📚 ebook2audiobook

Convert eBooks to audiobooks with chapters and metadata using Calibre and Coqui XTTS. Supports optional voice cloning and multiple languages!

🖥️ Web GUI Interface

demo_web_gui

Click to see images of Web GUI

README.md

🌟 Features

📖 Converts eBooks to text format with Calibre.
📚 Splits eBook into chapters for organized audio.
🎙️ High-quality text-to-speech with Coqui XTTS.
🗣️ Optional voice cloning with your own voice file.
🌍 Supports multiple languages (English by default).
🖥️ Designed to run on 4GB RAM.

🤗 Huggingface space demo

Huggingface space is running on free cpu tier so expect very slow or timeout lol, just don't give it giant files is all
Best to duplicate space or run locally.

Free Google Colab

🛠️ Requirements

Python 3.10
coqui-tts Python package
Calibre (for eBook conversion)
FFmpeg (for audiobook creation)
Optional: Custom voice file for voice cloning

🔧 Installation Instructions

Install Python 3.x from Python.org.
Install Calibre:
- Ubuntu: sudo apt-get install -y calibre
- macOS: brew install calibre
- Windows (Admin Powershell): choco install calibre
Install FFmpeg:
- Ubuntu: sudo apt-get install -y ffmpeg
- macOS: brew install ffmpeg
- Windows (Admin Powershell): choco install ffmpeg
Optional: Install Mecab (for non-Latin languages):
- Ubuntu: sudo apt-get install -y mecab libmecab-dev mecab-ipadic-utf8
- macOS: brew install mecab, brew install mecab-ipadic
- Windows: mecab-website-to-install-manually (Note: Japanese support is limited)

Install Python packages:

pip install coqui-tts==0.24.2 pydub nltk beautifulsoup4 ebooklib tqdm gradio==4.44.0

python -m nltk.downloader punkt
python -m nltk.downloader punkt_tab

For non-Latin languages:

pip install mecab mecab-python3 unidic

python -m unidic download

🌐 Supported Languages

English (en)
Spanish (es)
French (fr)
German (de)
Italian (it)
Portuguese (pt)
Polish (pl)
Turkish (tr)
Russian (ru)
Dutch (nl)
Czech (cs)
Arabic (ar)
Chinese (zh-cn)
Japanese (ja)
Hungarian (hu)
Korean (ko)

Specify the language code when running the script in headless mode.

🚀 Usage

🖥️ Launching Gradio Web Interface

Run the Script:
```
python app.py
```
Open the Web App: Click the URL provided in the terminal to access the web app and convert eBooks.
For Public Link: Add --share True to the end of it like this: python app.py --share True
- [For More Parameters]: use the -h parameter like this python app.py -h

📝 Basic Headless Usage

python app.py --headless True --ebook <path_to_ebook_file> --voice [path_to_voice_file] --language [language_code]

: Path to your eBook file.
[path_to_voice_file]: Optional for voice cloning.
[language_code]: Optional to specify language.
[For More Parameters]: use the -h parameter like this python app.py -h

🧩 Headless Custom XTTS Model Usage

python app.py --headless True --use_custom_model True --ebook <ebook_file_path> --voice <target_voice_file_path> --language <language> --custom_model <custom_model_path> --custom_config <custom_config_path> --custom_vocab <custom_vocab_path>

: Path to your eBook file.
: Optional for voice cloning.
: Optional to specify language.
: Path to model.pth.
: Path to config.json.
: Path to vocab.json.
[For More Parameters]: use the -h parameter like this python app.py -h

🧩 Headless Custom XTTS Model Usage With Zip link to XTTS Fine-Tune Model 🌐

python app.py --headless True --use_custom_model True --ebook <ebook_file_path> --voice <target_voice_file_path> --language <language> --custom_model_url <custom_model_URL_ZIP_path>

: Path to your eBook file.
: Optional for voice cloning.
: Optional to specify language.
: URL Path to zip of Model folder. For Example this for the xtts_David_Attenborough_fine_tune https://huggingface.co/drewThomasson/xtts_David_Attenborough_fine_tune/resolve/main/Finished_model_files.zip?download=true
For a custom model a ref audio clip of the voice will also be needed: ref audio clip of David Attenborough
[For More Parameters]: use the -h parameter like this python app.py -h

