# myshell-ai/OpenVoice

Instant voice cloning by MIT and MyShell. Audio foundation model.

Repository: https://github.com/myshell-ai/OpenVoice
Canonical: https://ross.abutalabs.com/products/openvoice
Homepage: https://research.myshell.ai/open-voice
Language: Python
License: MIT
License Family: permissive
Topics: text-to-speech, tts, voice-clone, zero-shot-tts
Last push: 2025-04-19T16:00:00+00:00

## Health v2 (maintenance only)
Score: 34/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 17, release rhythm 35, longevity 72
- inputs: {"age_days": 1008, "days_push": 501, "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 37312, forks 4175 (observed 2026-08-28T04:12:01.408400+00:00)

## What it is
OpenVoice is a Python library and audio foundation model for instant voice cloning, requiring only a short reference audio clip to replicate a speaker's tone color. It supports zero-shot cross-lingual text-to-speech and granular control over voice styles such as emotion, accent, rhythm, and intonation.

## Use cases
- clone a voice from a short audio clip
- generate speech in another language with a cloned voice
- control emotion and accent of generated speech
- build a text-to-speech app with custom voices
- dub content into multiple languages with one voice
- run free commercial TTS without API costs

## When to choose
- you need instant zero-shot voice cloning from a short sample
- you want cross-lingual TTS where the target language isn't in the training set
- you need MIT-licensed TTS free for commercial use
- you want granular control over emotion, accent, rhythm, and intonation

## When to avoid
- you need a fully managed hosted TTS API with SLA
- you lack GPU resources for local inference
- you need the highest possible audio fidelity over cloning speed
- you require languages beyond the natively supported set without a reference clip

## Facets
- artifact type: library
- maturity: active
- function: tts, speech-recognition, machine-learning, deep-learning, audio-processing
- domain: speech-processing, artificial-intelligence, machine-learning
- platform: python, cross-platform
- tags: voice-cloning, zero-shot-tts, text-to-speech, audio-foundation-model, cross-lingual, mit-license, audio, gpu

## Member repositories
- myshell-ai/OpenVoice (main) score 34

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:01.408400+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 2026-08-29T16:25:38.633117+00:00, confidence not recorded.
  - readme: https://github.com/myshell-ai/OpenVoice (fetched 2026-08-28T04:12:01.408400+00:00, sha 50dc90520360)
  - homepage: https://research.myshell.ai/open-voice (fetched 2026-08-29T07:47:14.807939+00:00, sha 0bcef4de0115)
- Data as of 2026-08-30T08:39:29.467469+00:00.