autiobooks 1.0.3

Automatically convert epubs to audiobooks

Autiobooks: Automatically convert epubs to audiobooks

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

Kokoro is an open-weight text-to-speech model with 82 million parameters. It yields natural sounding output while being able to run on consumer hardware.

It supports American, British English, French, Korean, Japanese and Mandarin (though we only-support English, for now) and a wide range of different voices with different accents and prosody.

PRs are welcome!

Changelog

1.0.1

Initial release

1.0.2

Window can be resized

1.0.3

• Fix bug causing errors on some linux installs
• Read epub files with chapters not marked as ITEM_DOCUMENT
• Select all chapters if none are selected

How to install and run

(Note that pip installs are currently not working - we are looking into the cause of this, but in the meantime, please download the repo and run directly)

If you have Python 3 on your computer, you can install it with pip. Be aware that it won't work with Python 3.13.

pip install autiobooks

You will require ffmpeg and tkinter installed:

Linux:

sudo apt install ffmpeg python3-tkinter

MacOS:

brew install ffmpeg python-tk

To start the program, run:

autiobooks

The program creates .wav files for each chapter, then combines them into a .m4b file for playing using an audiobook player.

Roadmap

In no particular order:

• Windows support
• GPU support (currently untested)
• CI tests - including handling of corner cases and odd epubs
• PDF Support

Author

by David Nesbitt, distributed under MIT license. Check out the excellent project audiblez if you'd prefer a command-line interface.