🔍 For Detailed Guide with list of all Parameters to use

python app.py -h

This will output the following:


usage: app.py [-h] [--share SHARE] [--headless HEADLESS] [--ebook EBOOK] [--voice VOICE]
          [--language LANGUAGE] [--use_custom_model USE_CUSTOM_MODEL]
          [--custom_model CUSTOM_MODEL] [--custom_config CUSTOM_CONFIG]
          [--custom_vocab CUSTOM_VOCAB] [--custom_model_url CUSTOM_MODEL_URL]
          [--temperature TEMPERATURE] [--length_penalty LENGTH_PENALTY]
          [--repetition_penalty REPETITION_PENALTY] [--top_k TOP_K] [--top_p TOP_P]
          [--speed SPEED] [--enable_text_splitting ENABLE_TEXT_SPLITTING]

Convert 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.

options: -h, --help show this help message and exit --share SHARE Set to True to enable a public shareable Gradio link. Defaults to False. --headless HEADLESS Set to True to run in headless mode without the Gradio interface. Defaults to False. --ebook EBOOK Path to the ebook file for conversion. Required in headless mode. --voice VOICE Path to the target voice file for TTS. Optional, uses a default voice if not provided. --language LANGUAGE Language for the audiobook conversion. Options: en, es, fr, de, it, pt, pl, tr, ru, nl, cs, ar, zh-cn, ja, hu, ko. Defaults to English (en). --use_custom_model USE_CUSTOM_MODEL Set to True to use a custom TTS model. Defaults to False. Must be True to use custom models, otherwise you'll get an error. --custom_model CUSTOM_MODEL Path to the custom model file (.pth). Required if using a custom model. --custom_config CUSTOM_CONFIG Path to the custom config file (config.json). Required if using a custom model. --custom_vocab CUSTOM_VOCAB Path to the custom vocab file (vocab.json). Required if using a custom model. --custom_model_url CUSTOM_MODEL_URL URL to download the custom model as a zip file. Optional, but will be used if provided. Examples include David Attenborough's model: 'https://huggingface.co/drewThomasson/xtts_David_Attenbor ough_fine_tune/resolve/main/Finished_model_files.zip?download=tr ue'. More XTTS fine-tunes can be found on my Hugging Face at 'https://huggingface.co/drewThomasson'. --temperature TEMPERATURE Temperature for the model. Defaults to 0.65. Higher Tempatures will lead to more creative outputs IE: more Hallucinations. Lower Tempatures will be more monotone outputs IE: less Hallucinations. --length_penalty LENGTH_PENALTY A length penalty applied to the autoregressive decoder. Defaults to 1.0. Not applied to custom models. --repetition_penalty REPETITION_PENALTY A penalty that prevents the autoregressive decoder from repeating itself. Defaults to 2.0. --top_k TOP_K Top-k sampling. Lower values mean more likely outputs and increased audio generation speed. Defaults to 50. --top_p TOP_P Top-p sampling. Lower values mean more likely outputs and increased audio generation speed. Defaults to 0.8. --speed SPEED Speed factor for the speech generation. IE: How fast the Narrerator will speak. Defaults to 1.0. --enable_text_splitting ENABLE_TEXT_SPLITTING Enable splitting text into sentences. Defaults to True.

Example: python script.py --headless --ebook path_to_ebook --voice path_to_voice --language en --use_custom_model True --custom_model model.pth --custom_config config.json --custom_vocab vocab.json


