shijincai/VibeVoice

Archive of the official Microsoft VibeVoice repository (7B & 1.5B). Backup of the deleted source code for the open-source TTS models, including the removed 7B version. Try the VibeVoice online service

44
/ 100
Emerging

This project helps create expressive, long-form conversational audio from text, such as podcasts or multi-speaker dialogues. You provide written text, and it generates natural-sounding speech, capable of handling up to four distinct speakers and up to 90 minutes of audio. It is ideal for content creators, podcasters, or anyone needing to transform written content into high-quality spoken audio.

No commits in the last 6 months.

Use this if you need to generate realistic, multi-speaker conversational audio from text for podcasts, audiobooks, or long-form narrated content.

Not ideal if you require precise control over background music or sound effects, as these can appear spontaneously based on the input text and voice prompts.

podcasting audiobook-creation content-creation speech-synthesis voice-over
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 15 / 25
Community 20 / 25

How are scores calculated?

Stars

27

Forks

27

Language

Python

License

MIT

Last pushed

Sep 05, 2025

Commits (30d)

0

Get this data via API

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

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