vorojar/VibeVoice

Open-source AI audiobook studio. A free, private alternative to ElevenLabs. 3 voice modes, per-sentence voice & emotion control, LLM smart character analysis, mixed-voice generation. Runs 100% locally on your GPU with zero API costs.

24
/ 100
Experimental

This is an AI audiobook studio that helps authors, publishers, or content creators convert written text into natural-sounding audiobooks. You input a script or manuscript, and it generates audio narration with customizable voices and emotions for each sentence. The primary users are individuals or small teams looking to produce audio content like audiobooks, podcasts, or narrated articles without cloud service costs.

Use this if you need fine-grained control over voice and emotion for different characters and narration in an audiobook, prefer a free and private solution, and have a local GPU.

Not ideal if you require real-time streaming audio generation, need extensive language support beyond the 10 offered, or lack a powerful local GPU for processing.

audiobook-production voice-narration content-creation podcast-production digital-publishing
No License No Package No Dependents
Maintenance 10 / 25
Adoption 5 / 25
Maturity 3 / 25
Community 6 / 25

How are scores calculated?

Stars

14

Forks

1

Language

JavaScript

License

Last pushed

Feb 20, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/vorojar/VibeVoice"

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