"نماذج TTS المضبوطة بدقة (fine-tuned)\",\n \"ar|Fine Tune your own XTTSv2 model\": \"اضبط نموذج XTTSv2 الخاص بك بدقة\",\n \"ar|De-noise training data\": \"إزالة الضوضاء من بيانات التدريب\",\n \"ar|Fine Tuned TTS Collection\": \"مجموعة نماذج TTS المضبوطة بدقة\",\n \"ar|For an XTTSv2 custom model a ref audio clip of the voice reference is mandatory:\": \"بالنسبة إلى نموذج XTTSv2 المخصص، يكون مقطع صوتي مرجعي للصوت إلزاميًا:\",\n \"ar|Your own Ebook2Audiobook customization\": \"تخصيصك الخاص لـ Ebook2Audiobook\",\n \"ar|You are free to modify libs/conf.py to add or remove the settings you wish. If you plan to do it just make\": \"أنت حر في تعديل libs/conf.py لإضافة أو إزالة الإعدادات التي تريدها. إذا كنت تخطط للقيام بذلك، فما عليك سوى إنشاء\",\n \"ar|a copy of the original conf.py so on each ebook2audiobook update you will backup your modified conf.py and put\": \"نسخة من conf.py الأصلي بحيث يمكنك في كل تحديث لـ ebook2audiobook عمل نسخة احتياطية من conf.py المعدّل وإعادة\",\n \"ar|back the original one. You must plan the same process for models.py. If you wish to make your own custom model\": \"وضع الأصلي. يجب عليك التخطيط للعملية نفسها بالنسبة لـ models.py. إذا كنت ترغب في جعل نموذجك المخصص\",\n \"ar|as an official ebook2audiobook fine tuned model so please contact us and we'll add it to the presets list.\": \"نموذج ebook2audiobook رسميًا مضبوطًا بدقة، فيرجى الاتصال بنا وسنضيفه إلى قائمة الإعدادات المسبقة.\",\n \"ar|Common Issues:\": \"المشكلات الشائعة:\",\n \"ar|My NVIDIA/ROCm/XPU/MPS GPU isn't being detected?? -> [GPU ISSUES Wiki Page](https://github.com/DrewThomasson/ebook2audiobook/wiki/GPU-ISSUES)\": \"لا يتم اكتشاف بطاقة NVIDIA/ROCm/XPU/MPS الرسومية لدي؟؟ -> [GPU ISSUES Wiki Page](https://github.com/DrewThomasson/ebook2audiobook/wiki/GPU-ISSUES)\",\n \"ar|CPU is slow (better on server smp CPU) while GPU can have almost real time conversion.\": \"المعالج بطيء (أفضل على معالج خادم SMP) بينما يمكن لبطاقة GPU إجراء تحويل شبه فوري.\",\n \"ar|(It doesn't have zero-shot voice cloning though, and is Siri quality voices, but it is much faster on cpu).\": \"(لكنه لا يحتوي على استنساخ صوت zero-shot، وهي أصوات بجودة Siri، لكنه أسرع بكثير على cpu).\",\n \"ar|\\\"I'm having dependency issues\\\" - Just use the docker, its fully self contained and has a headless mode,\": \"\\\"أواجه مشكلات في التبعيات\\\" - ما عليك سوى استخدام docker، فهو مكتفٍ ذاتيًا تمامًا وله وضع بدون واجهة،\",\n \"ar|add `--help` parameter at the end of the docker run command for more information.\": \"أضف المعامل `--help` في نهاية أمر docker run للمزيد من المعلومات.\",\n \"ar|\\\"I'm getting a truncated audio issue!\\\" - PLEASE MAKE AN ISSUE OF THIS,\": \"\\\"أواجه مشكلة في انقطاع الصوت!\\\" - يرجى إنشاء ISSUE حول هذا،\",\n \"ar|we don't speak every language and need advise from users to fine tune the sentence splitting logic.😊\": \"نحن لا نتحدث كل لغة ونحتاج إلى نصيحة من المستخدمين لضبط منطق تقسيم الجمل بدقة.😊\",\n \"ar|***** ROADMAP *****\": \"***** خارطة الطريق *****\",\n \"ar|All Features open to public Contributions ⭐\": \"جميع الميزات مفتوحة للمساهمات العامة ⭐\",\n \"ar|Any help from people speaking any of the supported languages to help us improve the models ⭐\": \"أي مساعدة من أشخاص يتحدثون أيًا من اللغات المدعومة لمساعدتنا في تحسين النماذج ⭐\",\n \"ar|Preview Blocks/Chapters before to start the conversion\": \"معاينة الكتل/الفصول قبل بدء التحويل\",\n \"ar|Edit by sentence converted for surgical text change\": \"التحرير لكل جملة محوّلة لتغيير نصي دقيق\",\n \"ar|SML tags integration for voice, pause, break, and more changes \": \"دمج وسوم SML للصوت والتوقف والفاصل والمزيد من التغييرات \",\n \"ar|-h -help parameter info in different languages\": \"معلومات معاملات -h -help بلغات مختلفة\",\n \"ar|OCR scanning for PDF / JPG / BMP / PNG / TIFF\": \"مسح OCR لملفات PDF / JPG / BMP / PNG / TIFF\",\n \"ar|Notebooks Folder [Talked about here](https://github.com/DrewThomasson/ebook2audiobookXTTS/issues/5#issuecomment-2408773254)\": \"مجلد Notebooks [Talked about here](https://github.com/DrewThomasson/ebook2audiobookXTTS/issues/5#issuecomment-2408773254)\",\n \"ar|Make Chinese text splitting not split words and improve pause timing [Talked about here](https://github.com/DrewThomasson/ebook2audiobookXTTS/issues/18#issuecomment-2401154894)\": \"جعل تقسيم النص الصيني لا يقسم الكلمات وتحسين توقيت الفواصل [Talked about here](https://github.com/DrewThomasson/ebook2audiobookXTTS/issues/18#issuecomment-2401154894)\",\n \"ar|Kaggle Notebook\": \"دفتر Kaggle\",\n \"ar|Google Colab Notebook\": \"دفتر Google Colab\",\n \"ar|[Make a IOS app](https://github.com/DrewThomasson/ebook2audiobook/pull/35#issuecomment-2496495212)\": \"[إنشاء تطبيق iOS](https://github.com/DrewThomasson/ebook2audiobook/pull/35#issuecomment-2496495212)\",\n \"ar|[Make an android app](https://github.com/DrewThomasson/ebook2audiobook/pull/35#issuecomment-2496495212)\": \"[إنشاء تطبيق android](https://github.com/DrewThomasson/ebook2audiobook/pull/35#issuecomment-2496495212)\",\n \"ar|Audiobookshelf integration\": \"دمج Audiobookshelf\",\n \"ar|Extra Options\": \"خيارات إضافية\",\n \"ar|Ebook Translation option\": \"خيار ترجمة الكتاب الإلكتروني\",\n \"ar|Output format choices\": \"خيارات صيغة الإخراج\",\n \"ar|Batch ebook folder\": \"مجلد كتب إلكترونية دفعي\",\n \"ar|Multiprocessing conversion\": \"تحويل متعدد المعالجة\",\n \"ar|Batch ebook folder conversion\": \"تحويل مجلد كتب إلكترونية دفعي\",\n \"ar|GPU Device detection\": \"اكتشاف جهاز GPU\",\n \"ar|Denoise any reference audio for upload voice cloning,\": \"إزالة الضوضاء من أي صوت مرجعي لرفع استنساخ الصوت،\",\n \"ar|Custom model upload (XTTSv2 only for now. more on request)\": \"رفع نموذج مخصص (XTTSv2 فقط حاليًا. المزيد عند الطلب)\",\n \"ar|Add European Portuguese language model for xttsv2, fairseq, vits, piper at least (help welcome)\": \"إضافة نموذج لغة البرتغالية الأوروبية على الأقل لـ xttsv2 وfairseq وvits وpiper (المساعدة مرحب بها)\",\n \"ar|Add Sindhi language model for xttsv2, fairseq, vits, piper at least (help welcome)\": \"إضافة نموذج لغة السندية على الأقل لـ xttsv2 وfairseq وvits وpiper (المساعدة مرحب بها)\",\n \"ar|Readme Translation\": \"ترجمة Readme\",\n \"ar|🐍 OS Compatibility\": \"🐍 توافق نظام التشغيل\",\n \"ar|Extra Overkill for training models and such (All supported Coqui-tts models and piper-tts in one easy command) \": \"مبالغة إضافية لتدريب النماذج وما شابه (جميع نماذج Coqui-tts المدعومة وpiper-tts في أمر واحد سهل) \",\n \"ar|For info about this @DrewThomasson, he is currently working on the development of this, [work-in-progress-repo here](https://github.com/DrewThomasson/Universal_TTS_Finetune)\": \"للمعلومات حول هذا @DrewThomasson، يعمل حاليًا على تطويره، [المستودع قيد العمل هنا](https://github.com/DrewThomasson/Universal_TTS_Finetune)\",\n \"ar|Make a easy to use training gui for all coqui-tts models in the ljspeech format training recipes [here from coqui tts](https://github.com/coqui-ai/TTS/tree/dev/recipes/ljspeech)\": \"إنشاء واجهة تدريب سهلة الاستخدام لجميع نماذج coqui-tts في وصفات التدريب بصيغة ljspeech [هنا من coqui tts](https://github.com/coqui-ai/TTS/tree/dev/recipes/ljspeech)\",\n \"ar|Python Code normalization information for contributors\": \"معلومات تسوية كود Python للمساهمين\",\n \"ar|no blank line between code, unless between functions and classes.\": \"لا سطر فارغ بين الكود، باستثناء بين الدوال والفئات.\",\n \"ar|single quote used for all key unless for dict() and json. dict['key'] always called with single quote\": \"تُستخدم علامات الاقتباس المفردة لجميع المفاتيح باستثناء dict() وjson. يتم استدعاء dict['key'] دائمًا بعلامات اقتباس مفردة\",\n \"ar|4 spaces indentation, not tab at all\": \"مسافة بادئة من 4 مسافات، دون أي علامات جدولة على الإطلاق\",\n \"ar|strict typing for all functions and its arguments declaration and return values\": \"كتابة صارمة للأنواع لجميع الدوال وإعلان وسائطها وقيم إرجاعها\",\n \"ar|no space between the argument and its typing, no space between the function, the \\\"->\\\" and the return value\": \"لا مسافة بين الوسيط وكتابة نوعه، لا مسافة بين الدالة و\\\"->\\\" وقيمة الإرجاع\",\n \"ar|Example:\": \"مثال:\",\n \"ar|Hardware donation for beta tests wanted\": \"مطلوب تبرع بالعتاد لاختبارات بيتا\",\n \"ar|We accept any kind of hardware to test our development like:\": \"نقبل أي نوع من العتاد لاختبار تطويرنا مثل:\",\n \"ar|@DrewThomasson if you want to help out at all! 😃\": \"@DrewThomasson إذا كنت ترغب في المساعدة بأي شكل من الأشكال! 😃\",\n \"ar|Do you need to rent a GPU to boost service from us?\": \"هل تحتاج إلى استئجار GPU لتعزيز خدمتنا؟\",\n \"ar|A poll is open here https://github.com/DrewThomasson/ebook2audiobook/discussions/889\": \"استطلاع رأي مفتوح هنا https://github.com/DrewThomasson/ebook2audiobook/discussions/889\",\n \"ar|Special Thanks\": \"شكر خاص\",\n \"ar|[@shakenbake15 for better chapter saving method](https://github.com/DrewThomasson/ebook2audiobook/issues/8) \": \"[@shakenbake15 لطريقة أفضل لحفظ الفصول](https://github.com/DrewThomasson/ebook2audiobook/issues/8) \",\n \"ar|TTS engines\": \"محركات TTS\",\n \"ar|XTTSv2\": \"XTTSv2\",\n \"ar|Bark\": \"ﺡﺎﺒﻧ\",\n \"ar|Fairseq\": \"فيرسيك\",\n \"ar|VITS\": \"فيتس\",\n \"ar|Tacotron2\": \"تاكوترون 2\",\n \"ar|YourTTS\": \"YourTTS\",\n \"ar|Tortoise\": \"لون السلحفاة\",\n \"ar|GlowTTS\": \"GlowTTS\",\n \"ar|Piper\": \"الفلفل الأسود\",\n \"ar|GPT-SoVITS (https://github.com/RVC-Boss/GPT-SoVITS)\": \"GPT - SoVITS (https://github.com/RVC-Boss/GPT-SoVITS)\",\n \"ar|OpenVoice (https://github.com/myshell-ai/OpenVoice)\": \"OpenVoice (https://github.com/myshell-ai/OpenVoice)\",\n \"ar|fish-speech (https://github.com/fishaudio/fish-speech)\": \"كلام السمكة (https://github.com/fishaudio/fish-speech)\",\n \"ar|ChatTTS (https://github.com/2noise/ChatTTS)\": \"ChatTTS (https://github.com/2noise/ChatTTS)\",\n \"ar|CosyVoice (https://github.com/FunAudioLLM/CosyVoice)\": \"CosyVoice (https://github.com/FunAudioLLM/CosyVoice)\",\n \"ar|F5-TTS (https://github.com/swivid/f5-tts)\": \"F5 - TTS (https://github.com/swivid/f5-tts)\",\n \"ar|chatterbox (https://github.com/resemble-ai/chatterbox)\": \"chatterbox (https://github.com/resemble-ai/chatterbox)\",\n \"ar|Supertonic (https://github.com/supertone-inc/supertonic)\": \"Supertonic (https://github.com/supertone-inc/supertonic)\",\n \"ar|Spark-TTS (https://github.com/sparkaudio/spark-tts)\": \"Spark - TTS (https://github.com/sparkaudio/spark-tts)\",\n \"ar|index-tts (https://github.com/index-tts/index-tts)\": \"index - tts (https://github.com/index-tts/index-tts)\",\n \"ar|MeloTTS (https://github.com/myshell-ai/MeloTTS)\": \"MeloTTS (https://github.com/myshell-ai/MeloTTS)\",\n \"ar|Kokoro-TTS (https://github.com/hexgrad/kokoro)\": \"Kokoro - TTS (https://github.com/hexgrad/kokoro)\",\n \"ar|OmniVoice (https://github.com/k2-fsa/OmniVoice)\": \"OmniVoice (https://github.com/k2-fsa/OmniVoice)\",\n \"ar|Zonos (https://github.com/Zyphra/Zonos)\": \"زونوس (https://github.com/Zyphra/Zonos)\",\n \"ar|Style-TTS2 (https://github.com/yl4579/StyleTTS2)\": \"Style - TTS2 (https://github.com/yl4579/StyleTTS2)\",\n \"ar|Orpheus-TTS (https://github.com/canopyai/Orpheus-TTS)\": \"Orpheus - TTS (https://github.com/canopyai/Orpheus-TTS)\",\n \"ar|NewTTS (https://github.com/neuphonic/neutts?tab=readme-ov-file)\": \"NewTTS (https://github.com/neuphonic/neutts?tab=readme-ov-file)\",\n \"ar|VIbeVoice (https://github.com/vibevoice-community/VibeVoice)\": \"VIbeVoice (https://github.com/vibevoice-community/VibeVoice)\",\n \"ar|Qwen3-TTS (https://huggingface.co/spaces/Qwen/Qwen3-TTS)\": \"Qwen3 - TTS (https://huggingface.co/spaces/Qwen/Qwen3-TTS)\",\n \"zh-CN|CPU/GPU Converter from E-Book to audiobook with chapters and metadata
\": \"将电子书转换为带有章节和元数据的有声书的 CPU/GPU 转换器
\",\n \"zh-CN|using advanced TTS engines and much more.
\": \"使用先进的 TTS 引擎等。
\",\n \"zh-CN|Supports voice cloning and 1158 languages!\": \"支持语音克隆和 1158 种语言！\",\n \"zh-CN|**This tool is intended for use with non-DRM, legally acquired eBooks only.**
\": \"**本工具仅供与合法获取的无 DRM 电子书一起使用。**
\",\n \"zh-CN|The authors are not responsible for any misuse of this software or any resulting legal consequences.
