📚 ebook2audiobook

CPU/GPU Converter from eBooks to audiobooks with chapters and metadata

using XTTSv2, Bark, Vits, Fairseq, YourTTS and more. Supports voice cloning and +1110 languages!

[!IMPORTANT]
This tool is intended for use with non-DRM, legally acquired eBooks only.

The authors are not responsible for any misuse of this software or any resulting legal consequences.

Use this tool responsibly and in accordance with all applicable laws.

Thanks to support ebook2audiobook developers!

Run locally

Run Remotely

GUI Interface

Click to see images of Web GUI

Demos

New Default Voice Demo

https://github.com/user-attachments/assets/750035dc-e355-46f1-9286-05c1d9e88cea

More Demos

Rainy Day Voice

https://github.com/user-attachments/assets/d25034d9-c77f-43a9-8f14-0d167172b080

David Attenborough Voice

https://github.com/user-attachments/assets/0d437a41-0b0d-48ed-8c9b-02763d5e48ea

Example

README.md

• ara العربية (Arabic)
• zho 中文 (Chinese)
• eng English
• swe Svenska (Swedish)
• fas فارسی (Persian)
• kor 한국어 (Korean)
• ita Italiano (Italian)

Table of Contents

• ebook2audiobook
• Features
• GUI Interface
• Demos
• Supported Languages
• Minimum Requirements
• Usage
  • Run Locally
    • Launching Gradio Web Interface
    • Basic Headless Usage
    • Headless Custom XTTS Model Usage
    • Help command output
  • Run Remotely
• Fine Tuned TTS models
  • Collection of Fine-Tuned TTS Models
  • Train XTTS
• Docker
  • GPU options
  • Docker Run
  • Docker Build
  • Docker Compose
  • Docker headless guide
  • Docker container file locations
  • Common Docker issues
• Supported eBook Formats
• Output Formats
• Common Issues
• Special Thanks
• Table of Contents

Features

• 📚 Splits eBook into chapters for organized audio.
• 🎙️ High-quality text-to-speech with Coqui XTTSv2 and Fairseq (and more).
• 🗣️ Optional voice cloning with your own voice file.
• 🌍 Supports +1110 languages (English by default). List of Supported languages
• 🖥️ Designed to run on 4GB RAM.

Supported Languages

Arabic (ar)	Chinese (zh)	English (en)	Spanish (es)
French (fr)	German (de)	Italian (it)	Portuguese (pt)
Polish (pl)	Turkish (tr)	Russian (ru)	Dutch (nl)
Czech (cs)	Japanese (ja)	Hindi (hi)	Bengali (bn)
Hungarian (hu)	Korean (ko)	Vietnamese (vi)	Swedish (sv)
Persian (fa)	Yoruba (yo)	Swahili (sw)	Indonesian (id)
Slovak (sk)	Croatian (hr)	Tamil (ta)	Danish (da)

• +1100 languages and dialects here

Hardware Requirements

• 4gb RAM minimum, 8GB recommended
• Virtualization enabled if running on windows (Docker only)
• CPU (intel, AMD, ARM), GPU (Nvidia, AMD*, Intel*) (Recommended), MPS (Apple Silicon CPU)
  *available very soon

[!IMPORTANT]
Before to post an install or bug issue search carefully to the opened and closed issues TAB

to be sure your issue does not exist already.

[!NOTE]
Lacking of any standards structure like what is a chapter, paragraph, preface etc.

you should first remove manually any text you don’t want to be converted in audio.

Installation Instructions

1. Clone repo

git clone https://github.com/DrewThomasson/ebook2audiobook.git
cd ebook2audiobook

Launching Gradio Web Interface

1. Run ebook2audiobook:
   • Linux/MacOS

     ./ebook2audiobook.sh  # Run launch script
     

   • Mac Launcher
     Double click Mac Ebook2Audiobook Launcher.command
   • Windows

     ebook2audiobook.cmd  # Run launch script or double click on it
     

   • Windows Launcher
     Double click ebook2audiobook.cmd
2. Open the Web App: Click the URL provided in the terminal to access the web app and convert eBooks.
3. For Public Link:
   python app.py --share (all OS)
   ./ebook2audiobook.sh --share (Linux/MacOS)
   ebook2audiobook.cmd --share (Windows)

[!IMPORTANT]
If the script is stopped and run again, you need to refresh your gradio GUI interface

to let the web page reconnect to the new connection socket.

Basic Usage

• Linux/MacOS:

  ./ebook2audiobook.sh --headless --ebook <path_to_ebook_file> \
      --voice [path_to_voice_file] --language [language_code]
  

• Windows

  ebook2audiobook.cmd --headless --ebook <path_to_ebook_file>
      --voice [path_to_voice_file] --language [language_code]
  

• [–ebook]: Path to your eBook file

• [–voice]: Voice cloning file path (optional)

• [–language]: Language code in ISO-639-3 (i.e.: ita for italian, eng for english, deu for german…).
  
