XTTS v2

Restricted

Coqui · XTTS · Released 2023-11

466MAudio

A widely-used voice-cloning TTS model that can clone a voice from just a few seconds of audio across 17 languages, but non-commercial by default.

Strengths

  • +Zero-shot voice cloning from a short audio clip
  • +17-language support with cross-language cloning
  • +Small enough to run on a single consumer GPU

Limitations

  • -Coqui Public Model License is non-commercial without a separate commercial agreement
  • -Voice cloning quality varies with reference audio quality

License

Coqui Public Model License 1.0.0 (non-commercial)

research/non-commercial - check before shipping

Hardware

runs on a good consumer GPU (or Apple Silicon) with quantization

Links

Stats

coqui/XTTS-v2— downloads·— likes

via Hugging Face

Related models