\": \"作者对本软件的任何滥用或由此产生的任何法律后果概不负责。
\",\n \"zh-CN|Use this tool responsibly and in accordance with all applicable laws.\": \"请负责任地使用本工具，并遵守所有适用的法律。\",\n \"zh-CN|Thanks to support ebook2audiobook developers!\": \"感谢您支持 ebook2audiobook 的开发者！\",\n \"zh-CN|Run locally\": \"本地运行\",\n \"zh-CN|Run Remotely\": \"远程运行\",\n \"zh-CN|GUI Interface\": \"图形界面（GUI）\",\n \"zh-CN|Click to see images of Web GUI\": \"点击查看 Web GUI 图像\",\n \"zh-CN|Demos\": \"演示\",\n \"zh-CN|**New Default Voice Demo** \": \"**新默认语音演示** \",\n \"zh-CN|More Demos\": \"更多演示\",\n \"zh-CN|**ASMR Voice** \": \"**ASMR 语音** \",\n \"zh-CN|**Rainy Day Voice** \": \"**雨天语音** \",\n \"zh-CN|**Scarlett Voice**\": \"**斯嘉丽语音**\",\n \"zh-CN|**David Attenborough Voice** \": \"**大卫·阿滕伯勒语音** \",\n \"zh-CN|**Example**\": \"**示例**\",\n \"zh-CN|Table of Contents\": \"目录\",\n \"zh-CN|[Features](#features)\": \"[功能](#features)\",\n \"zh-CN|[GUI Interface](#gui-interface)\": \"[图形界面](#gui-interface)\",\n \"zh-CN|[Demos](#demos)\": \"[演示](#demos)\",\n \"zh-CN|[Supported Languages](#supported-languages)\": \"[支持的语言](#supported-languages)\",\n \"zh-CN|[Minimum Requirements](#hardware-requirements)\": \"[最低要求](#hardware-requirements)\",\n \"zh-CN|[Usage](#instructions)\": \"[用法](#instructions)\",\n \"zh-CN|[Run Locally](#instructions)\": \"[本地运行](#instructions)\",\n \"zh-CN|[Launching Gradio Web Interface](#instructions)\": \"[启动 Gradio Web 界面](#instructions)\",\n \"zh-CN|[Basic Headless Usage](#basic-usage)\": \"[基本 Headless 用法](#basic-usage)\",\n \"zh-CN|[Headless Custom XTTS Model Usage](#example-of-custom-model-zip-upload)\": \"[Headless 自定义 XTTS 模型用法](#example-of-custom-model-zip-upload)\",\n \"zh-CN|[Help command output](#help-command-output)\": \"[帮助命令输出](#help-command-output)\",\n \"zh-CN|[Run Remotely](#run-remotely)\": \"[远程运行](#run-remotely)\",\n \"zh-CN|[Steps to Run](#docker)\": \"[运行步骤](#docker)\",\n \"zh-CN|[Common Docker Issues](#common-docker-issues)\": \"[常见的 Docker 问题](#common-docker-issues)\",\n \"zh-CN|[Fine Tuned TTS models](#fine-tuned-tts-models)\": \"[微调 TTS 模型](#fine-tuned-tts-models)\",\n \"zh-CN|[Collection of Fine-Tuned TTS Models](#fine-tuned-tts-collection)\": \"[微调 TTS 模型集合](#fine-tuned-tts-collection)\",\n \"zh-CN|[Train XTTSv2](#fine-tune-your-own-xttsv2-model)\": \"[训练 XTTSv2](#fine-tune-your-own-xttsv2-model)\",\n \"zh-CN|[Supported eBook Formats](#supported-ebook-formats)\": \"[支持的电子书格式](#supported-ebook-formats)\",\n \"zh-CN|[Output Formats](#output-and-process-formats)\": \"[输出格式](#output-and-process-formats)\",\n \"zh-CN|[Revert to older Version](#reverting-to-older-versions)\": \"[还原到较旧版本](#reverting-to-older-versions)\",\n \"zh-CN|[Common Issues](#common-issues)\": \"[常见问题](#common-issues)\",\n \"zh-CN|[Special Thanks](#special-thanks)\": \"[特别鸣谢](#special-thanks)\",\n \"zh-CN|[Table of Contents](#table-of-contents)\": \"[目录](#table-of-contents)\",\n \"zh-CN|Features\": \"功能\",\n \"zh-CN|🔧 **TTS Engines supported**: `XTTSv2`, `Bark`, `Fairseq`, `VITS`, `Tacotron2`, `Tortoise`, `GlowTTS`, `YourTTS`\": \"🔧 **支持的 TTS 引擎**： `XTTSv2`, `Bark`, `Fairseq`, `VITS`, `Tacotron2`, `Tortoise`, `GlowTTS`, `YourTTS`\",\n \"zh-CN|📚 **Convert multiple file formats**: `.epub`, `.mobi`, `.azw3`, `.fb2`, `.lrf`, `.rb`, `.snb`, `.tcr`, `.pdf`, `.txt`, `.rtf`, `.doc`, `.docx`, `.html`, `.odt`, `.azw`, `.tiff`, `.tif`, `.png`, `.jpg`, `.jpeg`, `.bmp`, `.zip`\": \"📚 **转换多种文件格式**： `.epub`, `.mobi`, `.azw3`, `.fb2`, `.lrf`, `.rb`, `.snb`, `.tcr`, `.pdf`, `.txt`, `.rtf`, `.doc`, `.docx`, `.html`, `.odt`, `.azw`, `.tiff`, `.tif`, `.png`, `.jpg`, `.jpeg`, `.bmp`, `.zip`\",\n \"zh-CN|💻 **TextArea** to convert directly a short text in audio\": \"💻 用于直接将短文本转换为音频的**文本区域**\",\n \"zh-CN|🔍 **OCR scanning** for files with text pages as images\": \"🔍 针对文本页面为图像的文件的 **OCR 扫描**\",\n \"zh-CN|🔊 **High-quality text-to-speech** from near realtime to near real voice\": \"🔊 **高质量文本转语音**，从接近实时到接近真实的语音\",\n \"zh-CN|🗣️ **Optional voice cloning** using your own voice file\": \"🗣️ 使用您自己的语音文件进行**可选的语音克隆**\",\n \"zh-CN|🌐 **Supports 1158 languages** ([supported languages list](https://dl.fbaipublicfiles.com/mms/tts/all-tts-languages.html))\": \"🌐 **支持 1158 种语言** ([supported languages list](https://dl.fbaipublicfiles.com/mms/tts/all-tts-languages.html))\",\n \"zh-CN|💻 **Low-resource friendly** — runs on **2 GB RAM / 1 GB VRAM (minimum)**\": \"💻 **低资源友好** — 可在 **2 GB RAM / 1 GB VRAM（最低）** 上运行\",\n \"zh-CN|🎵 **Audiobook output formats**: mono or stereo `aac`, `flac`, `mp3`, `m4b`, `m4a`, `mp4`, `mov`, `ogg`, `wav`, `webm`\": \"🎵 **有声书输出格式**： mono or stereo `aac`, `flac`, `mp3`, `m4b`, `m4a`, `mp4`, `mov`, `ogg`, `wav`, `webm`\",\n \"zh-CN|🧠 **SML tags supported** — fine-grained control of breaks, pauses, voice switching and more ([see below](#sml-tags-available))\": \"🧠 **支持 SML 标签** — 对中断、停顿、语音切换等进行精细控制 ([see below](#sml-tags-available))\",\n \"zh-CN|🧩 **Optional custom model** using your own trained model (XTTSv2, VITS, FAIRSEQ, PIPER, others on request)\": \"🧩 使用您自己训练的模型的**可选自定义模型** (XTTSv2, VITS, FAIRSEQ, PIPER, others on request)\",\n \"zh-CN|🎛️ **Fine-tuned preset models** trained by the E2A Team
\": \"🎛️ 由 E2A 团队训练的**微调预设模型**
\",\n \"zh-CN|(Contact us if you need additional fine-tuned models, or if you’d like to share yours to the official preset list)\": \"（如果您需要额外的微调模型，或者如果您想在官方预设列表中分享您自己的模型，请联系我们）\",\n \"zh-CN|Hardware Requirements\": \"硬件要求\",\n \"zh-CN|2GB RAM min, 8GB recommended.\": \"RAM 最低 2GB，推荐 8GB。\",\n \"zh-CN|1GB VRAM min, 4GB recommended.\": \"VRAM 最低 1GB，推荐 4GB。\",\n \"zh-CN|Virtualization enabled if running on windows (Docker only).\": \"在 windows 上运行时启用虚拟化（仅限 Docker）。\",\n \"zh-CN|CPU, XPU (intel, AMD, ARM)*.\": \"CPU、XPU（intel、AMD、ARM）*。\",\n \"zh-CN|CUDA, ROCm, JETSON\": \"CUDA、ROCm、JETSON\",\n \"zh-CN|MPS (Apple Silicon CPU)\": \"MPS（Apple Silicon CPU）\",\n \"zh-CN|* Modern TTS engines are very slow on CPU, so use lower quality TTS like YourTTS, Tacotron2 etc..\": \"* 现代 TTS 引擎在 CPU 上非常慢，因此请使用质量较低的 TTS，如 YourTTS、Tacotron2 等。\",\n \"zh-CN|Supported Languages\": \"支持的语言\",\n \"zh-CN|[**+1130 languages and dialects here**](https://dl.fbaipublicfiles.com/mms/tts/all-tts-languages.html)\": \"[**此处有 +1130 种语言和方言**](https://dl.fbaipublicfiles.com/mms/tts/all-tts-languages.html)\",\n \"zh-CN|Supported eBook Formats\": \"支持的电子书格式\",\n \"zh-CN|**Best results**: `.epub` or `.mobi` for automatic chapter detection\": \"**最佳效果**：使用 `.epub` 或 `.mobi` 进行自动章节检测\",\n \"zh-CN|Output and process Formats\": \"输出和处理格式\",\n \"zh-CN|Process format can be changed in lib/conf.py\": \"处理格式可在 lib/conf.py 中更改\",\n \"zh-CN|SML tags available\": \"可用的 SML 标签\",\n \"zh-CN|`[break]` — silence (random range **0.3–0.6 sec.**)\": \"`[break]` — 静音（随机范围 **0.3–0.6 sec.**）\",\n \"zh-CN|`[pause]` — silence (random range **1.0–1.6 sec.**)\": \"`[pause]` — 静音（随机范围 **1.0–1.6 sec.**）\",\n \"zh-CN|`[pause:N]` — fixed pause (**N sec.**)\": \"`[pause:N]` — 固定停顿（**N sec.**）\",\n \"zh-CN|`[voice:/path/to/voice/file]...[/voice]` — switch voice from default or selected voice from GUI/CLI\": \"`[voice:/path/to/voice/file]...[/voice]` — 从默认语音或从 GUI/CLI 选择的语音切换语音\",\n \"zh-CN|**Check our other repo dedicated to add SML automatically in your ebook -> [E2A-SML](./tools/E2A-SML)**\": \"**请查看我们另一个专门用于在电子书中自动添加 SML 的仓库 -> [E2A-SML](./tools/E2A-SML)**\",\n \"zh-CN|**Before to post an install or bug issue search carefully to the opened and closed issues TAB
\": \"**在发布安装或错误问题之前，请仔细搜索打开和已关闭问题的标签页
\",\n \"zh-CN|to be sure your issue does not exist already.**\": \"以确保您的问题尚不存在。**\",\n \"zh-CN|**EPUB format lacks any standard structure like what is a chapter, paragraph, preface etc.
\": \"**EPUB 格式缺乏任何定义什么是章节、段落、前言等的标准结构。
\",\n \"zh-CN|So you should first remove manually any text you don't want to be converted in audio.**\": \"因此，您应该首先手动删除任何不想转换为音频的文本。**\",\n \"zh-CN|**Install / Run ebook2audiobook**:\": \"**安装 / 运行 ebook2audiobook**：\",\n \"zh-CN|**Mac Launcher** \": \"**Mac 启动器** \",\n \"zh-CN|Double click `Mac Ebook2Audiobook Launcher.command`\": \"双击 `Mac Ebook2Audiobook Launcher.command`\",\n \"zh-CN|Note for Windows users: scoop is installed to install missing programs without administrator privileges.\": \"Windows 用户注意：将安装 scoop 以在没有管理员权限的情况下安装缺失的程序。\",\n \"zh-CN|**Open the Web App**: Click the URL provided in the terminal to access the web app and convert eBooks. `http://localhost:7860/`\": \"**打开 Web 应用**：点击终端中提供的 URL，以访问 Web 应用并转换电子书。 `http://localhost:7860/`\",\n \"zh-CN|**For Public Link**:\": \"**获取公共链接**：\",\n \"zh-CN|**If the script is stopped and run again, you need to refresh your gradio GUI interface
\": \"**如果脚本被停止并再次运行，您需要刷新您的 Gradio GUI 界面
\",\n \"zh-CN|to let the web page reconnect to the new connection socket.**\": \"以便网页能够重新连接到新的连接套接字。**\",\n \"zh-CN|**[--ebook]**: Path to your eBook file\": \"**[--ebook]**：电子书文件的路径\",\n \"zh-CN|**[--voice]**: Voice cloning file path (optional)\": \"**[--voice]**：语音克隆文件路径（可选）\",\n \"zh-CN|**[--language]**: Language code in ISO-639-3 (i.e.: ita for italian, eng for english, deu for german...).
\": \"**[--language]**：ISO-639-3 格式的语言代码（即：意大利语为 ita，英语为 eng，德语为 deu...）。
\",\n \"zh-CN|Default language is eng and --language is optional for default language set in ./lib/lang.py.
\": \"默认语言为 eng，对于 ./lib/lang.py 中设置的默认语言，--language 是可选的。
\",\n \"zh-CN|The ISO-639-1 2 letters codes are also supported.\": \"也支持 2 个字母的 ISO-639-1 代码。\",\n \"zh-CN|****: Path to `model_name.zip` file,\": \"****：`model_name.zip` 文件的路径，\",\n \"zh-CN|which must contain (according to the tts engine) all the mandatory files
\": \"该文件必须（根据 tts 引擎）包含所有必需文件
\",\n \"zh-CN|(see ./lib/models.py).\": \"（参见 ./lib/models.py）。\",\n \"zh-CN|NOTE: in gradio/gui mode, to cancel a running conversion, just click on the [X] from the ebook upload component.\": \"注意：在 gradio/gui 模式下，要取消正在进行的转换，只需点击电子书上传组件的 [X] 即可。\",\n \"zh-CN|TIP: if it needs some more pause, add '[pause:3]' for 3 sec. etc.\": \"提示：如果需要稍长的停顿，请添加 '[pause:3]' 表示 3 秒等。\",\n \"zh-CN|Common Docker Issues\": \"常见的 Docker 问题\",\n \"zh-CN|My NVIDIA GPU isn't being detected?? -> [GPU ISSUES Wiki Page](https://github.com/DrewThomasson/ebook2audiobook/wiki/GPU-ISSUES)\": \"未检测到我的 NVIDIA GPU？？ -> [GPU 问题 Wiki 页面](https://github.com/DrewThomasson/ebook2audiobook/wiki/GPU-ISSUES)\",\n \"zh-CN|Fine Tuned TTS models\": \"微调（fine-tuned）TTS 模型\",\n \"zh-CN|Fine Tune your own XTTSv2 model\": \"微调您自己的 XTTSv2 模型\",\n \"zh-CN|De-noise training data\": \"训练数据降噪\",\n \"zh-CN|Fine Tuned TTS Collection\": \"微调 TTS 模型集合\",\n \"zh-CN|For an XTTSv2 custom model a ref audio clip of the voice reference is mandatory:\": \"对于自定义 XTTSv2 模型，必须提供语音的参考音频片段：\",\n \"zh-CN|Your own Ebook2Audiobook customization\": \"您自己的 Ebook2Audiobook 自定义\",\n \"zh-CN|You are free to modify libs/conf.py to add or remove the settings you wish. If you plan to do it just make\": \"您可以自由修改 libs/conf.py 以添加或删除您想要的设置。如果您打算这样做，只需制作\",\n \"zh-CN|a copy of the original conf.py so on each ebook2audiobook update you will backup your modified conf.py and put\": \"原始 conf.py 的副本，这样在每次更新 ebook2audiobook 时，您可以备份修改后的 conf.py 并恢复\",\n \"zh-CN|back the original one. You must plan the same process for models.py. If you wish to make your own custom model\": \"原始文件。您必须为 models.py 计划相同的流程。如果您想将自己的自定义模型\",\n \"zh-CN|as an official ebook2audiobook fine tuned model so please contact us and we'll add it to the presets list.\": \"变成官方微调的 ebook2audiobook 模型，请联系我们，我们会将其添加到预设列表中。\",\n \"zh-CN|Common Issues:\": \"常见问题：\",\n \"zh-CN|My NVIDIA/ROCm/XPU/MPS GPU isn't being detected?? -> [GPU ISSUES Wiki Page](https://github.com/DrewThomasson/ebook2audiobook/wiki/GPU-ISSUES)\": \"未检测到我的 NVIDIA/ROCm/XPU/MPS GPU？？ -> [GPU ISSUES Wiki Page](https://github.com/DrewThomasson/ebook2audiobook/wiki/GPU-ISSUES)\",\n \"zh-CN|CPU is slow (better on server smp CPU) while GPU can have almost real time conversion.\": \"CPU 很慢（在服务器 SMP CPU 上更好），而 GPU 可以实现接近实时的转换。\",\n \"zh-CN|(It doesn't have zero-shot voice cloning though, and is Siri quality voices, but it is much faster on cpu).\": \"（不过它没有 zero-shot 语音克隆，是 Siri 质量的语音，但在 cpu 上快得多）。\",\n \"zh-CN|\\\"I'm having dependency issues\\\" - Just use the docker, its fully self contained and has a headless mode,\": \"“我遇到依赖项问题” - 只需使用 docker，它完全独立并具有 headless 模式，\",\n \"zh-CN|add `--help` parameter at the end of the docker run command for more information.\": \"在 docker run 命令末尾添加 `--help` 参数以获取更多信息。\",\n \"zh-CN|\\\"I'm getting a truncated audio issue!\\\" - PLEASE MAKE AN ISSUE OF THIS,\": \"“我遇到音频被截断的问题！” - 请就此创建一个 ISSUE，\",\n \"zh-CN|we don't speak every language and need advise from users to fine tune the sentence splitting logic.😊\": \"我们不会说每种语言，需要用户的建议来微调句子拆分逻辑。😊\",\n \"zh-CN|***** ROADMAP *****\": \"***** 路线图 *****\",\n \"zh-CN|All Features open to public Contributions ⭐\": \"所有功能均向公众贡献开放 ⭐\",\n \"zh-CN|Any help from people speaking any of the supported languages to help us improve the models ⭐\": \"来自任何说支持语言的人的任何帮助，以帮助我们改进模型 ⭐\",\n \"zh-CN|Preview Blocks/Chapters before to start the conversion\": \"在开始转换之前预览块/章节\",\n \"zh-CN|Edit by sentence converted for surgical text change\": \"按转换后的句子进行编辑，以进行精准的文本更改\",\n \"zh-CN|SML tags integration for voice, pause, break, and more changes \": \"用于语音、停顿、中断及更多更改的 SML 标签集成 \",\n \"zh-CN|-h -help parameter info in different languages\": \"不同语言的 -h -help 参数信息\",\n \"zh-CN|OCR scanning for PDF / JPG / BMP / PNG / TIFF\": \"针对 PDF / JPG / BMP / PNG / TIFF 的 OCR 扫描\",\n \"zh-CN|Notebooks Folder [Talked about here](https://github.com/DrewThomasson/ebook2audiobookXTTS/issues/5#issuecomment-2408773254)\": \"Notebooks 文件夹 [Talked about here](https://github.com/DrewThomasson/ebook2audiobookXTTS/issues/5#issuecomment-2408773254)\",\n \"zh-CN|Make Chinese text splitting not split words and improve pause timing [Talked about here](https://github.com/DrewThomasson/ebook2audiobookXTTS/issues/18#issuecomment-2401154894)\": \"使中文文本拆分不拆分单词并改善停顿时间 [Talked about here](https://github.com/DrewThomasson/ebook2audiobookXTTS/issues/18#issuecomment-2401154894)\",\n \"zh-CN|[Make a IOS app](https://github.com/DrewThomasson/ebook2audiobook/pull/35#issuecomment-2496495212)\": \"[制作 iOS 应用](https://github.com/DrewThomasson/ebook2audiobook/pull/35#issuecomment-2496495212)\",\n \"zh-CN|[Make an android app](https://github.com/DrewThomasson/ebook2audiobook/pull/35#issuecomment-2496495212)\": \"[制作 android 应用](https://github.com/DrewThomasson/ebook2audiobook/pull/35#issuecomment-2496495212)\",\n \"zh-CN|Audiobookshelf integration\": \"Audiobookshelf 集成\",\n \"zh-CN|Extra Options\": \"额外选项\",\n \"zh-CN|Ebook Translation option\": \"电子书翻译选项\",\n \"zh-CN|Output format choices\": \"输出格式选择\",\n \"zh-CN|Batch ebook folder\": \"批量电子书文件夹\",\n \"zh-CN|Multiprocessing conversion\": \"多进程转换\",\n \"zh-CN|Batch ebook folder conversion\": \"批量电子书文件夹转换\",\n \"zh-CN|GPU Device detection\": \"GPU 设备检测\",\n \"zh-CN|Denoise any reference audio for upload voice cloning,\": \"为上传的语音克隆对任何参考音频进行降噪，\",\n \"zh-CN|Custom model upload (XTTSv2 only for now. more on request)\": \"自定义模型上传（目前仅 XTTSv2。更多应需求提供）\",\n \"zh-CN|Add European Portuguese language model for xttsv2, fairseq, vits, piper at least (help welcome)\": \"至少为 xttsv2、fairseq、vits、piper 添加欧洲葡萄牙语语言模型（欢迎帮助）\",\n \"zh-CN|Add Sindhi language model for xttsv2, fairseq, vits, piper at least (help welcome)\": \"至少为 xttsv2、fairseq、vits、piper 添加信德语语言模型（欢迎帮助）\",\n \"zh-CN|Readme Translation\": \"Readme 翻译\",\n \"zh-CN|🐍 OS Compatibility\": \"🐍 操作系统兼容性\",\n \"zh-CN|Extra Overkill for training models and such (All supported Coqui-tts models and piper-tts in one easy command) \": \"用于训练模型等的额外杀手锏（所有支持的 Coqui-tts 模型和 piper-tts 通过一条简单命令） \",\n \"zh-CN|For info about this @DrewThomasson, he is currently working on the development of this, [work-in-progress-repo here](https://github.com/DrewThomasson/Universal_TTS_Finetune)\": \"有关此信息 @DrewThomasson，他目前正在进行其开发，[正在进行中的仓库在此处](https://github.com/DrewThomasson/Universal_TTS_Finetune)\",\n \"zh-CN|Make a easy to use training gui for all coqui-tts models in the ljspeech format training recipes [here from coqui tts](https://github.com/coqui-ai/TTS/tree/dev/recipes/ljspeech)\": \"为 ljspeech 格式训练配方中的所有 coqui-tts 模型创建一个易于使用的训练 gui [此处来自 coqui tts](https://github.com/coqui-ai/TTS/tree/dev/recipes/ljspeech)\",\n \"zh-CN|Python Code normalization information for contributors\": \"面向贡献者的 Python 代码规范化信息\",\n \"zh-CN|no blank line between code, unless between functions and classes.\": \"代码之间没有空行，函数和类之间除外。\",\n \"zh-CN|single quote used for all key unless for dict() and json. dict['key'] always called with single quote\": \"除 dict() 和 json 外，所有键均使用单引号。dict['key'] 始终用单引号调用\",\n \"zh-CN|4 spaces indentation, not tab at all\": \"4 个空格缩进，完全不使用制表符\",\n \"zh-CN|strict typing for all functions and its arguments declaration and return values\": \"对所有函数及其参数和返回值声明进行严格类型标注\",\n \"zh-CN|no space between the argument and its typing, no space between the function, the \\\"->\\\" and the return value\": \"参数与其类型标注之间无空格，函数、“->”和返回值之间无空格\",\n \"zh-CN|Example:\": \"示例：\",\n \"zh-CN|Hardware donation for beta tests wanted\": \"征求用于测试版测试的硬件捐赠\",\n \"zh-CN|We accept any kind of hardware to test our development like:\": \"我们接受任何类型的硬件来测试我们的开发，例如：\",\n \"zh-CN|@DrewThomasson if you want to help out at all! 😃\": \"@DrewThomasson 如果您想以任何方式提供帮助！ 😃\",\n \"zh-CN|Do you need to rent a GPU to boost service from us?\": \"您需要租用 GPU 来增强我们的服务吗？\",\n \"zh-CN|A poll is open here https://github.com/DrewThomasson/ebook2audiobook/discussions/889\": \"此处已开放投票 https://github.com/DrewThomasson/ebook2audiobook/discussions/889\",\n \"zh-CN|Special Thanks\": \"特别鸣谢\",\n \"zh-CN|[@shakenbake15 for better chapter saving method](https://github.com/DrewThomasson/ebook2audiobook/issues/8) \": \"[@shakenbake15 提供了更好的章节保存方法](https://github.com/DrewThomasson/ebook2audiobook/issues/8) \",\n \"zh-CN|TTS engines\": \"TTS引擎\",\n \"zh-CN|XTTSv2\": \"XTTSv2\",\n \"zh-CN|Bark\": \"巴克\",\n \"zh-CN|Fairseq\": \"公平交易\",\n \"zh-CN|VITS\": \"VITS\",\n \"zh-CN|Tacotron2\": \"Tacotron2\",\n \"zh-CN|YourTTS\": \"YourTTS\",\n \"zh-CN|Tortoise\": \"陸龜\",\n \"zh-CN|GlowTTS\": \"GlowTTS\",\n \"zh-CN|Piper\": \"胡椒属\",\n \"zh-CN|GPT-SoVITS (https://github.com/RVC-Boss/GPT-SoVITS)\": \"GPT-SoVITS (https://github.com/RVC-Boss/GPT-SoVITS)\",\n \"zh-CN|OpenVoice (https://github.com/myshell-ai/OpenVoice)\": \"OpenVoice (https://github.com/myshell-ai/OpenVoice)\",\n \"zh-CN|fish-speech (https://github.com/fishaudio/fish-speech)\": \"fish-speech (https://github.com/fishaudio/fish-speech)\",\n \"zh-CN|ChatTTS (https://github.com/2noise/ChatTTS)\": \"ChatTTS (https://github.com/2noise/ChatTTS)\",\n \"zh-CN|CosyVoice (https://github.com/FunAudioLLM/CosyVoice)\": \"CosyVoice (https://github.com/FunAudioLLM/CosyVoice)\",\n \"zh-CN|F5-TTS (https://github.com/swivid/f5-tts)\": \"F5-TTS (https://github.com/swivid/f5-tts)\",\n \"zh-CN|chatterbox (https://github.com/resemble-ai/chatterbox)\": \"chatterbox (https://github.com/resemble-ai/chatterbox)\",\n \"zh-CN|Supertonic (https://github.com/supertone-inc/supertonic)\": \"Supertonic (https://github.com/supertone-inc/supertonic)\",\n \"zh-CN|Spark-TTS (https://github.com/sparkaudio/spark-tts)\": \"Spark-TTS (https://github.com/sparkaudio/spark-tts)\",\n \"zh-CN|index-tts (https://github.com/index-tts/index-tts)\": \"index-tts (https://github.com/index-tts/index-tts)\",\n \"zh-CN|MeloTTS (https://github.com/myshell-ai/MeloTTS)\": \"MeloTTS (https://github.com/myshell-ai/MeloTTS)\",\n \"zh-CN|Kokoro-TTS (https://github.com/hexgrad/kokoro)\": \"Kokoro-TTS (https://github.com/hexgrad/kokoro)\",\n \"zh-CN|OmniVoice (https://github.com/k2-fsa/OmniVoice)\": \"OmniVoice (https://github.com/k2-fsa/OmniVoice)\",\n \"zh-CN|Zonos (https://github.com/Zyphra/Zonos)\": \"Zonos (https://github.com/Zyphra/Zonos)\",\n \"zh-CN|Style-TTS2 (https://github.com/yl4579/StyleTTS2)\": \"样式-TTS2 (https://github.com/yl4579/StyleTTS2)\",\n \"zh-CN|Orpheus-TTS (https://github.com/canopyai/Orpheus-TTS)\": \"Orpheus-TTS (https://github.com/canopyai/Orpheus-TTS)\",\n \"zh-CN|NewTTS (https://github.com/neuphonic/neutts?tab=readme-ov-file)\": \"NewTTS (https://github.com/neuphonic/neutts?tab=readme-ov-file)\",\n \"zh-CN|VIbeVoice (https://github.com/vibevoice-community/VibeVoice)\": \"VIbeVoice (https://github.com/vibevoice-community/VibeVoice)\",\n \"zh-CN|Qwen3-TTS (https://huggingface.co/spaces/Qwen/Qwen3-TTS)\": \"Qwen3-TTS (https://huggingface.co/spaces/Qwen/Qwen3-TTS)\",\n \"es|CPU/GPU Converter from E-Book to audiobook with chapters and metadata
\": \"Conversor CPU/GPU de libro electrónico a audiolibro con capítulos y metadatos
\",\n \"es|using advanced TTS engines and much more.