  Default language is eng and --language is optional for default language set in ./lib/lang.py.
  
  The ISO-639-1 2 letters codes are also supported.

Example of Custom Model Zip Upload

(must be a .zip file containing the mandatory model files. Example for XTTS: config.json, model.pth, vocab.json and ref.wav)

• Linux/MacOS

  ./ebook2audiobook.sh --headless --ebook <ebook_file_path> \
      --voice <target_voice_file_path> --language <language> --custom_model <custom_model_path>
  

• Windows

  ebook2audiobook.cmd --headless --ebook <ebook_file_path> \
      --voice <target_voice_file_path> --language <language> --custom_model <custom_model_path>
  

• <custom_model_path>: Path to model_name.zip file,
  which must contain (according to the tts engine) all the mandatory files
  
  (see ./lib/models.py).

For Detailed Guide with list of all Parameters to use

• Linux/MacOS

  ./ebook2audiobook.sh --help
  

• Windows

  ebook2audiobook.cmd --help
  

• Or for all OS

```python
 app.py --help
```

usage: app.py [-h] [--script_mode SCRIPT_MODE] [--session SESSION] [--share]
              [--headless] [--ebook EBOOK] [--ebooks_dir EBOOKS_DIR]
              [--language LANGUAGE] [--voice VOICE] [--device {cpu,gpu,mps}]
              [--tts_engine {xtts,bark,vits,fairseq,yourtts}]
              [--custom_model CUSTOM_MODEL] [--fine_tuned FINE_TUNED]
              [--output_format OUTPUT_FORMAT] [--temperature TEMPERATURE]
              [--length_penalty LENGTH_PENALTY] [--num_beams NUM_BEAMS]
              [--repetition_penalty REPETITION_PENALTY] [--top_k TOP_K] [--top_p TOP_P]
              [--speed SPEED] [--enable_text_splitting] [--output_dir OUTPUT_DIR]
              [--version]

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
  --session SESSION     Session to resume the conversion in case of interruption, crash, 
                            or reuse of custom models and custom cloning voices.

**** The following option are for gradio/gui mode only:
  Optional

  --share               Enable a public shareable Gradio link.

**** The following options are for --headless mode only:
  --headless            Run the script in headless mode
  --ebook EBOOK         Path to the ebook file for conversion. Cannot be used when --ebooks_dir is present.
  --ebooks_dir EBOOKS_DIR
                        Relative or absolute path of the directory containing the files to convert. 
                            Cannot be used when --ebook is present.
  --language LANGUAGE   Language of the e-book. Default language is set 
                            in ./lib/lang.py sed as default if not present. All compatible language codes are in ./lib/lang.py

optional parameters:
  --voice VOICE         (Optional) Path to the voice cloning file for TTS engine. 
                            Uses the default voice if not present.
  --device {cpu,gpu,mps}
                        (Optional) Pprocessor unit type for the conversion. 
                            Default is set in ./lib/conf.py if not present. Fall back to CPU if GPU not available.
  --tts_engine {xtts,bark,vits,fairseq,yourtts}
                        (Optional) Preferred TTS engine (available are: ['xtts', 'bark', 'vits', 'fairseq', 'yourtts'].
                            Default depends on the selected language. The tts engine should be compatible with the chosen language
  --custom_model CUSTOM_MODEL
                        (Optional) Path to the custom model zip file cntaining mandatory model files. 
                            Please refer to ./lib/models.py
  --fine_tuned FINE_TUNED
                        (Optional) Fine tuned model path. Default is builtin model.
  --output_format OUTPUT_FORMAT
                        (Optional) Output audio format. Default is set in ./lib/conf.py
  --temperature TEMPERATURE
                        (xtts only, optional) Temperature for the model. 
                            Default to config.json model. Higher temperatures lead to more creative outputs.
  --length_penalty LENGTH_PENALTY
                        (xtts only, optional) A length penalty applied to the autoregressive decoder. 
                            Default to config.json model. Not applied to custom models.
  --num_beams NUM_BEAMS
                        (xtts only, optional) Controls how many alternative sequences the model explores. Must be equal or greater than length penalty. 
                            Default to config.json model.
  --repetition_penalty REPETITION_PENALTY
                        (xtts only, optional) A penalty that prevents the autoregressive decoder from repeating itself. 
                            Default to config.json model.
  --top_k TOP_K         (xtts only, optional) Top-k sampling. 
                            Lower values mean more likely outputs and increased audio generation speed. 
                            Default to config.json model.
  --top_p TOP_P         (xtts only, optional) Top-p sampling. 
                            Lower values mean more likely outputs and increased audio generation speed. Default to 0.85
  --speed SPEED         (xtts only, optional) Speed factor for the speech generation. 
                            Default to config.json model.
  --enable_text_splitting
                        (xtts only, optional) Enable TTS text splitting. This option is known to not be very efficient. 
                            Default to config.json model.
  --output_dir OUTPUT_DIR
                        (Optional) Path to the output directory. Default is set in ./lib/conf.py
  --version             Show the version of the script and exit

