Harmonai is a deep learning research lab focused on creating open-source generative audio models,
supporting researchers and developers with compute grants and community, and providing musicians and audio engineers with new creative tools.

Harmonai’s mission is to create open-source audio generation and manipulation tools to make music production more accessible and fun for everyone.

 - Join the conversations in the Harmonai Play server - Use the tools we provide to create new sounds, and share your creations with the community
 - Fork our sample generator GitHub repo or the Dance Diffusion notebook, and make your own changes to it

- Dance Diffusion is a family of generative audio diffusion models that we've released publicly.
 The initial models generate around 1-3 seconds of audio,
 and can also be used to perform interpolations and style transfer on longer audio clips.