Uberduck Logo

What is this?

This is Uberduck. It's a synthetic speech toy. I started working on Uberduck in 2020 with the goal of creating a friendly, creative, open-ended dialog agent. I built an interactive audio chatbot over WebRTC that generated text responses with a Transformer model and synthesized them to audio, but I found that speech synthesis was the most exciting part of the project.

Contributing

You can help create synthetic voices by creating datasets and models. Join the Discord to learn how.

Why "Uberduck"?

It's a pun on  rubber duck debugging.

Horizon

I'm constantly working to improve the site. Here are a few things in the pipeline that I'm really excited about:

  • Better vocal synthesis and additional synthetic voices
  • Models that sing, rap and emote
  • Models with phoneme-level duration control
  • Voice conversion
  • User accounts, bookmarks and shortlinks for audio you create with Uberduck
  • Discord bot improvements

If you don't see a feature that you like on this list or have other ideas for what Uberduck should do, please email quack@uberduck.ai. Or Twitter at me. Or Discord at me. The duck will listen.