Finrandojin/alexandria-audiobook

AI-powered multi-voice audiobook generator — LLM script annotation, voice cloning, voice design, LoRA training, per-line style control, and export to MP3, chaptered M4B, or Audacity multi-track. Built on Qwen3-TTS.

50
/ 100
Established

Integrates with any OpenAI-compatible LLM API (LM Studio, Ollama, OpenAI) for automatic script annotation, runs Qwen3-TTS locally with optional batch compilation via `torch.compile`, and exports to MP3, chaptered M4B, or Audacity multi-track with per-speaker WAV separation. Features a browser-based editor with selective chunk regeneration, LoRA voice fine-tuning, and context-aware smart chunking (up to 500 chars per speaker, preserving character roster across segments).

371 stars.

No Package No Dependents
Maintenance 13 / 25
Adoption 10 / 25
Maturity 11 / 25
Community 16 / 25

How are scores calculated?

Stars

371

Forks

37

Language

Python

License

MIT

Last pushed

Mar 15, 2026

Commits (30d)

0

Get this data via API

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

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