\": \"usando motores TTS avanzados y mucho más.
\",\n \"es|Supports voice cloning and 1158 languages!\": \"¡Admite clonación de voz y 1158 idiomas!\",\n \"es|**This tool is intended for use with non-DRM, legally acquired eBooks only.**
\": \"**Esta herramienta está destinada a usarse únicamente con libros electrónicos sin DRM y adquiridos legalmente.**
\",\n \"es|The authors are not responsible for any misuse of this software or any resulting legal consequences.
\": \"Los autores no se hacen responsables de ningún uso indebido de este software ni de las consecuencias legales que de ello se deriven.
\",\n \"es|Use this tool responsibly and in accordance with all applicable laws.\": \"Utiliza esta herramienta de forma responsable y conforme a todas las leyes aplicables.\",\n \"es|Thanks to support ebook2audiobook developers!\": \"¡Gracias por apoyar a los desarrolladores de ebook2audiobook!\",\n \"es|Run locally\": \"Ejecución local\",\n \"es|Run Remotely\": \"Ejecución remota\",\n \"es|GUI Interface\": \"Interfaz gráfica (GUI)\",\n \"es|Click to see images of Web GUI\": \"Haz clic para ver imágenes de la GUI web\",\n \"es|**New Default Voice Demo** \": \"**Demo de la nueva voz por defecto** \",\n \"es|More Demos\": \"Más demos\",\n \"es|**ASMR Voice** \": \"**Voz ASMR** \",\n \"es|**Rainy Day Voice** \": \"**Voz de día lluvioso** \",\n \"es|**Scarlett Voice**\": \"**Voz Scarlett**\",\n \"es|**David Attenborough Voice** \": \"**Voz David Attenborough** \",\n \"es|**Example**\": \"**Ejemplo**\",\n \"es|Table of Contents\": \"Tabla de contenidos\",\n \"es|[Features](#features)\": \"[Características](#features)\",\n \"es|[GUI Interface](#gui-interface)\": \"[Interfaz gráfica](#gui-interface)\",\n \"es|[Supported Languages](#supported-languages)\": \"[Idiomas admitidos](#supported-languages)\",\n \"es|[Minimum Requirements](#hardware-requirements)\": \"[Requisitos mínimos](#hardware-requirements)\",\n \"es|[Usage](#instructions)\": \"[Uso](#instructions)\",\n \"es|[Run Locally](#instructions)\": \"[Ejecución local](#instructions)\",\n \"es|[Launching Gradio Web Interface](#instructions)\": \"[Lanzar la interfaz web de Gradio](#instructions)\",\n \"es|[Basic Headless Usage](#basic-usage)\": \"[Uso básico sin interfaz (headless)](#basic-usage)\",\n \"es|[Headless Custom XTTS Model Usage](#example-of-custom-model-zip-upload)\": \"[Uso de modelo XTTS personalizado sin interfaz](#example-of-custom-model-zip-upload)\",\n \"es|[Help command output](#help-command-output)\": \"[Salida del comando de ayuda](#help-command-output)\",\n \"es|[Run Remotely](#run-remotely)\": \"[Ejecución remota](#run-remotely)\",\n \"es|[Steps to Run](#docker)\": \"[Pasos para ejecutar](#docker)\",\n \"es|[Common Docker Issues](#common-docker-issues)\": \"[Problemas habituales con Docker](#common-docker-issues)\",\n \"es|[Fine Tuned TTS models](#fine-tuned-tts-models)\": \"[Modelos TTS ajustados](#fine-tuned-tts-models)\",\n \"es|[Collection of Fine-Tuned TTS Models](#fine-tuned-tts-collection)\": \"[Colección de modelos TTS ajustados](#fine-tuned-tts-collection)\",\n \"es|[Train XTTSv2](#fine-tune-your-own-xttsv2-model)\": \"[Entrenar XTTSv2](#fine-tune-your-own-xttsv2-model)\",\n \"es|[Supported eBook Formats](#supported-ebook-formats)\": \"[Formatos de libro electrónico admitidos](#supported-ebook-formats)\",\n \"es|[Output Formats](#output-and-process-formats)\": \"[Formatos de salida](#output-and-process-formats)\",\n \"es|[Revert to older Version](#reverting-to-older-versions)\": \"[Volver a una versión anterior](#reverting-to-older-versions)\",\n \"es|[Common Issues](#common-issues)\": \"[Problemas habituales](#common-issues)\",\n \"es|[Special Thanks](#special-thanks)\": \"[Agradecimientos especiales](#special-thanks)\",\n \"es|[Table of Contents](#table-of-contents)\": \"[Tabla de contenidos](#table-of-contents)\",\n \"es|Features\": \"Características\",\n \"es|🔧 **TTS Engines supported**: `XTTSv2`, `Bark`, `Fairseq`, `VITS`, `Tacotron2`, `Tortoise`, `GlowTTS`, `YourTTS`\": \"🔧 **Motores TTS admitidos**: `XTTSv2`, `Bark`, `Fairseq`, `VITS`, `Tacotron2`, `Tortoise`, `GlowTTS`, `YourTTS`\",\n \"es|📚 **Convert multiple file formats**: `.epub`, `.mobi`, `.azw3`, `.fb2`, `.lrf`, `.rb`, `.snb`, `.tcr`, `.pdf`, `.txt`, `.rtf`, `.doc`, `.docx`, `.html`, `.odt`, `.azw`, `.tiff`, `.tif`, `.png`, `.jpg`, `.jpeg`, `.bmp`, `.zip`\": \"📚 **Convertir múltiples formatos de archivo**: `.epub`, `.mobi`, `.azw3`, `.fb2`, `.lrf`, `.rb`, `.snb`, `.tcr`, `.pdf`, `.txt`, `.rtf`, `.doc`, `.docx`, `.html`, `.odt`, `.azw`, `.tiff`, `.tif`, `.png`, `.jpg`, `.jpeg`, `.bmp`, `.zip`\",\n \"es|💻 **TextArea** to convert directly a short text in audio\": \"💻 **Área de texto** para convertir directamente un texto corto en audio\",\n \"es|🔍 **OCR scanning** for files with text pages as images\": \"🔍 **Escaneo OCR** para archivos con páginas de texto en forma de imágenes\",\n \"es|🔊 **High-quality text-to-speech** from near realtime to near real voice\": \"🔊 **Texto a voz de alta calidad**, desde casi en tiempo real hasta una voz casi real\",\n \"es|🗣️ **Optional voice cloning** using your own voice file\": \"🗣️ **Clonación de voz opcional** usando tu propio archivo de voz\",\n \"es|🌐 **Supports 1158 languages** ([supported languages list](https://dl.fbaipublicfiles.com/mms/tts/all-tts-languages.html))\": \"🌐 **Admite 1158 idiomas** ([supported languages list](https://dl.fbaipublicfiles.com/mms/tts/all-tts-languages.html))\",\n \"es|💻 **Low-resource friendly** — runs on **2 GB RAM / 1 GB VRAM (minimum)**\": \"💻 **Apto para recursos limitados** — funciona con **2 GB de RAM / 1 GB de VRAM (mínimo)**\",\n \"es|🎵 **Audiobook output formats**: mono or stereo `aac`, `flac`, `mp3`, `m4b`, `m4a`, `mp4`, `mov`, `ogg`, `wav`, `webm`\": \"🎵 **Formatos de salida del audiolibro**: mono or stereo `aac`, `flac`, `mp3`, `m4b`, `m4a`, `mp4`, `mov`, `ogg`, `wav`, `webm`\",\n \"es|🧠 **SML tags supported** — fine-grained control of breaks, pauses, voice switching and more ([see below](#sml-tags-available))\": \"🧠 **Etiquetas SML admitidas** — control preciso de cortes, pausas, cambio de voz y mucho más ([see below](#sml-tags-available))\",\n \"es|🧩 **Optional custom model** using your own trained model (XTTSv2, VITS, FAIRSEQ, PIPER, others on request)\": \"🧩 **Modelo personalizado opcional** usando tu propio modelo entrenado (XTTSv2, VITS, FAIRSEQ, PIPER, others on request)\",\n \"es|🎛️ **Fine-tuned preset models** trained by the E2A Team
\": \"🎛️ **Modelos preajustados y ajustados** entrenados por el equipo de E2A
\",\n \"es|(Contact us if you need additional fine-tuned models, or if you’d like to share yours to the official preset list)\": \"(Contáctanos si necesitas modelos ajustados adicionales, o si quieres compartir los tuyos en la lista oficial de preajustes)\",\n \"es|Hardware Requirements\": \"Requisitos de hardware\",\n \"es|2GB RAM min, 8GB recommended.\": \"2 GB de RAM mín., 8 GB recomendados.\",\n \"es|1GB VRAM min, 4GB recommended.\": \"1 GB de VRAM mín., 4 GB recomendados.\",\n \"es|Virtualization enabled if running on windows (Docker only).\": \"Virtualización habilitada si se ejecuta en Windows (solo Docker).\",\n \"es|MPS (Apple Silicon CPU)\": \"MPS (CPU Apple Silicon)\",\n \"es|* Modern TTS engines are ve","isInternal":false,"tokens":19427,"sizeBytes":58925}],"systemPromptSnippet":"\n\n# 📚 ebook2audiobook (E2A)\n\n\nCPU/GPU Converter from E-Book to audiobook with chapters and metadata
\nusing advanced TTS engines and much more.
\nSupports voice cloning and 1158 languages!\n> [!IMPORTANT]\n**This tool is intended for use with non-DRM, legally acquired eBooks only.**
\nThe authors are not responsible for any misuse of this software or any resulting legal consequences.
\nUse this tool responsibly and in accordance with all applicable laws.\n\n[](https://discord.gg/63Tv3F65k6)\n\n### Thanks to support ebook2audiobook developers!\n[](https://ko-fi.com/athomasson2) \n\n### Run locally\n\n[](#instructions)\n\n[](https://github.com/DrewThomasson/ebook2audiobook/actions/workflows/Docker-Build.yml) [](https://github.com/DrewThomasson/ebook2audiobook/releases/latest) \n\n\n\n \n\n\n\n\n### Run Remotely\n[](https://huggingface.co/spaces/drewThomasson/ebook2audiobook)\n[](https://colab.research.google.com/github/DrewThomasson/ebook2audiobook/blob/main/Notebooks/colab_ebook2audiobook.ipynb) [](https://github.com/Rihcus/ebook2audiobookXTTS/blob/main/Notebooks/kaggle-ebook2audiobook.ipynb)\n\n#### GUI Interface\n\n\n\n Click to see images of Web GUI
\n \n \n \n \n\n## Demos\n\n**New Default Voice Demo** \n\nhttps://github.com/user-attachments/assets/750035dc-e355-46f1-9286-05c1d9e88cea \n\n\n More Demos
\n\n**ASMR Voice** \n\nhttps://github.com/user-attachments/assets/68eee9a1-6f71-4903-aacd-47397e47e422\n\n**Rainy Day Voice** \n\nhttps://github.com/user-attachments/assets/d25034d9-c77f-43a9-8f14-0d167172b080 \n\n**Scarlett Voice**\n\nhttps://github.com/user-attachments/assets/b12009ee-ec0d-45ce-a1ef-b3a52b9f8693\n\n**David Attenborough Voice** \n\nhttps://github.com/user-attachments/assets/81c4baad-117e-4db5-ac86-efc2b7fea921\n\n**Example**\n\n\n \n\n## README.md\n\n## Table of Contents\n- [ebook2audiobook](#-ebook2audiobook)\n- [Features](#features)\n- [GUI Interface](#gui-interface)\n- [Demos](#demos)\n- [Supported Languages](#supported-languages)\n- [Minimum Requirements](#hardware-requirements)\n- [Usage](#instructions)\n - [Run Locally](#instructions)\n - [Launching Gradio Web Interface](#instructions)\n - [Basic Headless Usage](#basic-usage)\n - [Headless Custom XTTS Model Usage](#example-of-custom-model-zip-upload)\n - [Help command output](#help-command-output)\n - [Run Remotely](#run-remotely)\n - [Docker](#docker)\n - [Steps to Run](#docker)\n \n- [Cloned Voices](#cloned-voices)\n- [Fine Tuned TTS models](#fine-tuned-tts-models) \n - [Collection of Fine-Tuned TTS Models](#fine-tuned-tts-collection)\n - [Train TTS Model](#fine-tune-your-own-tts-model)\n- [Supported eBook Formats](#supported-ebook-formats)\n- [Output Formats](#output-and-process-formats)\n- [Revert to older Version](#reverting-to-older-versions)\n- [Common Issues](#common-issues)\n- [Special Thanks](#special-thanks)\n- [Table of Contents](#table-of-contents)\n\n\n## Features\n- 🔧 **TTS Engines supported**: `XTTSv2`, `Bark`, `Fairseq`, `VITS`, `Tacotron2`, `Tortoise`, `GlowTTS`, `YourTTS`\n- 📚 **Convert multiple file formats**: `.epub`, `.mobi`, `.azw3`, `.fb2`, `.lrf`, `.rb`, `.snb`, `.tcr`, `.pdf`, `.txt`, `.rtf`, `.doc`, `.docx`, `.html`, `.odt`, `.azw`, `.tiff`, `.tif`, `.png`, `.jpg`, `.jpeg`, `.bmp`, `.zip`\n- 💻 **TextArea** to convert directly a short text in audio\n- 🔍 **OCR scanning** for files with text pages as images\n- 🔊 **High-quality text-to-speech** from near realtime to near real voice\n- 🗣️ **Optional voice cloning** using your own voice file\n- 🌐 **Supports 1158 languages** ([supported languages list](https://dl.fbaipublicfiles.com/mms/tts/all-tts-languages.html))\n- 💻 **Low-resource friendly** — runs on **2 GB RAM / 1 GB VRAM (minimum)**\n- 🎵 **Audiobook output formats**: mono or stereo `aac`, `flac`, `mp3`, `m4b`, `m4a`, `mp4`, `mov`, `ogg`, `wav`, `webm`\n- 🧠 **SML tags supported** — fine-grained control of breaks, pauses, voice switching and more ([see below](#sml-tags-available))\n- 🧩 **Optional custom model** using your own trained model (XTTSv2, VITS, FAIRSEQ, PIPER, others on request)\n- 🎛️ **Fine-tuned preset models** trained by the E2A Team
\n (Contact us if you need additional fine-tuned models, or if you’d like to share yours to the official preset list)\n\n\n## Hardware Requirements\n- 2GB RAM min, 8GB recommended.\n- 1GB VRAM min, 4GB recommended.\n- Virtualization enabled if running on windows (Docker only).\n- CPU, XPU (intel, AMD, ARM)*.\n- CUDA, ROCm, JETSON\n- MPS (Apple Silicon CPU)\n\n* Modern TTS engines are very slow on CPU, so use lower quality TTS like YourTTS, Tacotron2 etc..\n\n## Supported Languages\n| **Arabic (ar)** | **Chinese (zh)** | **English (en)** | **Spanish (es)** |\n|:------------------:|:------------------:|:------------------:|:------------------:|\n| **French (fr)** | **German (de)** | **Italian (it)** | **Portuguese (pt)** |\n| **Polish (pl)** | **Turkish (tr)** | **Russian (ru)** | **Dutch (nl)** |\n| **Czech (cs)** | **Japanese (ja)** | **Hindi (hi)** | **Bengali (bn)** |\n| **Hungarian (hu)** | **Korean (ko)** | **Vietnamese (vi)**| **Swedish (sv)** |\n| **Persian (fa)** | **Yoruba (yo)** | **Swahili (sw)** | **Indonesian (id)**|\n| **Slovak (sk)** | **Croatian (hr)** | **Tamil (ta)** | **Danish (da)** |\n- [**+1130 languages and dialects here**](https://dl.fbaipublicfiles.com/mms/tts/all-tts-languages.html)\n\n\n## Supported eBook Formats\n- `.epub`, `.pdf`, `.mobi`, `.txt`, `.html`, `.rtf`, `.chm`, `.lit`,\n `.pdb`, `.fb2`, `.odt`, `.cbr`, `.cbz`, `.prc`, `.lrf`, `.pml`,\n `.snb`, `.cbc`, `.rb`, `.tcr`\n- **Best results**: `.epub` or `.mobi` for automatic chapter detection\n\n## Output and process Formats\n- `.m4b`, `.m4a`, `.mp4`, `.webm`, `.mov`, `.mp3`, `.flac`, `.wav`, `.ogg`, `.aac`\n- Process format can be changed in lib/conf.py\n\n## SML tags available\n- `[break]` — silence (random range **0.3–0.6 sec.**)\n- `[pause]` — silence (random range **1.0–1.6 sec.**)\n- `[pause:N]` — fixed pause (**N sec.**)\n- `[voice:/path/to/voice/file]...[/voice]` — switch voice from default or selected voice from GUI/CLI\n\n**Check our other repo dedicated to add SML automatically in your ebook -> [E2A-SML](https://github.com/DrewThomasson/E2A-SML)**\n\n> [!IMPORTANT]\n**Before to post an install or bug issue search carefully to the opened and closed issues TAB
\nto be sure your issue does not exist already.**\n\n>[!NOTE]\n**EPUB format lacks any standard structure like what is a chapter, paragraph, preface etc.
