+0
日增长
8,881
stars
773
forks
43
watchers
47
prs
101
issues
0
releases
README
Audiblez: Generate audiobooks from e-books !PyPI - Python Version !PyPI - Version v4 Now with Graphical interface, CUDA support, and many languages! !Audiblez GUI on MacOSX 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: bash sudo apt install ffmpeg espeak-ng on Ubuntu/Debian 🐧 pip install audiblez bash 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 | Language | Voices
Top issues
#55audiblez-ui doesn't work on Windows?13 comments · 2025-02-10#80Audiblez ignores EPUB TOC and splits chapters by HTML10 comments · 2025-02-26#61v4 in windows, cuda is missing again8 comments · 2025-02-12#71RuntimeError: espeak not installed on your system7 comments · 2025-02-19#83When a Chinese paragraph exceeds 200 characters, the programme usually only recognises the first 120-130 characters.6 comments · 2025-03-02#65Is it possible to generate the audiobooks in lossless formats?6 comments · 2025-02-14#123uvx --python=3.13 audiblez --help fails on macOS5 comments · 2025-08-29#52Will it provide convert txt or md file to mp3 function later?5 comments · 2025-02-08
Discussions
#156Can we get a find / find+replace function with ctrl+F and ctrl+H?0 comments · 2026-09-13#152Can i add another language?0 comments · 2026-07-13#144Request: Dutch support0 comments · 2026-05-19#139Fast alternative TTS: Supertonic0 comments · 2026-03-14#129Vocabulary for specific words or abbreviations0 comments · 2025-10-22#113.m4b didn't play on any android audiobook player for me (VLC played them) - fix0 comments · 2025-07-10#99Save on-going audiblez session to reopen later0 comments · 2025-05-12#87macos sonoma & brew 4.4.23 & python 3.13.2 - pip install audiblez => no go0 comments · 2025-03-11