XTTS Voice Cloning

This app uses XTTS v2 to clone a voice from a sample and generate speech with that voice.

⚠️ CPU Warning: This is running on a CPU, so generation may take 1-3 minutes. Keep your text short (1-2 sentences) for best results.

Tips for better results:

  1. Use a clear voice recording with minimal background noise
  2. Keep the sample 5-10 seconds long
  3. For faster generation, keep your text very short (1-2 sentences max)
  4. Be patient! CPU generation takes time

License

This app uses the XTTS v2 model under the Coqui Public Model License for non-commercial use only.