Edresson/YourTTS

Health v2 · maintenance only

Flags: no_license

Adoption not part of the score

1053 stars · 97 forks observed · 2026-08-28

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

YourTTS is a zero-shot multi-speaker text-to-speech and voice conversion model built on VITS, implemented in the Coqui TTS framework. It supports multilingual synthesis, voice cloning from short reference clips, and fine-tuning with under a minute of speech.

Use cases

• clone a voice from a short audio sample
• synthesize speech in a target speaker's voice from text
• convert speech from one voice to another
• build TTS for low-resource languages
• fine-tune a TTS model with less than a minute of data

When to choose

• you need zero-shot multi-speaker TTS or voice conversion
• you want to clone voices from minimal reference audio
• you work with low-resource languages and need multilingual TTS
• you want a research-grade model integrated with Coqui TTS

When to avoid

• you need a production-ready, actively maintained TTS pipeline
• you want a simple plug-and-play API without ML setup
• you need fullband commercial-quality English-only synthesis
• you require a permissively licensed model

Facets

library · maturity maintenance

tts speech-recognition machine-learning deep-learning speech-processing machine-learning artificial-intelligence python cross-platform zero-shot-tts voice-conversion vits speech-synthesis voice-cloning research-model coqui-tts gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="Edresson/YourTTS")