Echo-TTS

Jordan Darefsky, 2025. See technical details here

License Notice: All audio outputs are subject to non-commercial use CC-BY-NC-SA-4.0.

Responsible Use: Do not use this model to impersonate real people without their explicit consent or to generate deceptive audio.

  1. Upload or record a short reference clip (or leave blank for no speaker reference).
  2. Pick a text preset or type your own prompt.
  3. Click Generate Audio.
๐Ÿ’ก **Tip:** If the generated voice does not match the reference, enable "Force Speaker" and regenerate.

Speaker Reference

Audio Library (click to load)


Text Prompt


Generation

Sampler Preset

Load preset configurations

Speaker KV Attention Scaling

Enable to more strongly match the reference speaker (though higher values may degrade quality)

Format