\nSo you should first remove manually any text you don't want to be converted in audio.**\n\n\n### Instructions \n1. **Clone repo**\n\t```bash\n\tgit clone https://github.com/DrewThomasson/ebook2audiobook.git\n\tcd ebook2audiobook\n\t```\n\n2. **Install / Run ebook2audiobook**:\n\n - **Linux/MacOS** \n ```bash\n ./ebook2audiobook.command\n ```\n Note for MacOS users: homebrew is installed to install missing programs.\n \n - **Mac Launcher** \n Double click `Mac Ebook2Audiobook Launcher.command`\n\n\n - **Windows** \n ```bash\n ebook2audiobook.cmd\n ```\n or\n Double click `ebook2audiobook.cmd`\n\n Note for Windows users: scoop is installed to install missing programs without administrator privileges.\n \n1. **Open the Web App**: Click the URL provided in the terminal to access the web app and convert eBooks. `http://localhost:7860/`\n2. **For Public Link**:\n `./ebook2audiobook.command --share` (Linux/MacOS)\n `ebook2audiobook.cmd --share` (Windows)\n `python app.py --share` (all OS)\n\n> [!IMPORTANT]\n**If the script is stopped and run again, you need to refresh your gradio GUI interface
\nto let the web page reconnect to the new connection socket.**\n\n### Basic Usage\n - **Linux/MacOS**:\n ```bash\n ./ebook2audiobook.command --headless --ebook --voice --language \n ```\n - **Windows**\n ```bash\n ebook2audiobook.cmd --headless --ebook --voice --language \n ```\n \n - **[--ebook]**: Path to your eBook file\n - **[--voice]**: Voice cloning file path (optional)\n - **[--language]**: Language code in ISO-639-3 (i.e.: ita for italian, eng for english, deu for german...).
\n Default language is eng and --language is optional for default language set in ./lib/lang.py.
\n The ISO-639-1 2 letters codes are also supported.\n\n\n### Example of Custom Model Zip Upload\n (must be a .zip file containing the mandatory model files. Example for XTTSv2: config.json, model.pth, vocab.json and ref.wav)\n - **Linux/MacOS**\n ```bash\n ./ebook2audiobook.command --headless --ebook --language --custom_model \n ```\n - **Windows**\n ```bash\n ebook2audiobook.cmd --headless --ebook --language --custom_model \n ```\n Note: the ref.wav of your custom model is always the voice selected for the conversion\n \n- ****: Path to `model_name.zip` file,\n which must contain (according to the tts engine) all the mandatory files
\n (see ./lib/models.py).\n\n### For Detailed Guide with list of all Parameters to use\n - **Linux/MacOS**\n ```bash\n ./ebook2audiobook.command --help\n ```\n - **Windows**\n ```bash\n ebook2audiobook.cmd --help\n ```\n - **Or for all OS**\n ```python\n app.py --help\n ```\n\n\n```bash\nusage: app.py [-h] [--session SESSION] [--share] [--headless] [--ebook EBOOK] [--ebooks_dir EBOOKS_DIR]\n [--language LANGUAGE] [--voice VOICE] [--voice_map VOICE_MAP] [--device {CPU,CUDA,MPS,ROCM,XPU,JETSON}]\n [--tts_engine {XTTS,BARK,VITS,FAIRSEQ,TACOTRON,YOURTTS,xtts,bark,vits,fairseq,tacotron,yourtts}]\n [--custom_model CUSTOM_MODEL] [--fine_tuned FINE_TUNED] [--output_format OUTPUT_FORMAT]\n [--output_channel OUTPUT_CHANNEL] [--temperature TEMPERATURE] [--length_penalty LENGTH_PENALTY]\n [--num_beams NUM_BEAMS] [--repetition_penalty REPETITION_PENALTY] [--top_k TOP_K] [--top_p TOP_P]\n [--speed SPEED] [--enable_text_splitting] [--text_temp TEXT_TEMP] [--waveform_temp WAVEFORM_TEMP]\n [--output_dir OUTPUT_DIR] [--version]\n\nConvert eBooks to Audiobooks using a Text-to-Speech model. You can either launch the Gradio interface or run the script in headless mode for direct conversion.\n\noptions:\n -h, --help show this help message and exit\n --session SESSION Session to resume the conversion in case of interruption, crash,\n or reuse of custom models and custom cloning voices.\n\n**** The following option is for gradio/gui mode only:\n --share (Optional) Enable a public shareable Gradio link.\n\n**** The following options are for --headless mode only:\n --headless Run the script in headless mode\n --ebook EBOOK Path to the ebook file for conversion. Cannot be used when --ebooks_dir is present.\n --ebooks_dir EBOOKS_DIR\n Relative or absolute path of the directory containing the files to convert.\n Cannot be used when --ebook is present.\n --text TEXT Raw text for conversion. Cannot be used when --ebook or --ebooks_dir is present.\n --language LANGUAGE Language of the e-book. Default language is set\n in ./lib/lang.py sed as default if not present. All compatible language codes are in ./lib/lang.py\n\noptional parameters:\n --translate ISO3 (Optional) Translate ebook to a target language (ISO 639-3 code, e.g. eng, fra, deu) before TTS synthesis.\n Uses argostranslate. The target language becomes the effective TTS language for the run.\n A copy of the source ebook is made with the _ suffix so translated and non-translated\n outputs stay isolated (independent process folder, audio chunks, and final file).\n --voice VOICE (Optional) Path to the voice cloning file for TTS engine.\n Uses the default voice if not present.\n --voice_map VOICE_MAP\n (Optional, --ebooks_dir only) Path to a JSON file mapping ebook path -> voice path.\n Each entry overrides --voice for that specific ebook. Missing/null entries fall back to --voice.\n Keys may be absolute paths or basenames. Example:\n {\"book1.epub\": \"/voices/eng/adult/female/alice.wav\", \"/abs/path/book2.epub\": null}\n --device {CPU,CUDA,MPS,ROCM,XPU,JETSON}\n (Optional) Processor unit type for the conversion.\n Default is set in ./lib/conf.py if not present. Fall back to CPU if CUDA or MPS is not available.\n --tts_engine {XTTS,BARK,VITS,FAIRSEQ,TACOTRON,YOURTTS,xtts,bark,vits,fairseq,tacotron,yourtts}\n (Optional) Preferred TTS engine (available are: ['XTTS', 'BARK', 'VITS', 'FAIRSEQ', 'TACOTRON', 'YOURTTS', 'xtts', 'bark', 'vits', 'fairseq', 'tacotron', 'yourtts'].\n Default depends on the selected language. The tts engine should be compatible with the chosen language\n --custom_model CUSTOM_MODEL\n (Optional) Path to the custom model zip file cntaining mandatory model files.\n Please refer to ./lib/models.py\n --fine_tuned FINE_TUNED\n (Optional) Fine tuned model path. Default is builtin model.\n --output_format OUTPUT_FORMAT\n (Optional) Output audio format. Default is m4b set in ./lib/conf.py\n --output_channel OUTPUT_CHANNEL\n (Optional) Output audio channel. Default is mono set in ./lib/conf.py\n --temperature TEMPERATURE\n (xtts only, optional) Temperature for the model.\n Default to config.json model. Higher temperatures lead to more creative outputs.\n --length_penalty LENGTH_PENALTY\n (xtts only, optional) A length penalty applied to the autoregressive decoder.\n Default to config.json model. Not applied to custom models.\n --num_beams NUM_BEAMS\n (xtts only, optional) Controls how many alternative sequences the model explores. Must be equal or greater than length penalty.\n Default to config.json model.\n --repetition_penalty REPETITION_PENALTY\n (xtts only, optional) A penalty that prevents the autoregressive decoder from repeating itself.\n Default to config.json model.\n --top_k TOP_K (xtts only, optional) Top-k sampling.\n Lower values mean more likely outputs and increased audio generation speed.\n Default to config.json model.\n --top_p TOP_P (xtts only, optional) Top-p sampling.\n Lower values mean more likely outputs and increased audio generation speed. Default to config.json model.\n --speed SPEED (xtts only, optional) Speed factor for the speech generation.\n Default to config.json model.\n --enable_text_splitting\n (xtts only, optional) Enable TTS text splitting. This option is known to not be very efficient.\n Default to config.json model.\n --text_temp TEXT_TEMP\n (bark only, optional) Text Temperature for the model.\n Default to config.json model.\n --waveform_temp WAVEFORM_TEMP\n (bark only, optional) Waveform Temperature for the model.\n Default to config.json model.\n --output_dir OUTPUT_DIR\n (Optional) Path to the output directory. Default is set in ./lib/conf.py\n --abs_url ABS_URL Audiobookshelf server URL (e.g. http://localhost:13378).\n --abs_api_token ABS_API_TOKEN\n Audiobookshelf API token.\n --abs_library ABS_LIBRARY\n Audiobookshelf library ID.\n --enable_interlude Add MusicGen music before the first chapter, between chapters, and at the end of the audiobook. Settings are in ./lib/conf_interlude.py\n --version Show the version of the script and exit\n\nExample usage:\nWindows:\n Gradio/GUI:\n ebook2audiobook.cmd\n Headless mode:\n ebook2audiobook.cmd --headless --ebook '/path/to/file' --language eng\nLinux/Mac:\n Gradio/GUI:\n ./ebook2audiobook.command\n Headless mode:\n ./ebook2audiobook.command --headless --ebook '/path/to/file' --language eng\n\nSML tags available:\n\t[break] — silence (random range **0.3–0.6 sec.**)\n\t[pause] — silence (random range **1.0–1.6 sec.**)\n\t[pause:N] — fixed pause (**N sec.**)\n\t[voice:/path/to/voice/file]...[/voice] — switch voice from default or selected voice from GUI/CLI\n\n```\n\nNOTE: in gradio/gui mode, to cancel a running conversion, just click on the [X] from the ebook upload component.\nTIP: if it needs some more pause, add '[pause:3]' for 3 sec. etc.\n\n### Docker\n1. **Clone the Repository**:\n```bash\n git clone https://github.com/DrewThomasson/ebook2audiobook.git\n cd ebook2audiobook\n```\n2. **Build the container**\n```bash\n Windows:\n Docker:\n ebook2audiobook.cmd --script_mode build_docker\n Docker Compose:\n ebook2audiobook.cmd --script_mode build_docker --docker_mode compose\n Podman Compose:\n ebook2audiobook.cmd --script_mode build_docker --docker_mode podman\n Linux/Mac\n Docker:\n ./ebook2audiobook.command --script_mode build_docker\n Docker Compose\n ./ebook2audiobook.command --script_mode build_docker --docker_mode compose\n Podman Compose:\n ./ebook2audiobook.command --script_mode build_docker --docker_mode podman\n```\n4. **Run the Container:**\n```bash\nDocker run image:\n Gradio/GUI:\n CPU:\n docker run -v \"./ebooks:/app/ebooks\" -v \"./audiobooks:/app/audiobooks\" -v \"./models:/app/models\" -v \"./voices:/app/voices\" -v \"./tmp:/app/tmp\" --rm -it -p 7860:7860 athomasson2/ebook2audiobook:cpu\n CUDA:\n docker run -v \"./ebooks:/app/ebooks\" -v \"./audiobooks:/app/audiobooks\" -v \"./models:/app/models\" -v \"./voices:/app/voices\" -v \"./tmp:/app/tmp\" --gpus all --rm -it -p 7860:7860 athomasson2/ebook2audiobook:cu[118/122/124/126 etc..]\n ROCM:\n docker run -v \"./ebooks:/app/ebooks\" -v \"./audiobooks:/app/audiobooks\" -v \"./models:/app/models\" -v \"./voices:/app/voices\" -v \"./tmp:/app/tmp\" --device=/dev/kfd --device=/dev/dri --rm -it -p 7860:7860 athomasson2/ebook2audiobook:rocm[6.0/6.1/6.4 etc..]\n XPU:\n docker run -v \"./ebooks:/app/ebooks\" -v \"./audiobooks:/app/audiobooks\" -v \"./models:/app/models\" -v \"./voices:/app/voices\" -v \"./tmp:/app/tmp\" --device=/dev/dri --rm -it -p 7860:7860 athomasson2/ebook2audiobook:xpu\n JETSON:\n docker run -v \"./ebooks:/app/ebooks\" -v \"./audiobooks:/app/audiobooks\" -v \"./models:/app/models\" -v \"./voices:/app/voices\" -v \"./tmp:/app/tmp\" --runtime nvidia --rm -it -p 7860:7860 athomasson2/ebook2audiobook:jetson[51/60/61 etc...]\n Headless mode:\n CPU:\n docker run -v \"./ebooks:/app/ebooks\" -v \"./audiobooks:/app/audiobooks\" -v \"./models:/app/models\" -v \"./voices:/app/voices\" -v \"./tmp:/app/tmp\" -v \"/my/real/ebooks/folder/absolute/path:/app/another_ebook_folder\" --rm -it -p 7860:7860 ebook2audiobook:cpu --headless --ebook \"/app/another_ebook_folder/myfile.pdf\" [--voice /app/my/voicepath/voice.mp3 etc..]\n CUDA:\n docker run -v \"./ebooks:/app/ebooks\" -v \"./audiobooks:/app/audiobooks\" -v \"./models:/app/models\" -v \"./voices:/app/voices\" -v \"./tmp:/app/tmp\" -v \"/my/real/ebooks/folder/absolute/path:/app/another_ebook_folder\" --gpus all --rm -it -p 7860:7860 ebook2audiobook:cu[118/122/124/126 etc..] --headless --ebook \"/app/another_ebook_folder/myfile.pdf\" [--voice /app/my/voicepath/voice.mp3 etc..]\n ROCM:\n docker run -v \"./ebooks:/app/ebooks\" -v \"./audiobooks:/app/audiobooks\" -v \"./models:/app/models\" -v \"./voices:/app/voices\" -v \"./tmp:/app/tmp\" -v \"/my/real/ebooks/folder/absolute/path:/app/another_ebook_folder\" --device=/dev/kfd --device=/dev/dri --rm -it -p 7860:7860 ebook2audiobook:rocm[6.0/6.1/6.4 etc.] --headless --ebook \"/app/another_ebook_folder/myfile.pdf\" [--voice /app/my/voicepath/voice.mp3 etc..]\n XPU:\n docker run -v \"./ebooks:/app/ebooks\" -v \"./audiobooks:/app/audiobooks\" -v \"./models:/app/models\" -v \"./voices:/app/voices\" -v \"./tmp:/app/tmp\" -v \"/my/real/ebooks/folder/absolute/path:/app/another_ebook_folder\" --device=/dev/dri --rm -it -p 7860:7860 ebook2audiobook:xpu --headless --ebook \"/app/another_ebook_folder/myfile.pdf\" [--voice /app/my/voicepath/voice.mp3 etc..]\n JETSON:\n docker run -v \"./ebooks:/app/ebooks\" -v \"./audiobooks:/app/audiobooks\" -v \"./models:/app/models\" -v \"./voices:/app/voices\" -v \"./tmp:/app/tmp\" -v \"/my/real/ebooks/folder/absolute/path:/app/another_ebook_folder\" --runtime nvidia --rm -it -p 7860:7860 ebook2audiobook:jetson[51/60/61 etc.] --headless --ebook \"/app/another_ebook_folder/myfile.pdf\" [--voice /app/my/voicepath/voice.mp3 etc..]\nDocker Compose (i.e. cuda 12.8:\n Run Gradio GUI:\n DEVICE_TAG=cu128 docker compose --profile gpu up --no-log-prefix\n Run Headless mode:\n DEVICE_TAG=cu128 docker compose --profile gpu run --rm ebook2audiobook --headless --ebook \"/app/ebooks/myfile.pdf\" --voice /app/voices/eng/adult/female/some_voice.wav etc..\nPodman Compose (i.e. cuda 12.8:\n Run Gradio GUI:\n DEVICE_TAG=cu128 podman-compose -f podman-compose.yml --profile gpu up\n Run Headless mode:\n DEVICE_TAG=cu128 podman-compose -f podman-compose.yml --profile gpu run --rm ebook2audiobook-gpu --headless --ebook \"/app/ebooks/myfile.pdf\" --voice /app/voices/eng/adult/female/some_voice.wav etc..\n```\n- NOTE: MPS is not exposed in docker so CPU must be used\n\n## Cloned Voices\nYou can upload any voice audio in any of the supported audio formats, the ideal duration is around 1 to 5 mn.\nIt doesn't matter if the recording has a noisy background or music playing over it — E2A will clean up the voice for you.\n\nThe built-in cloned voices list is mainly in English. If you need voices in other languages to be officially\nadded to the list, please contact us and we'll add them after review.\n\n## Fine Tuned TTS models\n#### Fine Tune your own TTS model\n\n[Universal_TTS_Finetune](https://github.com/DrewThomasson/Universal_TTS_Finetune)\n\n#### De-noise training data\n\n[](https://huggingface.co/spaces/drewThomasson/DeepFilterNet2_no_limit) [](https://github.com/Rikorose/DeepFilterNet)\n\n\n### Fine Tuned TTS Collection\n\n[](https://huggingface.co/drewThomasson/fineTunedTTSModels/tree/main)\n\nFor an XTTSv2 custom model a ref audio clip of the voice reference is mandatory:\n\n## Your own Ebook2Audiobook customization\nYou are free to modify libs/conf.py to add or remove the settings you wish. If you plan to do it just make\na copy of the original conf.py so on each ebook2audiobook update you will backup your modified conf.py and put\nback the original one. You must plan the same process for models.py. If you wish to make your own custom model\nas an official ebook2audiobook fine tuned model so please contact us and we'll add it to the presets list.