# vibevoice-community/VibeVoice

VibeVoice: Expressive, longform conversational speech synthesis. (Community fork)

Repository: https://github.com/vibevoice-community/VibeVoice
Canonical: https://ross.abutalabs.com/products/vibevoice-community-vibevoice
Homepage: https://discord.gg/ZDEYTTRxWG
Language: Python
License: MIT
License Family: permissive
Last push: 2026-08-08T01:13:53+00:00

## Health v2 (maintenance only)
Score: 60/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 96, release rhythm 35, longevity 25
- inputs: {"age_days": 363, "days_push": 26, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1542, forks 704 (observed 2026-08-28T04:05:00.632665+00:00)

## What it is
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
- artifact type: library
- maturity: active
- function: tts, speech-recognition, machine-learning, llm-inference, audio-processing
- domain: speech-processing, artificial-intelligence, deep-learning, large-language-models
- platform: python, cross-platform
- tags: text-to-speech, voice-cloning, podcast-generation, multi-speaker, long-form-audio, fine-tuning, diffusion, community-fork, audio, gpu

## Member repositories
- vibevoice-community/VibeVoice (main) score 60

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:00.632665+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:30:46.138798+00:00, confidence not recorded.
  - readme: https://github.com/vibevoice-community/VibeVoice (fetched 2026-08-28T04:05:00.632665+00:00, sha 2f669801d2a2)
  - homepage: https://discord.gg/ZDEYTTRxWG (fetched 2026-08-29T11:32:10.464086+00:00, sha 01c5e03464ba)
- Data as of 2026-08-30T08:39:29.467469+00:00.