sergenes/runandread-audiobook

🚀 Open-source project for creating high-quality AI TTS-narrated audiobooks at home using models like Zonos, Kokoro-82M, or services like Deepgram and Eleven Labs. Tested on Apple Silicon M1 (32GB RAM). 📖🎧

49
/ 100
Emerging

# Technical Summary Implements an end-to-end pipeline that converts EPUB files to structured JSON, synthesizes audio using local models (Zonos, Kokoro via MLX) or cloud APIs (Deepgram, OpenAI), and supports voice cloning from MP3 samples before packaging into a RANDR ZIP format for the Run & Read mobile app. Features resumable batch processing (tolerates interruption), ffmpeg-based audio merging, and CLI playback with synchronized text display. Targets cross-platform deployment (macOS/Linux/Windows) with optimized inference on Apple Silicon via MLX framework.

No Package No Dependents
Maintenance 10 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

57

Forks

9

Language

Python

License

MIT

Last pushed

Feb 03, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/sergenes/runandread-audiobook"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.