\n\n## Reverting to older Versions\nReleases can be found -> [here](https://github.com/DrewThomasson/ebook2audiobook/releases)\n```bash\ngit checkout tags/VERSION_NUM # Locally/Compose -> Example: git checkout tags/v25.7.7\n```\n\n## Common Issues:\n- My NVIDIA/ROCm/XPU/MPS GPU isn't being detected?? -> [GPU ISSUES Wiki Page](https://github.com/DrewThomasson/ebook2audiobook/wiki/GPU-ISSUES)\n- CPU is slow (better on server smp CPU) while GPU can have almost real time conversion.\n [Discussion about this](https://github.com/DrewThomasson/ebook2audiobook/discussions/19#discussioncomment-10879846)\n (It doesn't have zero-shot voice cloning though, and is Siri quality voices, but it is much faster on cpu).\n- \"I'm having dependency issues\" - Just use the docker, its fully self contained and has a headless mode,\n add `--help` parameter at the end of the docker run command for more information.\n- \"I'm getting a truncated audio issue!\" - PLEASE MAKE AN ISSUE OF THIS,\n we don't speak every language and need advise from users to fine tune the sentence splitting logic.😊\n\n## ***** ROADMAP *****\n- All Features open to public Contributions ⭐\n- Any help from people speaking any of the supported languages to help us improve the models ⭐\n- [x] Preview Blocks/Chapters before to start the conversion\n- [x] Edit by sentence converted for surgical text change\n- [x] Generate music intros, interludes, and endings; edit interludes and endings\n- [x] SML tags integration for voice, pause, break, and more changes \n- [x] -h -help parameter info in different languages\n- [x] OCR scanning for PDF / JPG / BMP / PNG / TIFF\n- [x] Notebooks Folder [Talked about here](https://github.com/DrewThomasson/ebook2audiobookXTTS/issues/5#issuecomment-2408773254)\n- [x] Make Chinese text splitting not split words and improve pause timing [Talked about here](https://github.com/DrewThomasson/ebook2audiobookXTTS/issues/18#issuecomment-2401154894)\n- [x] Dockerfile\n- [x] Docker compose\n- [x] Podman compose \n- [x] Kaggle Notebook\n- [x] Google Colab Notebook\n- [x] Audiobookshelf integration\n- [x] Ebook Translation option\n- [x] Output format choices\n- [x] Multiprocessing conversion\n- [x] Batch ebook folder conversion\n- [x] GPU Device detection\n- [x] Denoise any background reference audio for voice cloning upload\n- [x] Custom fine-tuned model upload\n- [ ] [Make a IOS app](https://github.com/DrewThomasson/ebook2audiobook/pull/35#issuecomment-2496495212)\n- [ ] [Make an android app](https://github.com/DrewThomasson/ebook2audiobook/pull/35#issuecomment-2496495212)\n\n#### User Requests\n- [ ] Add European Portuguese language model for xttsv2, fairseq, vits, piper at least (help welcome)\n- [ ] Add Sindhi language model for xttsv2, fairseq, vits, piper at least (help welcome)\n\n#### TTS engines\n- [x] XTTSv2\n- [x] Bark\n- [x] Fairseq\n- [x] VITS\n- [x] Tacotron2\n- [x] YourTTS\n- [x] Tortoise\n- [x] GlowTTS\n- [x] Piper\n- [ ] GPT-SoVITS (https://github.com/RVC-Boss/GPT-SoVITS)\n- [ ] OpenVoice (https://github.com/myshell-ai/OpenVoice)\n- [ ] fish-speech (https://github.com/fishaudio/fish-speech)\n- [ ] ChatTTS (https://github.com/2noise/ChatTTS)\n- [ ] CosyVoice (https://github.com/FunAudioLLM/CosyVoice)\n- [ ] F5-TTS (https://github.com/swivid/f5-tts)\n- [ ] chatterbox (https://github.com/resemble-ai/chatterbox)\n- [ ] Supertonic (https://github.com/supertone-inc/supertonic)\n- [ ] Spark-TTS (https://github.com/sparkaudio/spark-tts)\n- [ ] index-tts (https://github.com/index-tts/index-tts)\n- [ ] MeloTTS (https://github.com/myshell-ai/MeloTTS)\n- [ ] Kokoro-TTS (https://github.com/hexgrad/kokoro)\n- [ ] OmniVoice (https://github.com/k2-fsa/OmniVoice)\n- [ ] Zonos (https://github.com/Zyphra/Zonos)\n- [ ] Style-TTS2 (https://github.com/yl4579/StyleTTS2)\n- [ ] Orpheus-TTS (https://github.com/canopyai/Orpheus-TTS)\n- [ ] NewTTS (https://github.com/neuphonic/neutts?tab=readme-ov-file)\n- [ ] VIbeVoice (https://github.com/vibevoice-community/VibeVoice)\n- [ ] Qwen3-TTS (https://huggingface.co/spaces/Qwen/Qwen3-TTS)\n\n#### Readme Translation\n- [x] Arabic (ara)\n- [x] Chinese (zho)\n- [x] English (eng)\n- [x] Spanish (spa)\n- [x] French (fra)\n- [x] German (deu)\n- [x] Italian (ita)\n- [x] Portuguese (por)\n- [x] Polish (pol)\n- [x] Turkish (tur)\n- [x] Russian (rus)\n- [x] Dutch (nld)\n- [x] Czech (ces)\n- [x] Japanese (jpn)\n- [x] Hindi (hin)\n- [x] Bengali (ben)\n- [x] Hungarian (hun)\n- [x] Korean (kor)\n- [x] Vietnamese (vie)\n- [x] Swedish (swe)\n- [x] Persian (fas)\n- [x] Yoruba (yor)\n- [x] Swahili (swa)\n- [x] Indonesian (ind)\n- [x] Slovak (slk)\n- [x] Croatian (hrv)\n\n#### 🐍 OS Compatibility\n- [x] 🍎 Mac Intel x86\n- [x] 🪟 Windows x86\n- [x] 🐧 Linux x86\n- [x] 🖥️🍏 Apple Silicon Mac\n- [x] 🪟💪 ARM Windows\n- [x] 🐧💪 ARM Linux\n\n**********\n\n## Extra Overkill for training models and such (All supported Coqui-tts models and piper-tts in one easy command) \n- For info about this @DrewThomasson, he is currently working on the development of this, [Universal TTS Finetune](https://github.com/DrewThomasson/Universal_TTS_Finetune)\n- [x] Make a easy to use training gui for all coqui-tts models in the [ljspeech format training recipes](https://github.com/coqui-ai/TTS/tree/dev/recipes/ljspeech) Completed at [Universal TTS Finetune](https://github.com/DrewThomasson/Universal_TTS_Finetune)\n\n\n## Python Code normalization information for contributors\n- no blank line between code, unless between functions and classes.\n- single quote used for all key unless for dict() and json. dict['key'] always called with single quote\n- 4 spaces indentation, not tab at all\n- strict typing for all functions and its arguments declaration and return values\n- no space between the argument and its typing, no space between the function, the \"->\" and the return value\n\nExample:\n\n```python\nimport json\nfrom typing import Optional\n\ndef get_user(user_id:int, users:list[dict])->Optional[dict]:\n for user in users:\n if user['id'] == user_id:\n return user\n return None\n\ndef summarize(user:dict)->str:\n return f\"User {user['name']} is {'active' if user['is_active'] else 'inactive'}.\"\n\ndef to_json(user:dict)->str:\n return json.dumps({\"id\": user['id'], \"name\": user['name'], \"email\": user['email']})\n\nusers:list = [\n dict(id=1, name=\"alice\", email=\"alice@example.com\", role=\"admin\", is_active=True),\n dict(id=2, name=\"bob\", email=\"bob@example.com\", role=\"editor\", is_active=False),\n dict(id=3, name=\"carol\", email=\"carol@example.com\", role=\"viewer\", is_active=True),\n]\nconfig = {\n \"max_users\": 100,\n \"default_role\": \"viewer\",\n \"allow_signup\": True,\n}\nroles = ['admin', 'editor', 'viewer']\nfound = get_user(1, users)\nif found:\n print(summarize(found))\n print(found['email'])\n print(to_json(found))\nif config['default_role'] in roles:\n print(config['default_role'])\n```\n\n## Hardware donation for beta tests wanted\nWe accept any kind of hardware to test our development like:\n- Nvidia supporting cuda >= 11.8\n- XPU intel cards\n- ROCm AMD cards supporting ROCm >=5.7\n\n@DrewThomasson if you want to help out at all! 😃\n\n\n## Special Thanks\nTo all financial and code contributors, each contribution and suggestion helps to improve the quality of E2A.\n\n\n{\n \"ar|Thanks to support ebook2audiobook developers!\": \"شكرًا لدعمك لمطوّري ebook2audiobook!\",\n \"ar|Run locally\": \"التشغيل محليًا\",\n \"ar|Run Remotely\": \"التشغيل عن بُعد\",\n \"ar|GUI Interface\": \"الواجهة الرسومية (GUI)\",\n \"ar|Click to see images of Web GUI\": \"انقر لرؤية صور واجهة الويب الرسومية\",\n \"ar|Demos\": \"عروض توضيحية\",\n \"ar|**New Default Voice Demo** \": \"**عرض توضيحي للصوت الافتراضي الجديد** \",\n \"ar|More Demos\": \"المزيد من العروض التوضيحية\",\n \"ar|**ASMR Voice** \": \"**صوت ASMR** \",\n \"ar|**Rainy Day Voice** \": \"**صوت يوم ممطر** \",\n \"ar|**Scarlett Voice**\": \"**صوت سكارليت**\",\n \"ar|**David Attenborough Voice** \": \"**صوت ديفيد أتينبورو** \",\n \"ar|**Example**\": \"**مثال**\",\n \"ar|Table of Contents\": \"جدول المحتويات\",\n \"ar|[Features](#features)\": \"[الميزات](#features)\",\n \"ar|[GUI Interface](#gui-interface)\": \"[الواجهة الرسومية](#gui-interface)\",\n \"ar|[Demos](#demos)\": \"[عروض توضيحية](#demos)\",\n \"ar|[Supported Languages](#supported-languages)\": \"[اللغات المدعومة](#supported-languages)\",\n \"ar|[Minimum Requirements](#hardware-requirements)\": \"[الحد الأدنى من المتطلبات](#hardware-requirements)\",\n \"ar|[Usage](#instructions)\": \"[الاستخدام](#instructions)\",\n \"ar|[Run Locally](#instructions)\": \"[التشغيل محليًا](#instructions)\",\n \"ar|[Launching Gradio Web Interface](#instructions)\": \"[تشغيل واجهة الويب Gradio](#instructions)\",\n \"ar|[Basic Headless Usage](#basic-usage)\": \"[الاستخدام الأساسي بدون واجهة](#basic-usage)\",\n \"ar|[Headless Custom XTTS Model Usage](#example-of-custom-model-zip-upload)\": \"[استخدام نموذج XTTS مخصص بدون واجهة](#example-of-custom-model-zip-upload)\",\n \"ar|[Help command output](#help-command-output)\": \"[مخرجات أمر المساعدة](#help-command-output)\",\n \"ar|[Run Remotely](#run-remotely)\": \"[التشغيل عن بُعد](#run-remotely)\",\n \"ar|[Steps to Run](#docker)\": \"[خطوات التشغيل](#docker)\",\n \"ar|[Common Docker Issues](#common-docker-issues)\": \"[مشكلات Docker الشائعة](#common-docker-issues)\",\n \"ar|[Fine Tuned TTS models](#fine-tuned-tts-models)\": \"[نماذج TTS المضبوطة بدقة](#fine-tuned-tts-models)\",\n \"ar|[Collection of Fine-Tuned TTS Models](#fine-tuned-tts-collection)\": \"[مجموعة نماذج TTS المضبوطة بدقة](#fine-tuned-tts-collection)\",\n \"ar|[Train XTTSv2](#fine-tune-your-own-xttsv2-model)\": \"[تدريب XTTSv2](#fine-tune-your-own-xttsv2-model)\",\n \"ar|[Supported eBook Formats](#supported-ebook-formats)\": \"[صيغ الكتب الإلكترونية المدعومة](#supported-ebook-formats)\",\n \"ar|[Output Formats](#output-and-process-formats)\": \"[صيغ الإخراج](#output-and-process-formats)\",\n \"ar|[Revert to older Version](#reverting-to-older-versions)\": \"[العودة إلى إصدار أقدم](#reverting-to-older-versions)\",\n \"ar|[Common Issues](#common-issues)\": \"[المشكلات الشائعة](#common-issues)\",\n \"ar|[Special Thanks](#special-thanks)\": \"[شكر خاص](#special-thanks)\",\n \"ar|[Table of Contents](#table-of-contents)\": \"[جدول المحتويات](#table-of-contents)\",\n \"ar|Features\": \"الميزات\",\n \"ar|🔧 **TTS Engines supported**: `XTTSv2`, `Bark`, `Fairseq`, `VITS`, `Tacotron2`, `Tortoise`, `GlowTTS`, `YourTTS`\": \"🔧 **محركات TTS المدعومة**: `XTTSv2`, `Bark`, `Fairseq`, `VITS`, `Tacotron2`, `Tortoise`, `GlowTTS`, `YourTTS`\",\n \"ar|📚 **Convert multiple file formats**: `.epub`, `.mobi`, `.azw3`, `.fb2`, `.lrf`, `.rb`, `.snb`, `.tcr`, `.pdf`, `.txt`, `.rtf`, `.doc`, `.docx`, `.html`, `.odt`, `.azw`, `.tiff`, `.tif`, `.png`, `.jpg`, `.jpeg`, `.bmp`, `.zip`\": \"📚 **تحويل صيغ ملفات متعددة**: `.epub`, `.mobi`, `.azw3`, `.fb2`, `.lrf`, `.rb`, `.snb`, `.tcr`, `.pdf`, `.txt`, `.rtf`, `.doc`, `.docx`, `.html`, `.odt`, `.azw`, `.tiff`, `.tif`, `.png`, `.jpg`, `.jpeg`, `.bmp`, `.zip`\",\n \"ar|💻 **TextArea** to convert directly a short text in audio\": \"💻 **منطقة نص** لتحويل نص قصير مباشرةً إلى صوت\",\n \"ar|🔍 **OCR scanning** for files with text pages as images\": \"🔍 **مسح OCR** للملفات التي تحتوي على صفحات نصية كصور\",\n \"ar|🔊 **High-quality text-to-speech** from near realtime to near real voice\": \"🔊 **تحويل نص إلى كلام عالي الجودة**، من شبه الوقت الفعلي إلى صوت شبه حقيقي\",\n \"ar|🗣️ **Optional voice cloning** using your own voice file\": \"🗣️ **استنساخ صوت اختياري** باستخدام ملف صوتك الخاص\",\n \"ar|🌐 **Supports 1158 languages** ([supported languages list](https://dl.fbaipublicfiles.com/mms/tts/all-tts-languages.html))\": \"🌐 **يدعم 1158 لغة** ([supported languages list](https://dl.fbaipublicfiles.com/mms/tts/all-tts-languages.html))\",\n \"ar|💻 **Low-resource friendly** — runs on **2 GB RAM / 1 GB VRAM (minimum)**\": \"💻 **صديق للموارد المنخفضة** — يعمل على **2 GB RAM / 1 GB VRAM (الحد الأدنى)**\",\n \"ar|🎵 **Audiobook output formats**: mono or stereo `aac`, `flac`, `mp3`, `m4b`, `m4a`, `mp4`, `mov`, `ogg`, `wav`, `webm`\": \"🎵 **صيغ إخراج الكتاب الصوتي**: mono or stereo `aac`, `flac`, `mp3`, `m4b`, `m4a`, `mp4`, `mov`, `ogg`, `wav`, `webm`\",\n \"ar|🧠 **SML tags supported** — fine-grained control of breaks, pauses, voice switching and more ([see below](#sml-tags-available))\": \"🧠 **وسوم SML مدعومة** — تحكم دقيق في الفواصل والتوقفات وتبديل الصوت والمزيد ([see below](#sml-tags-available))\",\n \"ar|🧩 **Optional custom model** using your own trained model (XTTSv2, VITS, FAIRSEQ, PIPER, others on request)\": \"🧩 **نموذج مخصص اختياري** باستخدام نموذجك المدرّب الخاص (XTTSv2, VITS, FAIRSEQ, PIPER, others on request)\",\n \"ar|🎛️ **Fine-tuned preset models** trained by the E2A Team
\": \"🎛️ **نماذج مُعدّة مسبقًا ومضبوطة بدقة** دُرّبت بواسطة فريق E2A
\",\n \"ar|(Contact us if you need additional fine-tuned models, or if you’d like to share yours to the official preset list)\": \"(تواصل معنا إذا كنت بحاجة إلى نماذج إضافية مضبوطة بدقة، أو إذا كنت ترغب في مشاركة نماذجك في قائمة الإعدادات المسبقة الرسمية)\",\n \"ar|Hardware Requirements\": \"متطلبات العتاد\",\n \"ar|2GB RAM min, 8GB recommended.\": \"2 جيجابايت RAM كحد أدنى، 8 جيجابايت موصى به.\",\n \"ar|1GB VRAM min, 4GB recommended.\": \"1 جيجابايت VRAM كحد أدنى، 4 جيجابايت موصى به.\",\n \"ar|Virtualization enabled if running on windows (Docker only).\": \"المحاكاة الافتراضية مُفعّلة عند التشغيل على windows (Docker فقط).\",\n \"ar|CPU, XPU (intel, AMD, ARM)*.\": \"CPU، XPU (intel، AMD، ARM)*.\",\n \"ar|CUDA, ROCm, JETSON\": \"CUDA، ROCm، JETSON\",\n \"ar|MPS (Apple Silicon CPU)\": \"MPS (معالج Apple Silicon)\",\n \"ar|* Modern TTS engines are very slow on CPU, so use lower quality TTS like YourTTS, Tacotron2 etc..\": \"* محركات TTS الحديثة بطيئة جدًا على CPU، لذا استخدم TTS أقل جودة مثل YourTTS وTacotron2 وما إلى ذلك.\",\n \"ar|Supported Languages\": \"اللغات المدعومة\",\n \"ar|[**+1130 languages and dialects here**](https://dl.fbaipublicfiles.com/mms/tts/all-tts-languages.html)\": \"[**+1130 لغة ولهجة هنا**](https://dl.fbaipublicfiles.com/mms/tts/all-tts-languages.html)\",\n \"ar|Supported eBook Formats\": \"صيغ الكتب الإلكترونية المدعومة\",\n \"ar|**Best results**: `.epub` or `.mobi` for automatic chapter detection\": \"**أفضل النتائج**: `.epub` أو `.mobi` للكشف التلقائي عن الفصول\",\n \"ar|Output and process Formats\": \"صيغ الإخراج والمعالجة\",\n \"ar|Process format can be changed in lib/conf.py\": \"يمكن تغيير صيغة المعالجة في lib/conf.py\",\n \"ar|SML tags available\": \"وسوم SML المتاحة\",\n \"ar|`[break]` — silence (random range **0.3–0.6 sec.**)\": \"`[break]` — صمت (نطاق عشوائي **0.3–0.6 sec.**)\",\n \"ar|`[pause]` — silence (random range **1.0–1.6 sec.**)\": \"`[pause]` — صمت (نطاق عشوائي **1.0–1.6 sec.**)\",\n \"ar|`[pause:N]` — fixed pause (**N sec.**)\": \"`[pause:N]` — توقف ثابت (**N sec.**)\",\n \"ar|`[voice:/path/to/voice/file]...[/voice]` — switch voice from default or selected voice from GUI/CLI\": \"`[voice:/path/to/voice/file]...[/voice]` — تبديل الصوت من الصوت الافتراضي أو المحدد من GUI/CLI\",\n \"ar|**Check our other repo dedicated to add SML automatically in your ebook -> [E2A-SML](./tools/E2A-SML)**\": \"**اطّلع على مستودعنا الآخر المخصص لإضافة SML تلقائيًا في كتابك الإلكتروني -> [E2A-SML](./tools/E2A-SML)**\",\n \"ar|**Before to post an install or bug issue search carefully to the opened and closed issues TAB
\": \"**قبل نشر مشكلة تثبيت أو خطأ، ابحث بعناية في علامة تبويب المشكلات المفتوحة والمغلقة
\",\n \"ar|to be sure your issue does not exist already.**\": \"للتأكد من أن مشكلتك غير موجودة بالفعل.**\",\n \"ar|**EPUB format lacks any standard structure like what is a chapter, paragraph, preface etc.
