santinic/audiblez

Audiblez: Generate audiobooks from e-books

v4 Now with Graphical interface, CUDA support, and many languages!

Audiblez generates .m4b audiobooks from regular .epub e-books, using Kokoro's high-quality speech synthesis.

Kokoro-82M is a recently published text-to-speech model with just 82M params and very natural sounding output. It's released under Apache licence and it was trained on < 100 hours of audio. It currently supports these languages: 🇺🇸 🇬🇧 🇪🇸 🇫🇷 🇮🇳 🇮🇹 🇯🇵 🇧🇷 🇨🇳

On a Google Colab's T4 GPU via Cuda, it takes about 5 minutes to convert "Animal's Farm" by Orwell (which is about 160,000 characters) to audiobook, at a rate of about 600 characters per second.

On my M2 MacBook Pro, on CPU, it takes about 1 hour, at a rate of about 60 characters per second.

How to install the Command Line tool

If you have Python 3 on your computer, you can install it with pip. You also need espeak-ng and ffmpeg installed on your machine:

sudo apt install ffmpeg espeak-ng                   # on Ubuntu/Debian 🐧
pip install audiblez

brew install ffmpeg espeak-ng                       # on Mac 🍏
pip install audiblez

Then you can convert an .epub directly with:

audiblez book.epub -v af_sky

It will first create a bunch of book_chapter_1.wav, book_chapter_2.wav, etc. files in the same directory, and at the end it will produce a book.m4b file with the whole book you can listen with VLC or any audiobook player. It will only produce the .m4b file if you have ffmpeg installed on your machine.

How to run the GUI

The GUI is a simple graphical interface to use audiblez. You need some extra dependencies to run the GUI:

sudo apt install ffmpeg espeak-ng 
sudo apt install libgtk-3-dev        # just for Ubuntu/Debian 🐧, Windows/Mac don't need this
  
pip install audiblez pillow wxpython

Then you can run the GUI with:

audiblez-ui

How to run on Windows

After many trials, on Windows we recommend to install audiblez in a Python venv:

1. Open a Windows terminal
2. Create anew folder: mkdir audiblez
3. Enter the folder: cd audiblez
4. Create a venv: python -m venv venv
5. Activate the venv: .\venv\Scripts\Activate.ps1
6. Install the dependencies: pip install audiblez pillow wxpython
7. Now you can run audiblez or audiblez-ui
8. For Cuda support, you need to install Pytorch accordingly: https://pytorch.org/get-started/locally/

Speed

By default the audio is generated using a normal speed, but you can make it up to twice slower or faster by specifying a speed argument between 0.5 to 2.0:

audiblez book.epub -v af_sky -s 1.5

Supported Voices

Use -v option to specify the voice to use. Available voices are listed here. The first letter is the language code and the second is the gender of the speaker e.g. im_nicola is an italian male voice.

For hearing samples of Kokoro-82M voices, go here

For more detaila about voice quality, check this document: Kokoro-82M voices

How to run on GPU

By default, audiblez runs on CPU. If you pass the option --cuda it will try to use the Cuda device via Torch.

Check out this example: Audiblez running on a Google Colab Notebook with Cuda .

We don't currently support Apple Silicon, as there is not yet a Kokoro implementation in MLX. As soon as it will be available, we will support it.

Manually pick chapters to convert

Sometimes you want to manually select which chapters/sections in the e-book to read out loud. To do so, you can use --pick to interactively choose the chapters to convert (without running the GUI).

Help page

For all the options available, you can check the help page audiblez --help:

usage: audiblez [-h] [-v VOICE] [-p] [-s SPEED] [-c] [-o FOLDER] epub_file_path

positional arguments:
  epub_file_path        Path to the epub file

options:
  -h, --help            show this help message and exit
  -v VOICE, --voice VOICE
                        Choose narrating voice: a, b, e, f, h, i, j, p, z
  -p, --pick            Interactively select which chapters to read in the audiobook
  -s SPEED, --speed SPEED
                        Set speed from 0.5 to 2.0
  -c, --cuda            Use GPU via Cuda in Torch if available
  -o FOLDER, --output FOLDER
                        Output folder for the audiobook and temporary files

example:
  audiblez book.epub -l en-us -v af_sky

to use the GUI, run:
  audiblez-ui

Author

by Claudio Santini in 2025, distributed under MIT licence.

Related Article: Audiblez v4: Generate Audiobooks from E-books