Example usage:    
Windows:
    Gradio/GUI:
    ebook2audiobook.cmd
    Headless mode:
    ebook2audiobook.cmd --headless --ebook '/path/to/file'
Linux/Mac:
    Gradio/GUI:
    ./ebook2audiobook.sh
    Headless mode:
    ./ebook2audiobook.sh --headless --ebook '/path/to/file'

NOTE: in gradio/gui mode, to cancel a running conversion, just click on the [X] from the ebook upload component.

Docker GPU Options

Available tags: latest (CUDA 11), cpu, rocm, cuda11, cuda12, cuda128, xpu (x86 only)

Running the Docker Container

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

-Run with CPU only

docker run --pull always --rm -p 7860:7860 athomasson2/ebook2audiobook

-Run with GPU Speedup (NVIDIA compatible only)

docker run --pull always --rm --gpus all -p 7860:7860 athomasson2/ebook2audiobook

Building the Docker Container

• You can build the docker image with the command:

docker build -t athomasson2/ebook2audiobook .

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

• For more options add the parameter --help

Docker container file locations

All ebook2audiobooks will have the base dir of /app/
For example:
tmp = /app/tmp
audiobooks = /app/audiobooks

Docker headless guide

• 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 --pull always --rm \
    -v $(pwd)/input-folder:/app/input_folder \
    -v $(pwd)/audiobooks:/app/audiobooks \
    athomasson2/ebook2audiobook \
    --headless --ebook /input_folder/YOUR_EBOOK_FILE

• 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 --pull always --rm athomasson2/ebook2audiobook --help

That will output this
Help command output

Docker Compose

This project uses Docker Compose to run locally. You can enable or disable GPU support
by setting either *gpu-enabled or *gpu-disabled in docker-compose.yml

Steps to Run

1. Clone the Repository (if you haven’t already):

   git clone https://github.com/DrewThomasson/ebook2audiobook.git
   cd ebook2audiobook
   

2. Set GPU Support (disabled by default)
   To enable GPU support, modify docker-compose.yml and change *gpu-disabled to *gpu-enabled
3. Start the service:

   docker-compose up -d
   

4. Access the service:
   The service will be available at http://localhost:7860.

Common Docker Issues

• python: can't open file '/home/user/app/app.py': [Errno 2] No such file or directory (Just remove all post arguments as I replaced the CMD with ENTRYPOINT in the Dockerfile)

  • Example: docker run --pull always athomasson2/ebook2audiobook app.py --script_mode full_docker - > corrected - > docker run --pull always athomasson2/ebook2audiobook
  • Arguments can be easily added like this now docker run --pull always athomasson2/ebook2audiobook --share

• Docker gets stuck downloading Fine-Tuned models.
  (This does not happen for every computer but some appear to run into this issue)
  Disabling the progress bar appears to fix the issue,
  as discussed here in #191
  Example of adding this fix in the docker run command

docker run --pull always --rm --gpus all -e HF_HUB_DISABLE_PROGRESS_BARS=1 -e HF_HUB_ENABLE_HF_TRANSFER=0 \
    -p 7860:7860 athomasson2/ebook2audiobook

Fine Tuned TTS models

Fine Tune your own xtts model

De-noise training data

Fine Tuned TTS Collection

For an XTTS custom model a ref audio clip of the voice reference is mandatory:

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 Formats

• Creates a ['m4b', 'm4a', 'mp4', 'webm', 'mov', 'mp3', 'flac', 'wav', 'ogg', 'aac'] (set in ./lib/conf.py) file with metadata and chapters.

Common Issues:

• CPU is slow (better on server smp CPU) while NVIDIA GPU can have almost real time conversion.
  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 --help parameter at the end of the docker run command for more information.
• “Im getting a truncated audio issue!” - PLEASE MAKE AN ISSUE OF THIS,
  we don’t speak every language and need advise from users to fine tune the sentence splitting logic.😊

What I need help with! 🙌

Full list of things can be found here

• Any help from people speaking any of the supported languages 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
• FFmpeg: FFmpeg Website
• @shakenbake15 for better chapter saving method