vibevoice-community/VibeVoice

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1542 stars · 704 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

VibeVoice is a community-maintained fork of Microsoft's long-form conversational text-to-speech model, generating expressive multi-speaker audio such as podcasts for up to 90 minutes with up to 4 speakers. It uses continuous speech tokenizers and a next-token diffusion LLM framework, with community-added fine-tuning and voice cloning support.

Use cases

• generate a podcast from a multi-speaker script
• synthesize long-form conversational audio with consistent voices
• fine-tune a TTS model on a new language or voice
• clone a voice for speech synthesis
• run real-time streaming text-to-speech
• create audiobook narration with multiple characters

When to choose

• you need expressive multi-speaker conversational TTS beyond a few minutes
• you want to fine-tune or voice-clone an open TTS model
• you need podcast-style audio generation from text

When to avoid

• you need lightweight on-device TTS without a GPU
• you need only short single-phrase synthesis
• you require official vendor support rather than a community fork

Facets

library · maturity active

tts speech-recognition machine-learning llm-inference audio-processing speech-processing artificial-intelligence deep-learning large-language-models python cross-platform text-to-speech voice-cloning podcast-generation multi-speaker long-form-audio fine-tuning diffusion community-fork audio gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="vibevoice-community/VibeVoice")