In this project we combine techniques from neural voice cloning and musical instrument synthesis to achieve good results from as little as 16 seconds of target data.

• Colab where you can play with pretrained models.

• Blogpost with audio examples.

• Preprint of paper (under review at DAFX 2022)

Preprint coming soon.

Note that this is very much research code 🗑

Also check out https://github.com/magenta/ddsp which our project builds upon.