Edresson/YourTTS

YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone

45
/ 100
Emerging

Based on VITS architecture, YourTTS adds speaker encoder integration and multilingual training to enable zero-shot adaptation with minimal speaker data (<1 minute of speech). The model decouples speaker identity through pre-computed d-vector embeddings and speaker consistency loss, allowing transfer across languages and low-resource scenarios. Implemented within the Coqui TTS ecosystem, it provides command-line interfaces for both TTS and voice conversion tasks via speaker/reference audio conditioning.

1,052 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

1,052

Forks

97

Language

Jupyter Notebook

License

Last pushed

Nov 04, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/Edresson/YourTTS"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.