\": \"**تفتقر صيغة EPUB إلى أي بنية معيارية لما هو الفصل أو الفقرة أو المقدمة وما إلى ذلك.
\",\n \"ar|So you should first remove manually any text you don't want to be converted in audio.**\": \"لذا يجب عليك أولًا أن تزيل يدويًا أي نص لا ترغب في تحويله إلى صوت.**\",\n \"ar|**Install / Run ebook2audiobook**:\": \"**ثبّت / شغّل ebook2audiobook**:\",\n \"ar|**Mac Launcher** \": \"**مشغّل Mac** \",\n \"ar|Double click `Mac Ebook2Audiobook Launcher.command`\": \"انقر نقرًا مزدوجًا على `Mac Ebook2Audiobook Launcher.command`\",\n \"ar|Note for Windows users: scoop is installed to install missing programs without administrator privileges.\": \"ملاحظة لمستخدمي Windows: يتم تثبيت scoop لتثبيت البرامج المفقودة دون امتيازات المسؤول.\",\n \"ar|**Open the Web App**: Click the URL provided in the terminal to access the web app and convert eBooks. `http://localhost:7860/`\": \"**افتح تطبيق الويب**: انقر على الرابط المتوفر في الطرفية للوصول إلى تطبيق الويب وتحويل الكتب الإلكترونية. `http://localhost:7860/`\",\n \"ar|**For Public Link**:\": \"**للحصول على رابط عام**:\",\n \"ar|**If the script is stopped and run again, you need to refresh your gradio GUI interface
\": \"**إذا تم إيقاف السكربت وتشغيله مرة أخرى، فستحتاج إلى تحديث واجهة Gradio الرسومية
\",\n \"ar|to let the web page reconnect to the new connection socket.**\": \"للسماح لصفحة الويب بإعادة الاتصال بمقبس الاتصال الجديد.**\",\n \"ar|**[--ebook]**: Path to your eBook file\": \"**[--ebook]**: مسار ملف كتابك الإلكتروني\",\n \"ar|**[--voice]**: Voice cloning file path (optional)\": \"**[--voice]**: مسار ملف استنساخ الصوت (اختياري)\",\n \"ar|**[--language]**: Language code in ISO-639-3 (i.e.: ita for italian, eng for english, deu for german...).
\": \"**[--language]**: رمز اللغة بصيغة ISO-639-3 (أي: ita للإيطالية، eng للإنجليزية، deu للألمانية...).
\",\n \"ar|Default language is eng and --language is optional for default language set in ./lib/lang.py.
\": \"اللغة الافتراضية هي eng و--language اختياري للغة الافتراضية المحددة في ./lib/lang.py.
\",\n \"ar|The ISO-639-1 2 letters codes are also supported.\": \"كما يتم دعم رموز ISO-639-1 المكونة من حرفين.\",\n \"ar|****: Path to `model_name.zip` file,\": \"****: مسار ملف `model_name.zip`،\",\n \"ar|which must contain (according to the tts engine) all the mandatory files
\": \"الذي يجب أن يحتوي (وفقًا لمحرك tts) على جميع الملفات الإلزامية
\",\n \"ar|(see ./lib/models.py).\": \"(انظر ./lib/models.py).\",\n \"ar|NOTE: in gradio/gui mode, to cancel a running conversion, just click on the [X] from the ebook upload component.\": \"ملاحظة: في وضع gradio/gui، لإلغاء تحويل قيد التشغيل، ما عليك سوى النقر على [X] في مكوّن رفع الكتاب الإلكتروني.\",\n \"ar|TIP: if it needs some more pause, add '[pause:3]' for 3 sec. etc.\": \"نصيحة: إذا كانت هناك حاجة إلى توقف أطول قليلًا، أضف '[pause:3]' لمدة 3 ثوانٍ وما إلى ذلك.\",\n \"ar|Common Docker Issues\": \"مشكلات Docker الشائعة\",\n \"ar|My NVIDIA GPU isn't being detected?? -> [GPU ISSUES Wiki Page](https://github.com/DrewThomasson/ebook2audiobook/wiki/GPU-ISSUES)\": \"لا يتم اكتشاف بطاقة NVIDIA الرسومية لدي؟؟ -> [صفحة Wiki لمشكلات GPU](https://github.com/DrewThomasson/ebook2audiobook/wiki/GPU-ISSUES)\",\n \"ar|Fine Tuned TTS models\": \"نماذج TTS المضبوطة بدقة (fine-tuned)\",\n \"ar|Fine Tune your own XTTSv2 model\": \"اضبط نموذج XTTSv2 الخاص بك بدقة\",\n \"ar|De-noise training data\": \"إزالة الضوضاء من بيانات التدريب\",\n \"ar|Fine Tuned TTS Collection\": \"مجموعة نماذج TTS المضبوطة بدقة\",\n \"ar|For an XTTSv2 custom model a ref audio clip of the voice reference is mandatory:\": \"بالنسبة إلى نموذج XTTSv2 المخصص، يكون مقطع صوتي مرجعي للصوت إلزاميًا:\",\n \"ar|Your own Ebook2Audiobook customization\": \"تخصيصك الخاص لـ Ebook2Audiobook\",\n \"ar|You are free to modify libs/conf.py to add or remove the settings you wish. If you plan to do it just make\": \"أنت حر في تعديل libs/conf.py لإضافة أو إزالة الإعدادات التي تريدها. إذا كنت تخطط للقيام بذلك، فما عليك سوى إنشاء\",\n \"ar|a copy of the original conf.py so on each ebook2audiobook update you will backup your modified conf.py and put\": \"نسخة من conf.py الأصلي بحيث يمكنك في كل تحديث لـ ebook2audiobook عمل نسخة احتياطية من conf.py المعدّل وإعادة\",\n \"ar|back the original one. You must plan the same process for models.py. If you wish to make your own custom model\": \"وضع الأصلي. يجب عليك التخطيط للعملية نفسها بالنسبة لـ models.py. إذا كنت ترغب في جعل نموذجك المخصص\",\n \"ar|as an official ebook2audiobook fine tuned model so please contact us and we'll add it to the presets list.\": \"نموذج ebook2audiobook رسميًا مضبوطًا بدقة، فيرجى الاتصال بنا وسنضيفه إلى قائمة الإعدادات المسبقة.\",\n \"ar|Common Issues:\": \"المشكلات الشائعة:\",\n \"ar|My NVIDIA/ROCm/XPU/MPS GPU isn't being detected?? -> [GPU ISSUES Wiki Page](https://github.com/DrewThomasson/ebook2audiobook/wiki/GPU-ISSUES)\": \"لا يتم اكتشاف بطاقة NVIDIA/ROCm/XPU/MPS الرسومية لدي؟؟ -> [GPU ISSUES Wiki Page](https://github.com/DrewThomasson/ebook2audiobook/wiki/GPU-ISSUES)\",\n \"ar|CPU is slow (better on server smp CPU) while GPU can have almost real time conversion.\": \"المعالج بطيء (أفضل على معالج خادم SMP) بينما يمكن لبطاقة GPU إجراء تحويل شبه فوري.\",\n \"ar|(It doesn't have zero-shot voice cloning though, and is Siri quality voices, but it is much faster on cpu).\": \"(لكنه لا يحتوي على استنساخ صوت zero-shot، وهي أصوات بجودة Siri، لكنه أسرع بكثير على cpu).\",\n \"ar|\\\"I'm having dependency issues\\\" - Just use the docker, its fully self contained and has a headless mode,\": \"\\\"أواجه مشكلات في التبعيات\\\" - ما عليك سوى استخدام docker، فهو مكتفٍ ذاتيًا تمامًا وله وضع بدون واجهة،\",\n \"ar|add `--help` parameter at the end of the docker run command for more information.\": \"أضف المعامل `--help` في نهاية أمر docker run للمزيد من المعلومات.\",\n \"ar|\\\"I'm getting a truncated audio issue!\\\" - PLEASE MAKE AN ISSUE OF THIS,\": \"\\\"أواجه مشكلة في انقطاع الصوت!\\\" - يرجى إنشاء ISSUE حول هذا،\",\n \"ar|we don't speak every language and need advise from users to fine tune the sentence splitting logic.😊\": \"نحن لا نتحدث كل لغة ونحتاج إلى نصيحة من المستخدمين لضبط منطق تقسيم الجمل بدقة.😊\",\n \"ar|***** ROADMAP *****\": \"***** خارطة الطريق *****\",\n \"ar|All Features open to public Contributions ⭐\": \"جميع الميزات مفتوحة للمساهمات العامة ⭐\",\n \"ar|Any help from people speaking any of the supported languages to help us improve the models ⭐\": \"أي مساعدة من أشخاص يتحدثون أيًا من اللغات المدعومة لمساعدتنا في تحسين النماذج ⭐\",\n \"ar|Preview Blocks/Chapters before to start the conversion\": \"معاينة الكتل/الفصول قبل بدء التحويل\",\n \"ar|Edit by sentence converted for surgical text change\": \"التحرير لكل جملة محوّلة لتغيير نصي دقيق\",\n \"ar|SML tags integration for voice, pause, break, and more changes \": \"دمج وسوم SML للصوت والتوقف والفاصل والمزيد من التغييرات \",\n \"ar|-h -help parameter info in different languages\": \"معلومات معاملات -h -help بلغات مختلفة\",\n \"ar|OCR scanning for PDF / JPG / BMP / PNG / TIFF\": \"مسح OCR لملفات PDF / JPG / BMP / PNG / TIFF\",\n \"ar|Notebooks Folder [Talked about here](https://github.com/DrewThomasson/ebook2audiobookXTTS/issues/5#issuecomment-2408773254)\": \"مجلد Notebooks [Talked about here](https://github.com/DrewThomasson/ebook2audiobookXTTS/issues/5#issuecomment-2408773254)\",\n \"ar|Make Chinese text splitting not split words and improve pause timing [Talked about here](https://github.com/DrewThomasson/ebook2audiobookXTTS/issues/18#issuecomment-2401154894)\": \"جعل تقسيم النص الصيني لا يقسم الكلمات وتحسين توقيت الفواصل [Talked about here](https://github.com/DrewThomasson/ebook2audiobookXTTS/issues/18#issuecomment-2401154894)\",\n \"ar|Kaggle Notebook\": \"دفتر Kaggle\",\n \"ar|Google Colab Notebook\": \"دفتر Google Colab\",\n \"ar|[Make a IOS app](https://github.com/DrewThomasson/ebook2audiobook/pull/35#issuecomment-2496495212)\": \"[إنشاء تطبيق iOS](https://github.com/DrewThomasson/ebook2audiobook/pull/35#issuecomment-2496495212)\",\n \"ar|[Make an android app](https://github.com/DrewThomasson/ebook2audiobook/pull/35#issuecomment-2496495212)\": \"[إنشاء تطبيق android](https://github.com/DrewThomasson/ebook2audiobook/pull/35#issuecomment-2496495212)\",\n \"ar|Audiobookshelf integration\": \"دمج Audiobookshelf\",\n \"ar|Extra Options\": \"خيارات إضافية\",\n \"ar|Ebook Translation option\": \"خيار ترجمة الكتاب الإلكتروني\",\n \"ar|Output format choices\": \"خيارات صيغة الإخراج\",\n \"ar|Batch ebook folder\": \"مجلد كتب إلكترونية دفعي\",\n \"ar|Multiprocessing conversion\": \"تحويل متعدد المعالجة\",\n \"ar|Batch ebook folder conversion\": \"تحويل مجلد كتب إلكترونية دفعي\",\n \"ar|GPU Device detection\": \"اكتشاف جهاز GPU\",\n \"ar|Denoise any reference audio for upload voice cloning,\": \"إزالة الضوضاء من أي صوت مرجعي لرفع استنساخ الصوت،\",\n \"ar|Custom model upload (XTTSv2 only for now. more on request)\": \"رفع نموذج مخصص (XTTSv2 فقط حاليًا. المزيد عند الطلب)\",\n \"ar|Add European Portuguese language model for xttsv2, fairseq, vits, piper at least (help welcome)\": \"إضافة نموذج لغة البرتغالية الأوروبية على الأقل لـ xttsv2 وfairseq وvits وpiper (المساعدة مرحب بها)\",\n \"ar|Add Sindhi language model for xttsv2, fairseq, vits, piper at least (help welcome)\": \"إضافة نموذج لغة السندية على الأقل لـ xttsv2 وfairseq وvits وpiper (المساعدة مرحب بها)\",\n \"ar|Readme Translation\": \"ترجمة Readme\",\n \"ar|🐍 OS Compatibility\": \"🐍 توافق نظام التشغيل\",\n \"ar|Extra Overkill for training models and such (All supported Coqui-tts models and piper-tts in one easy command) \": \"مبالغة إضافية لتدريب النماذج وما شابه (جميع نماذج Coqui-tts المدعومة وpiper-tts في أمر واحد سهل) \",\n \"ar|For info about this @DrewThomasson, he is currently working on the development of this, [work-in-progress-repo here](https://github.com/DrewThomasson/Universal_TTS_Finetune)\": \"للمعلومات حول هذا @DrewThomasson، يعمل حاليًا على تطويره، [المستودع قيد العمل هنا](https://github.com/DrewThomasson/Universal_TTS_Finetune)\",\n \"ar|Make a easy to use training gui for all coqui-tts models in the ljspeech format training recipes [here from coqui tts](https://github.com/coqui-ai/TTS/tree/dev/recipes/ljspeech)\": \"إنشاء واجهة تدريب سهلة الاستخدام لجميع نماذج coqui-tts في وصفات التدريب بصيغة ljspeech [هنا من coqui tts](https://github.com/coqui-ai/TTS/tree/dev/recipes/ljspeech)\",\n \"ar|Python Code normalization information for contributors\": \"معلومات تسوية كود Python للمساهمين\",\n \"ar|no blank line between code, unless between functions and classes.\": \"لا سطر فارغ بين الكود، باستثناء بين الدوال والفئات.\",\n \"ar|single quote used for all key unless for dict() and json. dict['key'] always called with single quote\": \"تُستخدم علامات الاقتباس المفردة لجميع المفاتيح باستثناء dict() وjson. يتم استدعاء dict['key'] دائمًا بعلامات اقتباس مفردة\",\n \"ar|4 spaces indentation, not tab at all\": \"مسافة بادئة من 4 مسافات، دون أي علامات جدولة على الإطلاق\",\n \"ar|strict typing for all functions and its arguments declaration and return values\": \"كتابة صارمة للأنواع لجميع الدوال وإعلان وسائطها وقيم إرجاعها\",\n \"ar|no space between the argument and its typing, no space between the function, the \\\"->\\\" and the return value\": \"لا مسافة بين الوسيط وكتابة نوعه، لا مسافة بين الدالة و\\\"->\\\" وقيمة الإرجاع\",\n \"ar|Example:\": \"مثال:\",\n \"ar|Hardware donation for beta tests wanted\": \"مطلوب تبرع بالعتاد لاختبارات بيتا\",\n \"ar|We accept any kind of hardware to test our development like:\": \"نقبل أي نوع من العتاد لاختبار تطويرنا مثل:\",\n \"ar|@DrewThomasson if you want to help out at all! 😃\": \"@DrewThomasson إذا كنت ترغب في المساعدة بأي شكل من الأشكال! 😃\",\n \"ar|Do you need to rent a GPU to boost service from us?\": \"هل تحتاج إلى استئجار GPU لتعزيز خدمتنا؟\",\n \"ar|A poll is open here https://github.com/DrewThomasson/ebook2audiobook/discussions/889\": \"استطلاع رأي مفتوح هنا https://github.com/DrewThomasson/ebook2audiobook/discussions/889\",\n \"ar|Special Thanks\": \"شكر خاص\",\n \"ar|[@shakenbake15 for better chapter saving method](https://github.com/DrewThomasson/ebook2audiobook/issues/8) \": \"[@shakenbake15 لطريقة أفضل لحفظ الفصول](https://github.com/DrewThomasson/ebook2audiobook/issues/8) \",\n \"ar|TTS engines\": \"محركات TTS\",\n \"ar|XTTSv2\": \"XTTSv2\",\n \"ar|Bark\": \"ﺡﺎﺒﻧ\",\n \"ar|Fairseq\": \"فيرسيك\",\n \"ar|VITS\": \"فيتس\",\n \"ar|Tacotron2\": \"تاكوترون 2\",\n \"ar|YourTTS\": \"YourTTS\",\n \"ar|Tortoise\": \"لون السلحفاة\",\n \"ar|GlowTTS\": \"GlowTTS\",\n \"ar|Piper\": \"الفلفل الأسود\",\n \"ar|GPT-SoVITS (https://github.com/RVC-Boss/GPT-SoVITS)\": \"GPT - SoVITS (https://github.com/RVC-Boss/GPT-SoVITS)\",\n \"ar|OpenVoice (https://github.com/myshell-ai/OpenVoice)\": \"OpenVoice (https://github.com/myshell-ai/OpenVoice)\",\n \"ar|fish-speech (https://github.com/fishaudio/fish-speech)\": \"كلام السمكة (https://github.com/fishaudio/fish-speech)\",\n \"ar|ChatTTS (https://github.com/2noise/ChatTTS)\": \"ChatTTS (https://github.com/2noise/ChatTTS)\",\n \"ar|CosyVoice (https://github.com/FunAudioLLM/CosyVoice)\": \"CosyVoice (https://github.com/FunAudioLLM/CosyVoice)\",\n \"ar|F5-TTS (https://github.com/swivid/f5-tts)\": \"F5 - TTS (https://github.com/swivid/f5-tts)\",\n \"ar|chatterbox (https://github.com/resemble-ai/chatterbox)\": \"chatterbox (https://github.com/resemble-ai/chatterbox)\",\n \"ar|Supertonic (https://github.com/supertone-inc/supertonic)\": \"Supertonic (https://github.com/supertone-inc/supertonic)\",\n \"ar|Spark-TTS (https://github.com/sparkaudio/spark-tts)\": \"Spark - TTS (https://github.com/sparkaudio/spark-tts)\",\n \"ar|index-tts (https://github.com/index-tts/index-tts)\": \"index - tts (https://github.com/index-tts/index-tts)\",\n \"ar|MeloTTS (https://github.com/myshell-ai/MeloTTS)\": \"MeloTTS (https://github.com/myshell-ai/MeloTTS)\",\n \"ar|Kokoro-TTS (https://github.com/hexgrad/kokoro)\": \"Kokoro - TTS (https://github.com/hexgrad/kokoro)\",\n \"ar|OmniVoice (https://github.com/k2-fsa/OmniVoice)\": \"OmniVoice (https://github.com/k2-fsa/OmniVoice)\",\n \"ar|Zonos (https://github.com/Zyphra/Zonos)\": \"زونوس (https://github.com/Zyphra/Zonos)\",\n \"ar|Style-TTS2 (https://github.com/yl4579/StyleTTS2)\": \"Style - TTS2 (https://github.com/yl4579/StyleTTS2)\",\n \"ar|Orpheus-TTS (https://github.com/canopyai/Orpheus-TTS)\": \"Orpheus - TTS (https://github.com/canopyai/Orpheus-TTS)\",\n \"ar|NewTTS (https://github.com/neuphonic/neutts?tab=readme-ov-file)\": \"NewTTS (https://github.com/neuphonic/neutts?tab=readme-ov-file)\",\n \"ar|VIbeVoice (https://github.com/vibevoice-community/VibeVoice)\": \"VIbeVoice (https://github.com/vibevoice-community/VibeVoice)\",\n \"ar|Qwen3-TTS (https://huggingface.co/spaces/Qwen/Qwen3-TTS)\": \"Qwen3 - TTS (https://huggingface.co/spaces/Qwen/Qwen3-TTS)\",\n \"zh-CN|CPU/GPU Converter from E-Book to audiobook with chapters and metadata
\": \"将电子书转换为带有章节和元数据的有声书的 CPU/GPU 转换器
\",\n \"zh-CN|using advanced TTS engines and much more.
