myshell-ai/OpenVoice

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

37312 stars · 4175 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

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

library · maturity active

tts speech-recognition machine-learning deep-learning audio-processing speech-processing artificial-intelligence machine-learning python cross-platform voice-cloning zero-shot-tts text-to-speech audio-foundation-model cross-lingual mit-license audio gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="myshell-ai/OpenVoice")