Audiblez is a tool for generating high-quality .m4b audiobooks directly from .epub e-books using the Kokoro-82M neural text-to-speech model. It focuses on making audiobook creation easy and fast: from a single command, the tool splits an e-book into chapters, synthesizes audio for each section, and then merges the results into a structured audiobook with chapter-based WAV files and a final .m4b container. The Kokoro-82M model it uses is compact (82M parameters) yet natural sounding, trained on under 100 hours of audio, and supports multiple languages, including English (US/UK), Spanish, French, Hindi, Italian, Japanese, Brazilian Portuguese, and Mandarin Chinese. Audiblez can run entirely from the command line via a PyPI package or through a simple cross-platform GUI built on wxPython, giving both advanced users and non-technical users an accessible workflow.
Features
- Converts .epub e-books into chaptered .m4b audiobooks using Kokoro-82M TTS
- Command-line interface with options for voice selection, speed, GPU usage, and output folder
- Simple GUI (audiblez-ui) built with wxPython for users who prefer a visual interface
- Multilingual voice support across many Kokoro voices and languages (EN, ES, FR, HI, IT, JA, PT-BR, ZH)
- Interactive chapter-picking mode to convert only selected sections of a book
- CPU and CUDA GPU support with performance optimized for both local machines and Colab-style environments