\": \"使用先进的 TTS 引擎等。
\",\n \"zh-CN|Supports voice cloning and 1158 languages!\": \"支持语音克隆和 1158 种语言！\",\n \"zh-CN|**This tool is intended for use with non-DRM, legally acquired eBooks only.**
\": \"**本工具仅供与合法获取的无 DRM 电子书一起使用。**
\",\n \"zh-CN|The authors are not responsible for any misuse of this software or any resulting legal consequences.
\": \"作者对本软件的任何滥用或由此产生的任何法律后果概不负责。
\",\n \"zh-CN|Use this tool responsibly and in accordance with all applicable laws.\": \"请负责任地使用本工具，并遵守所有适用的法律。\",\n \"zh-CN|Thanks to support ebook2audiobook developers!\": \"感谢您支持 ebook2audiobook 的开发者！\",\n \"zh-CN|Run locally\": \"本地运行\",\n \"zh-CN|Run Remotely\": \"远程运行\",\n \"zh-CN|GUI Interface\": \"图形界面（GUI）\",\n \"zh-CN|Click to see images of Web GUI\": \"点击查看 Web GUI 图像\",\n \"zh-CN|Demos\": \"演示\",\n \"zh-CN|**New Default Voice Demo** \": \"**新默认语音演示** \",\n \"zh-CN|More Demos\": \"更多演示\",\n \"zh-CN|**ASMR Voice** \": \"**ASMR 语音** \",\n \"zh-CN|**Rainy Day Voice** \": \"**雨天语音** \",\n \"zh-CN|**Scarlett Voice**\": \"**斯嘉丽语音**\",\n \"zh-CN|**David Attenborough Voice** \": \"**大卫·阿滕伯勒语音** \",\n \"zh-CN|**Example**\": \"**示例**\",\n \"zh-CN|Table of Contents\": \"目录\",\n \"zh-CN|[Features](#features)\": \"[功能](#features)\",\n \"zh-CN|[GUI Interface](#gui-interface)\": \"[图形界面](#gui-interface)\",\n \"zh-CN|[Demos](#demos)\": \"[演示](#demos)\",\n \"zh-CN|[Supported Languages](#supported-languages)\": \"[支持的语言](#supported-languages)\",\n \"zh-CN|[Minimum Requirements](#hardware-requirements)\": \"[最低要求](#hardware-requirements)\",\n \"zh-CN|[Usage](#instructions)\": \"[用法](#instructions)\",\n \"zh-CN|[Run Locally](#instructions)\": \"[本地运行](#instructions)\",\n \"zh-CN|[Launching Gradio Web Interface](#instructions)\": \"[启动 Gradio Web 界面](#instructions)\",\n \"zh-CN|[Basic Headless Usage](#basic-usage)\": \"[基本 Headless 用法](#basic-usage)\",\n \"zh-CN|[Headless Custom XTTS Model Usage](#example-of-custom-model-zip-upload)\": \"[Headless 自定义 XTTS 模型用法](#example-of-custom-model-zip-upload)\",\n \"zh-CN|[Help command output](#help-command-output)\": \"[帮助命令输出](#help-command-output)\",\n \"zh-CN|[Run Remotely](#run-remotely)\": \"[远程运行](#run-remotely)\",\n \"zh-CN|[Steps to Run](#docker)\": \"[运行步骤](#docker)\",\n \"zh-CN|[Common Docker Issues](#common-docker-issues)\": \"[常见的 Docker 问题](#common-docker-issues)\",\n \"zh-CN|[Fine Tuned TTS models](#fine-tuned-tts-models)\": \"[微调 TTS 模型](#fine-tuned-tts-models)\",\n \"zh-CN|[Collection of Fine-Tuned TTS Models](#fine-tuned-tts-collection)\": \"[微调 TTS 模型集合](#fine-tuned-tts-collection)\",\n \"zh-CN|[Train XTTSv2](#fine-tune-your-own-xttsv2-model)\": \"[训练 XTTSv2](#fine-tune-your-own-xttsv2-model)\",\n \"zh-CN|[Supported eBook Formats](#supported-ebook-formats)\": \"[支持的电子书格式](#supported-ebook-formats)\",\n \"zh-CN|[Output Formats](#output-and-process-formats)\": \"[输出格式](#output-and-process-formats)\",\n \"zh-CN|[Revert to older Version](#reverting-to-older-versions)\": \"[还原到较旧版本](#reverting-to-older-versions)\",\n \"zh-CN|[Common Issues](#common-issues)\": \"[常见问题](#common-issues)\",\n \"zh-CN|[Special Thanks](#special-thanks)\": \"[特别鸣谢](#special-thanks)\",\n \"zh-CN|[Table of Contents](#table-of-contents)\": \"[目录](#table-of-contents)\",\n \"zh-CN|Features\": \"功能\",\n \"zh-CN|🔧 **TTS Engines supported**: `XTTSv2`, `Bark`, `Fairseq`, `VITS`, `Tacotron2`, `Tortoise`, `GlowTTS`, `YourTTS`\": \"🔧 **支持的 TTS 引擎**： `XTTSv2`, `Bark`, `Fairseq`, `VITS`, `Tacotron2`, `Tortoise`, `GlowTTS`, `YourTTS`\",\n \"zh-CN|📚 **Convert multiple file formats**: `.epub`, `.mobi`, `.azw3`, `.fb2`, `.lrf`, `.rb`, `.snb`, `.tcr`, `.pdf`, `.txt`, `.rtf`, `.doc`, `.docx`, `.html`, `.odt`, `.azw`, `.tiff`, `.tif`, `.png`, `.jpg`, `.jpeg`, `.bmp`, `.zip`\": \"📚 **转换多种文件格式**： `.epub`, `.mobi`, `.azw3`, `.fb2`, `.lrf`, `.rb`, `.snb`, `.tcr`, `.pdf`, `.txt`, `.rtf`, `.doc`, `.docx`, `.html`, `.odt`, `.azw`, `.tiff`, `.tif`, `.png`, `.jpg`, `.jpeg`, `.bmp`, `.zip`\",\n \"zh-CN|💻 **TextArea** to convert directly a short text in audio\": \"💻 用于直接将短文本转换为音频的**文本区域**\",\n \"zh-CN|🔍 **OCR scanning** for files with text pages as images\": \"🔍 针对文本页面为图像的文件的 **OCR 扫描**\",\n \"zh-CN|🔊 **High-quality text-to-speech** from near realtime to near real voice\": \"🔊 **高质量文本转语音**，从接近实时到接近真实的语音\",\n \"zh-CN|🗣️ **Optional voice cloning** using your own voice file\": \"🗣️ 使用您自己的语音文件进行**可选的语音克隆**\",\n \"zh-CN|🌐 **Supports 1158 languages** ([supported languages list](https://dl.fbaipublicfiles.com/mms/tts/all-tts-languages.html))\": \"🌐 **支持 1158 种语言** ([supported languages list](https://dl.fbaipublicfiles.com/mms/tts/all-tts-languages.html))\",\n \"zh-CN|💻 **Low-resource friendly** — runs on **2 GB RAM / 1 GB VRAM (minimum)**\": \"💻 **低资源友好** — 可在 **2 GB RAM / 1 GB VRAM（最低）** 上运行\",\n \"zh-CN|🎵 **Audiobook output formats**: mono or stereo `aac`, `flac`, `mp3`, `m4b`, `m4a`, `mp4`, `mov`, `ogg`, `wav`, `webm`\": \"🎵 **有声书输出格式**： mono or stereo `aac`, `flac`, `mp3`, `m4b`, `m4a`, `mp4`, `mov`, `ogg`, `wav`, `webm`\",\n \"zh-CN|🧠 **SML tags supported** — fine-grained control of breaks, pauses, voice switching and more ([see below](#sml-tags-available))\": \"🧠 **支持 SML 标签** — 对中断、停顿、语音切换等进行精细控制 ([see below](#sml-tags-available))\",\n \"zh-CN|🧩 **Optional custom model** using your own trained model (XTTSv2, VITS, FAIRSEQ, PIPER, others on request)\": \"🧩 使用您自己训练的模型的**可选自定义模型** (XTTSv2, VITS, FAIRSEQ, PIPER, others on request)\",\n \"zh-CN|🎛️ **Fine-tuned preset models** trained by the E2A Team
\": \"🎛️ 由 E2A 团队训练的**微调预设模型**
\",\n \"zh-CN|(Contact us if you need additional fine-tuned models, or if you’d like to share yours to the official preset list)\": \"（如果您需要额外的微调模型，或者如果您想在官方预设列表中分享您自己的模型，请联系我们）\",\n \"zh-CN|Hardware Requirements\": \"硬件要求\",\n \"zh-CN|2GB RAM min, 8GB recommended.\": \"RAM 最低 2GB，推荐 8GB。\",\n \"zh-CN|1GB VRAM min, 4GB recommended.\": \"VRAM 最低 1GB，推荐 4GB。\",\n \"zh-CN|Virtualization enabled if running on windows (Docker only).\": \"在 windows 上运行时启用虚拟化（仅限 Docker）。\",\n \"zh-CN|CPU, XPU (intel, AMD, ARM)*.\": \"CPU、XPU（intel、AMD、ARM）*。\",\n \"zh-CN|CUDA, ROCm, JETSON\": \"CUDA、ROCm、JETSON\",\n \"zh-CN|MPS (Apple Silicon CPU)\": \"MPS（Apple Silicon CPU）\",\n \"zh-CN|* Modern TTS engines are very slow on CPU, so use lower quality TTS like YourTTS, Tacotron2 etc..\": \"* 现代 TTS 引擎在 CPU 上非常慢，因此请使用质量较低的 TTS，如 YourTTS、Tacotron2 等。\",\n \"zh-CN|Supported Languages\": \"支持的语言\",\n \"zh-CN|[**+1130 languages and dialects here**](https://dl.fbaipublicfiles.com/mms/tts/all-tts-languages.html)\": \"[**此处有 +1130 种语言和方言**](https://dl.fbaipublicfiles.com/mms/tts/all-tts-languages.html)\",\n \"zh-CN|Supported eBook Formats\": \"支持的电子书格式\",\n \"zh-CN|**Best results**: `.epub` or `.mobi` for automatic chapter detection\": \"**最佳效果**：使用 `.epub` 或 `.mobi` 进行自动章节检测\",\n \"zh-CN|Output and process Formats\": \"输出和处理格式\",\n \"zh-CN|Process format can be changed in lib/conf.py\": \"处理格式可在 lib/conf.py 中更改\",\n \"zh-CN|SML tags available\": \"可用的 SML 标签\",\n \"zh-CN|`[break]` — silence (random range **0.3–0.6 sec.**)\": \"`[break]` — 静音（随机范围 **0.3–0.6 sec.**）\",\n \"zh-CN|`[pause]` — silence (random range **1.0–1.6 sec.**)\": \"`[pause]` — 静音（随机范围 **1.0–1.6 sec.**）\",\n \"zh-CN|`[pause:N]` — fixed pause (**N sec.**)\": \"`[pause:N]` — 固定停顿（**N sec.**）\",\n \"zh-CN|`[voice:/path/to/voice/file]...[/voice]` — switch voice from default or selected voice from GUI/CLI\": \"`[voice:/path/to/voice/file]...[/voice]` — 从默认语音或从 GUI/CLI 选择的语音切换语音\",\n \"zh-CN|**Check our other repo dedicated to add SML automatically in your ebook -> [E2A-SML](./tools/E2A-SML)**\": \"**请查看我们另一个专门用于在电子书中自动添加 SML 的仓库 -> [E2A-SML](./tools/E2A-SML)**\",\n \"zh-CN|**Before to post an install or bug issue search carefully to the opened and closed issues TAB
\": \"**在发布安装或错误问题之前，请仔细搜索打开和已关闭问题的标签页
\",\n \"zh-CN|to be sure your issue does not exist already.**\": \"以确保您的问题尚不存在。**\",\n \"zh-CN|**EPUB format lacks any standard structure like what is a chapter, paragraph, preface etc.
\": \"**EPUB 格式缺乏任何定义什么是章节、段落、前言等的标准结构。
\",\n \"zh-CN|So you should first remove manually any text you don't want to be converted in audio.**\": \"因此，您应该首先手动删除任何不想转换为音频的文本。**\",\n \"zh-CN|**Install / Run ebook2audiobook**:\": \"**安装 / 运行 ebook2audiobook**：\",\n \"zh-CN|**Mac Launcher** \": \"**Mac 启动器** \",\n \"zh-CN|Double click `Mac Ebook2Audiobook Launcher.command`\": \"双击 `Mac Ebook2Audiobook Launcher.command`\",\n \"zh-CN|Note for Windows users: scoop is installed to install missing programs without administrator privileges.\": \"Windows 用户注意：将安装 scoop 以在没有管理员权限的情况下安装缺失的程序。\",\n \"zh-CN|**Open the Web App**: Click the URL provided in the terminal to access the web app and convert eBooks. `http://localhost:7860/`\": \"**打开 Web 应用**：点击终端中提供的 URL，以访问 Web 应用并转换电子书。 `http://localhost:7860/`\",\n \"zh-CN|**For Public Link**:\": \"**获取公共链接**：\",\n \"zh-CN|**If the script is stopped and run again, you need to refresh your gradio GUI interface
\": \"**如果脚本被停止并再次运行，您需要刷新您的 Gradio GUI 界面
\",\n \"zh-CN|to let the web page reconnect to the new connection socket.**\": \"以便网页能够重新连接到新的连接套接字。**\",\n \"zh-CN|**[--ebook]**: Path to your eBook file\": \"**[--ebook]**：电子书文件的路径\",\n \"zh-CN|**[--voice]**: Voice cloning file path (optional)\": \"**[--voice]**：语音克隆文件路径（可选）\",\n \"zh-CN|**[--language]**: Language code in ISO-639-3 (i.e.: ita for italian, eng for english, deu for german...).
\": \"**[--language]**：ISO-639-3 格式的语言代码（即：意大利语为 ita，英语为 eng，德语为 deu...）。
\",\n \"zh-CN|Default language is eng and --language is optional for default language set in ./lib/lang.py.
