Echo-TTS

Echo-TTS is a diffusion-based text-to-speech model.
The weights in this repository are intended for research and non-commercial use only.

• Technical overview/samples (blog): https://jordandarefsky.com/blog/2025/echo/
• Code and reference implementation (GitHub): https://github.com/jordandare/echo-tts

---

License

• Model weights: Released under CC-BY-NC-SA-4.0.
• Code: The reference implementation and tooling live in a separate GitHub repository and are released under MIT (except where individual files specify otherwise).

---

Responsible & Restricted Use

By using this model, you agree not to use it for:

• Deception, fraud, or impersonation, including:
  • Generating audio that mimics a real person’s voice without their explicit consent.
  • Creating deepfakes meant to mislead others about who is speaking.
• Harassment, abuse, or discrimination, including targeted abuse or hate content generated in someone’s voice.
• Misinformation or political manipulation, such as fabricated statements by public figures.
• Any use that violates applicable laws or regulations.

If you are unsure whether your use is allowed, please treat it as not allowed and err on the side of caution.

---