<details>
  <summary>⚠️ Legacy-Depricated Old Use Instructions</summary>

## 🚀 Usage

## Legacy files have been moved to `ebook2audiobookXTTS/legacy/`

### 🖥️ Gradio Web Interface

1. **Run the Script**:
   ```bash
   python custom_model_ebook2audiobookXTTS_gradio.py

Open the Web App: Click the URL provided in the terminal to access the web app and convert eBooks.

📝 Basic Usage

python ebook2audiobook.py <path_to_ebook_file> [path_to_voice_file] [language_code]

: Path to your eBook file.
[path_to_voice_file]: Optional for voice cloning.
[language_code]: Optional to specify language.

🧩 Custom XTTS Model

python custom_model_ebook2audiobookXTTS.py <ebook_file_path> <target_voice_file_path> <language> <custom_model_path> <custom_config_path> <custom_vocab_path>

: Path to your eBook file.
: Optional for voice cloning.
: Optional to specify language.
: Path to model.pth.
: Path to config.json.
: Path to vocab.json.

🐳 Using Docker

You can also use Docker to run the eBook to Audiobook converter. This method ensures consistency across different environments and simplifies setup.

🚀 Running the Docker Container

To run the Docker container and start the Gradio interface, use the following command:

-Run with CPU only

docker run -it --rm -p 7860:7860 --platform=linux/amd64 athomasson2/ebook2audiobookxtts:huggingface python app.py

-Run with GPU Speedup (Nvida graphics cards only)

docker run -it --rm --gpus all -p 7860:7860 --platform=linux/amd64 athomasson2/ebook2audiobookxtts:huggingface python app.py

This command will start the Gradio interface on port 7860.(localhost:7860)

For more options like running the docker in headless mode or making the gradio link public add the -h parameter after the app.py in the docker launch command

Example of using docker in headless mode or modifying anything with the extra parameters + Full guide

Example of using docker in headless mode

first for a docker pull of the latest with

docker pull athomasson2/ebook2audiobookxtts:huggingface

Before you do run this you need to create a dir named "input-folder" in your current dir which will be linked, This is where you can put your input files for the docker image to see
```
mkdir input-folder && mkdir Audiobooks
```
In the command below swap out YOUR_INPUT_FILE.TXT with the name of your input file

docker run -it --rm \
    -v $(pwd)/input-folder:/home/user/app/input_folder \
    -v $(pwd)/Audiobooks:/home/user/app/Audiobooks \
    --platform linux/amd64 \
    athomasson2/ebook2audiobookxtts:huggingface \
    python app.py --headless True --ebook /home/user/app/input_folder/YOUR_INPUT_FILE.TXT

And that should be it!
The output Audiobooks will be found in the Audiobook folder which will also be located in your local dir you ran this docker command in

To get the help command for the other parameters this program has you can run this

docker run -it --rm \
    --platform linux/amd64 \
    athomasson2/ebook2audiobookxtts:huggingface \
    python app.py -h

and that will output this

user/app/ebook2audiobookXTTS/input-folder -v $(pwd)/Audiobooks:/home/user/app/ebook2audiobookXTTS/Audiobooks --memory="4g" --network none --platform linux/amd64 athomasson2/ebook2audiobookxtts:huggingface python app.py -h
starting...
usage: app.py [-h] [--share SHARE] [--headless HEADLESS] [--ebook EBOOK] [--voice VOICE]
              [--language LANGUAGE] [--use_custom_model USE_CUSTOM_MODEL]
              [--custom_model CUSTOM_MODEL] [--custom_config CUSTOM_CONFIG]
              [--custom_vocab CUSTOM_VOCAB] [--custom_model_url CUSTOM_MODEL_URL]
              [--temperature TEMPERATURE] [--length_penalty LENGTH_PENALTY]
              [--repetition_penalty REPETITION_PENALTY] [--top_k TOP_K] [--top_p TOP_P]
              [--speed SPEED] [--enable_text_splitting ENABLE_TEXT_SPLITTING]

Convert 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.

options:
  -h, --help            show this help message and exit
  --share SHARE         Set to True to enable a public shareable Gradio link. Defaults
                        to False.
  --headless HEADLESS   Set to True to run in headless mode without the Gradio
                        interface. Defaults to False.
  --ebook EBOOK         Path to the ebook file for conversion. Required in headless
                        mode.
  --voice VOICE         Path to the target voice file for TTS. Optional, uses a default
                        voice if not provided.
  --language LANGUAGE   Language for the audiobook conversion. Options: en, es, fr, de,
                        it, pt, pl, tr, ru, nl, cs, ar, zh-cn, ja, hu, ko. Defaults to
                        English (en).
  --use_custom_model USE_CUSTOM_MODEL
                        Set to True to use a custom TTS model. Defaults to False. Must
                        be True to use custom models, otherwise you'll get an error.
  --custom_model CUSTOM_MODEL
                        Path to the custom model file (.pth). Required if using a custom
                        model.
  --custom_config CUSTOM_CONFIG
                        Path to the custom config file (config.json). Required if using
                        a custom model.
  --custom_vocab CUSTOM_VOCAB
                        Path to the custom vocab file (vocab.json). Required if using a
                        custom model.
  --custom_model_url CUSTOM_MODEL_URL
                        URL to download the custom model as a zip file. Optional, but