\": \"默认语言为 eng，对于 ./lib/lang.py 中设置的默认语言，--language 是可选的。
\",\n \"zh-CN|The ISO-639-1 2 letters codes are also supported.\": \"也支持 2 个字母的 ISO-639-1 代码。\",\n \"zh-CN|****: Path to `model_name.zip` file,\": \"****：`model_name.zip` 文件的路径，\",\n \"zh-CN|which must contain (according to the tts engine) all the mandatory files
\": \"该文件必须（根据 tts 引擎）包含所有必需文件
\",\n \"zh-CN|(see ./lib/models.py).\": \"（参见 ./lib/models.py）。\",\n \"zh-CN|NOTE: in gradio/gui mode, to cancel a running conversion, just click on the [X] from the ebook upload component.\": \"注意：在 gradio/gui 模式下，要取消正在进行的转换，只需点击电子书上传组件的 [X] 即可。\",\n \"zh-CN|TIP: if it needs some more pause, add '[pause:3]' for 3 sec. etc.\": \"提示：如果需要稍长的停顿，请添加 '[pause:3]' 表示 3 秒等。\",\n \"zh-CN|Common Docker Issues\": \"常见的 Docker 问题\",\n \"zh-CN|My NVIDIA GPU isn't being detected?? -> [GPU ISSUES Wiki Page](https://github.com/DrewThomasson/ebook2audiobook/wiki/GPU-ISSUES)\": \"未检测到我的 NVIDIA GPU？？ -> [GPU 问题 Wiki 页面](https://github.com/DrewThomasson/ebook2audiobook/wiki/GPU-ISSUES)\",\n \"zh-CN|Fine Tuned TTS models\": \"微调（fine-tuned）TTS 模型\",\n \"zh-CN|Fine Tune your own XTTSv2 model\": \"微调您自己的 XTTSv2 模型\",\n \"zh-CN|De-noise training data\": \"训练数据降噪\",\n \"zh-CN|Fine Tuned TTS Collection\": \"微调 TTS 模型集合\",\n \"zh-CN|For an XTTSv2 custom model a ref audio clip of the voice reference is mandatory:\": \"对于自定义 XTTSv2 模型，必须提供语音的参考音频片段：\",\n \"zh-CN|Your own Ebook2Audiobook customization\": \"您自己的 Ebook2Audiobook 自定义\",\n \"zh-CN|You are free to modify libs/conf.py to add or remove the settings you wish. If you plan to do it just make\": \"您可以自由修改 libs/conf.py 以添加或删除您想要的设置。如果您打算这样做，只需制作\",\n \"zh-CN|a copy of the original conf.py so on each ebook2audiobook update you will backup your modified conf.py and put\": \"原始 conf.py 的副本，这样在每次更新 ebook2audiobook 时，您可以备份修改后的 conf.py 并恢复\",\n \"zh-CN|back the original one. You must plan the same process for models.py. If you wish to make your own custom model\": \"原始文件。您必须为 models.py 计划相同的流程。如果您想将自己的自定义模型\",\n \"zh-CN|as an official ebook2audiobook fine tuned model so please contact us and we'll add it to the presets list.\": \"变成官方微调的 ebook2audiobook 模型，请联系我们，我们会将其添加到预设列表中。\",\n \"zh-CN|Common Issues:\": \"常见问题：\",\n \"zh-CN|My NVIDIA/ROCm/XPU/MPS GPU isn't being detected?? -> [GPU ISSUES Wiki Page](https://github.com/DrewThomasson/ebook2audiobook/wiki/GPU-ISSUES)\": \"未检测到我的 NVIDIA/ROCm/XPU/MPS GPU？？ -> [GPU ISSUES Wiki Page](https://github.com/DrewThomasson/ebook2audiobook/wiki/GPU-ISSUES)\",\n \"zh-CN|CPU is slow (better on server smp CPU) while GPU can have almost real time conversion.\": \"CPU 很慢（在服务器 SMP CPU 上更好），而 GPU 可以实现接近实时的转换。\",\n \"zh-CN|(It doesn't have zero-shot voice cloning though, and is Siri quality voices, but it is much faster on cpu).\": \"（不过它没有 zero-shot 语音克隆，是 Siri 质量的语音，但在 cpu 上快得多）。\",\n \"zh-CN|\\\"I'm having dependency issues\\\" - Just use the docker, its fully self contained and has a headless mode,\": \"“我遇到依赖项问题” - 只需使用 docker，它完全独立并具有 headless 模式，\",\n \"zh-CN|add `--help` parameter at the end of the docker run command for more information.\": \"在 docker run 命令末尾添加 `--help` 参数以获取更多信息。\",\n \"zh-CN|\\\"I'm getting a truncated audio issue!\\\" - PLEASE MAKE AN ISSUE OF THIS,\": \"“我遇到音频被截断的问题！” - 请就此创建一个 ISSUE，\",\n \"zh-CN|we don't speak every language and need advise from users to fine tune the sentence splitting logic.😊\": \"我们不会说每种语言，需要用户的建议来微调句子拆分逻辑。😊\",\n \"zh-CN|***** ROADMAP *****\": \"***** 路线图 *****\",\n \"zh-CN|All Features open to public Contributions ⭐\": \"所有功能均向公众贡献开放 ⭐\",\n \"zh-CN|Any help from people speaking any of the supported languages to help us improve the models ⭐\": \"来自任何说支持语言的人的任何帮助，以帮助我们改进模型 ⭐\",\n \"zh-CN|Preview Blocks/Chapters before to start the conversion\": \"在开始转换之前预览块/章节\",\n \"zh-CN|Edit by sentence converted for surgical text change\": \"按转换后的句子进行编辑，以进行精准的文本更改\",\n \"zh-CN|SML tags integration for voice, pause, break, and more changes \": \"用于语音、停顿、中断及更多更改的 SML 标签集成 \",\n \"zh-CN|-h -help parameter info in different languages\": \"不同语言的 -h -help 参数信息\",\n \"zh-CN|OCR scanning for PDF / JPG / BMP / PNG / TIFF\": \"针对 PDF / JPG / BMP / PNG / TIFF 的 OCR 扫描\",\n \"zh-CN|Notebooks Folder [Talked about here](https://github.com/DrewThomasson/ebook2audiobookXTTS/issues/5#issuecomment-2408773254)\": \"Notebooks 文件夹 [Talked about here](https://github.com/DrewThomasson/ebook2audiobookXTTS/issues/5#issuecomment-2408773254)\",\n \"zh-CN|Make Chinese text splitting not split words and improve pause timing [Talked about here](https://github.com/DrewThomasson/ebook2audiobookXTTS/issues/18#issuecomment-2401154894)\": \"使中文文本拆分不拆分单词并改善停顿时间 [Talked about here](https://github.com/DrewThomasson/ebook2audiobookXTTS/issues/18#issuecomment-2401154894)\",\n \"zh-CN|[Make a IOS app](https://github.com/DrewThomasson/ebook2audiobook/pull/35#issuecomment-2496495212)\": \"[制作 iOS 应用](https://github.com/DrewThomasson/ebook2audiobook/pull/35#issuecomment-2496495212)\",\n \"zh-CN|[Make an android app](https://github.com/DrewThomasson/ebook2audiobook/pull/35#issuecomment-2496495212)\": \"[制作 android 应用](https://github.com/DrewThomasson/ebook2audiobook/pull/35#issuecomment-2496495212)\",\n \"zh-CN|Audiobookshelf integration\": \"Audiobookshelf 集成\",\n \"zh-CN|Extra Options\": \"额外选项\",\n \"zh-CN|Ebook Translation option\": \"电子书翻译选项\",\n \"zh-CN|Output format choices\": \"输出格式选择\",\n \"zh-CN|Batch ebook folder\": \"批量电子书文件夹\",\n \"zh-CN|Multiprocessing conversion\": \"多进程转换\",\n \"zh-CN|Batch ebook folder conversion\": \"批量电子书文件夹转换\",\n \"zh-CN|GPU Device detection\": \"GPU 设备检测\",\n \"zh-CN|Denoise any reference audio for upload voice cloning,\": \"为上传的语音克隆对任何参考音频进行降噪，\",\n \"zh-CN|Custom model upload (XTTSv2 only for now. more on request)\": \"自定义模型上传（目前仅 XTTSv2。更多应需求提供）\",\n \"zh-CN|Add European Portuguese language model for xttsv2, fairseq, vits, piper at least (help welcome)\": \"至少为 xttsv2、fairseq、vits、piper 添加欧洲葡萄牙语语言模型（欢迎帮助）\",\n \"zh-CN|Add Sindhi language model for xttsv2, fairseq, vits, piper at least (help welcome)\": \"至少为 xttsv2、fairseq、vits、piper 添加信德语语言模型（欢迎帮助）\",\n \"zh-CN|Readme Translation\": \"Readme 翻译\",\n \"zh-CN|🐍 OS Compatibility\": \"🐍 操作系统兼容性\",\n \"zh-CN|Extra Overkill for training models and such (All supported Coqui-tts models and piper-tts in one easy command) \": \"用于训练模型等的额外杀手锏（所有支持的 Coqui-tts 模型和 piper-tts 通过一条简单命令） \",\n \"zh-CN|For info about this @DrewThomasson, he is currently working on the development of this, [work-in-progress-repo here](https://github.com/DrewThomasson/Universal_TTS_Finetune)\": \"有关此信息 @DrewThomasson，他目前正在进行其开发，[正在进行中的仓库在此处](https://github.com/DrewThomasson/Universal_TTS_Finetune)\",\n \"zh-CN|Make a easy to use training gui for all coqui-tts models in the ljspeech format training recipes [here from coqui tts](https://github.com/coqui-ai/TTS/tree/dev/recipes/ljspeech)\": \"为 ljspeech 格式训练配方中的所有 coqui-tts 模型创建一个易于使用的训练 gui [此处来自 coqui tts](https://github.com/coqui-ai/TTS/tree/dev/recipes/ljspeech)\",\n \"zh-CN|Python Code normalization information for contributors\": \"面向贡献者的 Python 代码规范化信息\",\n \"zh-CN|no blank line between code, unless between functions and classes.\": \"代码之间没有空行，函数和类之间除外。\",\n \"zh-CN|single quote used for all key unless for dict() and json. dict['key'] always called with single quote\": \"除 dict() 和 json 外，所有键均使用单引号。dict['key'] 始终用单引号调用\",\n \"zh-CN|4 spaces indentation, not tab at all\": \"4 个空格缩进，完全不使用制表符\",\n \"zh-CN|strict typing for all functions and its arguments declaration and return values\": \"对所有函数及其参数和返回值声明进行严格类型标注\",\n \"zh-CN|no space between the argument and its typing, no space between the function, the \\\"->\\\" and the return value\": \"参数与其类型标注之间无空格，函数、“->”和返回值之间无空格\",\n \"zh-CN|Example:\": \"示例：\",\n \"zh-CN|Hardware donation for beta tests wanted\": \"征求用于测试版测试的硬件捐赠\",\n \"zh-CN|We accept any kind of hardware to test our development like:\": \"我们接受任何类型的硬件来测试我们的开发，例如：\",\n \"zh-CN|@DrewThomasson if you want to help out at all! 😃\": \"@DrewThomasson 如果您想以任何方式提供帮助！ 😃\",\n \"zh-CN|Do you need to rent a GPU to boost service from us?\": \"您需要租用 GPU 来增强我们的服务吗？\",\n \"zh-CN|A poll is open here https://github.com/DrewThomasson/ebook2audiobook/discussions/889\": \"此处已开放投票 https://github.com/DrewThomasson/ebook2audiobook/discussions/889\",\n \"zh-CN|Special Thanks\": \"特别鸣谢\",\n \"zh-CN|[@shakenbake15 for better chapter saving method](https://github.com/DrewThomasson/ebook2audiobook/issues/8) \": \"[@shakenbake15 提供了更好的章节保存方法](https://github.com/DrewThomasson/ebook2audiobook/issues/8) \",\n \"zh-CN|TTS engines\": \"TTS引擎\",\n \"zh-CN|XTTSv2\": \"XTTSv2\",\n \"zh-CN|Bark\": \"巴克\",\n \"zh-CN|Fairseq\": \"公平交易\",\n \"zh-CN|VITS\": \"VITS\",\n \"zh-CN|Tacotron2\": \"Tacotron2\",\n \"zh-CN|YourTTS\": \"YourTTS\",\n \"zh-CN|Tortoise\": \"陸龜\",\n \"zh-CN|GlowTTS\": \"GlowTTS\",\n \"zh-CN|Piper\": \"胡椒属\",\n \"zh-CN|GPT-SoVITS (https://github.com/RVC-Boss/GPT-SoVITS)\": \"GPT-SoVITS (https://github.com/RVC-Boss/GPT-SoVITS)\",\n \"zh-CN|OpenVoice (https://github.com/myshell-ai/OpenVoice)\": \"OpenVoice (https://github.com/myshell-ai/OpenVoice)\",\n \"zh-CN|fish-speech (https://github.com/fishaudio/fish-speech)\": \"fish-speech (https://github.com/fishaudio/fish-speech)\",\n \"zh-CN|ChatTTS (https://github.com/2noise/ChatTTS)\": \"ChatTTS (https://github.com/2noise/ChatTTS)\",\n \"zh-CN|CosyVoice (https://github.com/FunAudioLLM/CosyVoice)\": \"CosyVoice (https://github.com/FunAudioLLM/CosyVoice)\",\n \"zh-CN|F5-TTS (https://github.com/swivid/f5-tts)\": \"F5-TTS (https://github.com/swivid/f5-tts)\",\n \"zh-CN|chatterbox (https://github.com/resemble-ai/chatterbox)\": \"chatterbox (https://github.com/resemble-ai/chatterbox)\",\n \"zh-CN|Supertonic (https://github.com/supertone-inc/supertonic)\": \"Supertonic (https://github.com/supertone-inc/supertonic)\",\n \"zh-CN|Spark-TTS (https://github.com/sparkaudio/spark-tts)\": \"Spark-TTS (https://github.com/sparkaudio/spark-tts)\",\n \"zh-CN|index-tts (https://github.com/index-tts/index-tts)\": \"index-tts (https://github.com/index-tts/index-tts)\",\n \"zh-CN|MeloTTS (https://github.com/myshell-ai/MeloTTS)\": \"MeloTTS (https://github.com/myshell-ai/MeloTTS)\",\n \"zh-CN|Kokoro-TTS (https://github.com/hexgrad/kokoro)\": \"Kokoro-TTS (https://github.com/hexgrad/kokoro)\",\n \"zh-CN|OmniVoice (https://github.com/k2-fsa/OmniVoice)\": \"OmniVoice (https://github.com/k2-fsa/OmniVoice)\",\n \"zh-CN|Zonos (https://github.com/Zyphra/Zonos)\": \"Zonos (https://github.com/Zyphra/Zonos)\",\n \"zh-CN|Style-TTS2 (https://github.com/yl4579/StyleTTS2)\": \"样式-TTS2 (https://github.com/yl4579/StyleTTS2)\",\n \"zh-CN|Orpheus-TTS (https://github.com/canopyai/Orpheus-TTS)\": \"Orpheus-TTS (https://github.com/canopyai/Orpheus-TTS)\",\n \"zh-CN|NewTTS (https://github.com/neuphonic/neutts?tab=readme-ov-file)\": \"NewTTS (https://github.com/neuphonic/neutts?tab=readme-ov-file)\",\n \"zh-CN|VIbeVoice (https://github.com/vibevoice-community/VibeVoice)\": \"VIbeVoice (https://github.com/vibevoice-community/VibeVoice)\",\n \"zh-CN|Qwen3-TTS (https://huggingface.co/spaces/Qwen/Qwen3-TTS)\": \"Qwen3-TTS (https://huggingface.co/spaces/Qwen/Qwen3-TTS)\",\n \"es|CPU/GPU Converter from E-Book to audiobook with chapters and metadata
\": \"Conversor CPU/GPU de libro electrónico a audiolibro con capítulos y metadatos
\",\n \"es|using advanced TTS engines and much more.
\": \"usando motores TTS avanzados y mucho más.
\",\n \"es|Supports voice cloning and 1158 languages!\": \"¡Admite clonación de voz y 1158 idiomas!\",\n \"es|**This tool is intended for use with non-DRM, legally acquired eBooks only.**
\": \"**Esta herramienta está destinada a usarse únicamente con libros electrónicos sin DRM y adquiridos legalmente.**
\",\n \"es|The authors are not responsible for any misuse of this software or any resulting legal consequences.
\": \"Los autores no se hacen responsables de ningún uso indebido de este software ni de las consecuencias legales que de ello se deriven.
\",\n \"es|Use this tool responsibly and in accordance with all applicable laws.\": \"Utiliza esta herramienta de forma responsable y conforme a todas las leyes aplicables.\",\n \"es|Thanks to support ebook2audiobook developers!\": \"¡Gracias por apoyar a los desarrolladores de ebook2audiobook!\",\n \"es|Run locally\": \"Ejecución local\",\n \"es|Run Remotely\": \"Ejecución remota\",\n \"es|GUI Interface\": \"Interfaz gráfica (GUI)\",\n \"es|Click to see images of Web GUI\": \"Haz clic para ver imágenes de la GUI web\",\n \"es|**New Default Voice Demo** \": \"**Demo de la nueva voz por defecto** \",\n \"es|More Demos\": \"Más demos\",\n \"es|**ASMR Voice** \": \"**Voz ASMR** \",\n \"es|**Rainy Day Voice** \": \"**Voz de día lluvioso** \",\n \"es|**Scarlett Voice**\": \"**Voz Scarlett**\",\n \"es|**David Attenborough Voice** \": \"**Voz David Attenborough** \",\n \"es|**Example**\": \"**Ejemplo**\",\n \"es|Table of Contents\": \"Tabla de contenidos\",\n \"es|[Features](#features)\": \"[Características](#features)\",\n \"es|[GUI Interface](#gui-interface)\": \"[Interfaz gráfica](#gui-interface)\",\n \"es|[Supported Languages](#supported-languages)\": \"[Idiomas admitidos](#supported-languages)\",\n \"es|[Minimum Requirements](#hardware-requirements)\": \"[Requisitos mínimos](#hardware-requirements)\",\n \"es|[Usage](#instructions)\": \"[Uso](#instructions)\",\n \"es|[Run Locally](#instructions)\": \"[Ejecución local](#instructions)\",\n \"es|[Launching Gradio Web Interface](#instructions)\": \"[Lanzar la interfaz web de Gradio](#instructions)\",\n \"es|[Basic Headless Usage](#basic-usage)\": \"[Uso básico sin interfaz (headless)](#basic-usage)\",\n \"es|[Headless Custom XTTS Model Usage](#example-of-custom-model-zip-upload)\": \"[Uso de modelo XTTS personalizado sin interfaz](#example-of-custom-model-zip-upload)\",\n \"es|[Help command output](#help-command-output)\": \"[Salida del comando de ayuda](#help-command-output)\",\n \"es|[Run Remotely](#run-remotely)\": \"[Ejecución remota](#run-remotely)\",\n \"es|[Steps to Run](#docker)\": \"[Pasos para ejecutar](#docker)\",\n \"es|[Common Docker Issues](#common-docker-issues)\": \"[Problemas habituales con Docker](#common-docker-issues)\",\n \"es|[Fine Tuned TTS models](#fine-tuned-tts-models)\": \"[Modelos TTS ajustados](#fine-tuned-tts-models)\",\n \"es|[Collection of Fine-Tuned TTS Models](#fine-tuned-tts-collection)\": \"[Colección de modelos TTS ajustados](#fine-tuned-tts-collection)\",\n \"es|[Train XTTSv2](#fine-tune-your-own-xttsv2-model)\": \"[Entrenar XTTSv2](#fine-tune-your-own-xttsv2-model)\",\n \"es|[Supported eBook Formats](#supported-ebook-formats)\": \"[Formatos de libro electrónico admitidos](#supported-ebook-formats)\",\n \"es|[Output Formats](#output-and-process-formats)\": \"[Formatos de salida](#output-and-process-formats)\",\n \"es|[Revert to older Version](#reverting-to-older-versions)\": \"[Volver a una versión anterior](#reverting-to-older-versions)\",\n \"es|[Common Issues](#common-issues)\": \"[Problemas habituales](#common-issues)\",\n \"es|[Special Thanks](#special-thanks)\": \"[Agradecimientos especiales](#special-thanks)\",\n \"es|[Table of Contents](#table-of-contents)\": \"[Tabla de contenidos](#table-of-contents)\",\n \"es|Features\": \"Características\",\n \"es|🔧 **TTS Engines supported**: `XTTSv2`, `Bark`, `Fairseq`, `VITS`, `Tacotron2`, `Tortoise`, `GlowTTS`, `YourTTS`\": \"🔧 **Motores TTS admitidos**: `XTTSv2`, `Bark`, `Fairseq`, `VITS`, `Tacotron2`, `Tortoise`, `GlowTTS`, `YourTTS`\",\n \"es|📚 **Convert multiple file formats**: `.epub`, `.mobi`, `.azw3`, `.fb2`, `.lrf`, `.rb`, `.snb`, `.tcr`, `.pdf`, `.txt`, `.rtf`, `.doc`, `.docx`, `.html`, `.odt`, `.azw`, `.tiff`, `.tif`, `.png`, `.jpg`, `.jpeg`, `.bmp`, `.zip`\": \"📚 **Convertir múltiples formatos de archivo**: `.epub`, `.mobi`, `.azw3`, `.fb2`, `.lrf`, `.rb`, `.snb`, `.tcr`, `.pdf`, `.txt`, `.rtf`, `.doc`, `.docx`, `.html`, `.odt`, `.azw`, `.tiff`, `.tif`, `.png`, `.jpg`, `.jpeg`, `.bmp`, `.zip`\",\n \"es|💻 **TextArea** to convert directly a short text in audio\": \"💻 **Área de texto** para convertir directamente un texto corto en audio\",\n \"es|🔍 **OCR scanning** for files with text pages as images\": \"🔍 **Escaneo OCR** para archivos con páginas de texto en forma de imágenes\",\n \"es|🔊 **High-quality text-to-speech** from near realtime to near real voice\": \"🔊 **Texto a voz de alta calidad**, desde casi en tiempo real hasta una voz casi real\",\n \"es|🗣️ **Optional voice cloning** using your own voice file\": \"🗣️ **Clonación de voz opcional** usando tu propio archivo de voz\",\n \"es|🌐 **Supports 1158 languages** ([supported languages list](https://dl.fbaipublicfiles.com/mms/tts/all-tts-languages.html))\": \"🌐 **Admite 1158 idiomas** ([supported languages list](https://dl.fbaipublicfiles.com/mms/tts/all-tts-languages.html))\",\n \"es|💻 **Low-resource friendly** — runs on **2 GB RAM / 1 GB VRAM (minimum)**\": \"💻 **Apto para recursos limitados** — funciona con **2 GB de RAM / 1 GB de VRAM (mínimo)**\",\n \"es|🎵 **Audiobook output formats**: mono or stereo `aac`, `flac`, `mp3`, `m4b`, `m4a`, `mp4`, `mov`, `ogg`, `wav`, `webm`\": \"🎵 **Formatos de salida del audiolibro**: mono or stereo `aac`, `flac`, `mp3`, `m4b`, `m4a`, `mp4`, `mov`, `ogg`, `wav`, `webm`\",\n \"es|🧠 **SML tags supported** — fine-grained control of breaks, pauses, voice switching and more ([see below](#sml-tags-available))\": \"🧠 **Etiquetas SML admitidas** — control preciso de cortes, pausas, cambio de voz y mucho más ([see below](#sml-tags-available))\",\n \"es|🧩 **Optional custom model** using your own trained model (XTTSv2, VITS, FAIRSEQ, PIPER, others on request)\": \"🧩 **Modelo personalizado opcional** usando tu propio modelo entrenado (XTTSv2, VITS, FAIRSEQ, PIPER, others on request)\",\n \"es|🎛️ **Fine-tuned preset models** trained by the E2A Team
\": \"🎛️ **Modelos preajustados y ajustados** entrenados por el equipo de E2A
\",\n \"es|(Contact us if you need additional fine-tuned models, or if you’d like to share yours to the official preset list)\": \"(Contáctanos si necesitas modelos ajustados adicionales, o si quieres compartir los tuyos en la lista oficial de preajustes)\",\n \"es|Hardware Requirements\": \"Requisitos de hardware\",\n \"es|2GB RAM min, 8GB recommended.\": \"2 GB de RAM mín., 8 GB recomendados.\",\n \"es|1GB VRAM min, 4GB recommended.\": \"1 GB de VRAM mín., 4 GB recomendados.\",\n \"es|Virtualization enabled if running on windows (Docker only).\": \"Virtualización habilitada si se ejecuta en Windows (solo Docker).\",\n \"es|MPS (Apple Silicon CPU)\": \"MPS (CPU Apple Silicon)\",\n \"es|* Modern TTS engines are ve\n"}