                        will be used if provided. Examples include David Attenborough's
                        model: 'https://huggingface.co/drewThomasson/xtts_David_Attenbor
                        ough_fine_tune/resolve/main/Finished_model_files.zip?download=tr
                        ue'. More XTTS fine-tunes can be found on my Hugging Face at
                        'https://huggingface.co/drewThomasson'.
  --temperature TEMPERATURE
                        Temperature for the model. Defaults to 0.65. Higher Tempatures
                        will lead to more creative outputs IE: more Hallucinations.
                        Lower Tempatures will be more monotone outputs IE: less
                        Hallucinations.
  --length_penalty LENGTH_PENALTY
                        A length penalty applied to the autoregressive decoder. Defaults
                        to 1.0. Not applied to custom models.
  --repetition_penalty REPETITION_PENALTY
                        A penalty that prevents the autoregressive decoder from
                        repeating itself. Defaults to 2.0.
  --top_k TOP_K         Top-k sampling. Lower values mean more likely outputs and
                        increased audio generation speed. Defaults to 50.
  --top_p TOP_P         Top-p sampling. Lower values mean more likely outputs and
                        increased audio generation speed. Defaults to 0.8.
  --speed SPEED         Speed factor for the speech generation. IE: How fast the
                        Narrerator will speak. Defaults to 1.0.
  --enable_text_splitting ENABLE_TEXT_SPLITTING
                        Enable splitting text into sentences. Defaults to True.

Example: python script.py --headless --ebook path_to_ebook --voice path_to_voice
--language en --use_custom_model True --custom_model model.pth --custom_config
config.json --custom_vocab vocab.json

🖥️ Docker GUI

demo_web_gui

Click to see images of Web GUI

🛠️ For Custom Xtts Models

Models built to be better at a specific voice. Check out my Hugging Face page here.

To use a custom model, paste the link of the Finished_model_files.zip file like this:

David Attenborough fine tuned Finished_model_files.zip

For a custom model a ref audio clip of the voice will also be needed: ref audio clip of David Attenborough

More details can be found at the Dockerfile Hub Page.

🌐 Fine Tuned Xtts models

To find already fine-tuned XTTS models, visit this Hugging Face link 🌐. Search for models that include "xtts fine tune" in their names.

🎥 Demos

Rainy day voice

https://github.com/user-attachments/assets/8486603c-38b1-43ce-9639-73757dfb1031

David Attenborough voice

https://github.com/user-attachments/assets/47c846a7-9e51-4eb9-844a-7460402a20a8

🤗 Huggingface space demo

Huggingface space is running on free cpu tier so expect very slow or timeout lol, just don't give it giant files is all
Best to duplicate space or run locally.

Free Google Colab

📚 Supported eBook Formats

.epub, .pdf, .mobi, .txt, .html, .rtf, .chm, .lit, .pdb, .fb2, .odt, .cbr, .cbz, .prc, .lrf, .pml, .snb, .cbc, .rb, .tcr
Best results: .epub or .mobi for automatic chapter detection

📂 Output

Creates an .m4b file with metadata and chapters.
Example Output:

🛠️ Common Issues:

"It's slow!" - On CPU only this is very slow, and you can only get speedups though a NVIDIA GPU. Discussion about this For faster multilingual generation I would suggest my other project that uses piper-tts instead(It doesn't have zero-shot voice cloning though, and is siri quality voices, but it is much faster on cpu.)
"I'm having dependency issues" - Just use the docker, its fully self contained and has a headless mode, add -h parameter after the app.py in the docker run command for more information.
"Im getting a truncated audio issue!" - PLEASE MAKE AN ISSUE OF THIS, I don't speak every language and I need advise from each person to fine tune my sentense splitting function on any other languages.😊
"The loading bar is stuck at 30% in the web gui!" - The web gui loading bar is extreamly basic as its just split between the three loading steps, refer to the terminal and what sentense it's on for a more accurate gauge on where is it progress wise.

What I need help with! 🙌

Full list of things can be found here

Any help from people speaking any of the supported langues to help with proper sentence splitting methods
Potentially creating readme Guides for Multiple languages(Becuase the only language I know is English 😔)

🙏 Special Thanks

Coqui TTS: Coqui TTS GitHub
Calibre: Calibre Website
@shakenbake15 for better chapter saving method

DrewThomasson / ebook2audiobook

readme

📚 ebook2audiobook

🖥️ Web GUI Interface

README.md

🌟 Features

🤗 Huggingface space demo

Free Google Colab

🛠️ Requirements

🔧 Installation Instructions

🌐 Supported Languages

🚀 Usage

🖥️ Launching Gradio Web Interface

📝 Basic Headless Usage

🧩 Headless Custom XTTS Model Usage

🧩 Headless Custom XTTS Model Usage With Zip link to XTTS Fine-Tune Model 🌐

🔍 For Detailed Guide with list of all Parameters to use

📝 Basic Usage

🧩 Custom XTTS Model

🐳 Using Docker

🚀 Running the Docker Container

Example of using docker in headless mode

To get the help command for the other parameters this program has you can run this

🖥️ Docker GUI

🛠️ For Custom Xtts Models

🌐 Fine Tuned Xtts models

🎥 Demos

🤗 Huggingface space demo

Free Google Colab

📚 Supported eBook Formats

📂 Output

🛠️ Common Issues:

What I need help with! 🙌

Full list of things can be found here

🙏 Special Thanks