And finally, the Magenta project has a long history of contributing to the open-source community and I am very proud to be part of a team that continues to put artists, researchers and all-round creative experimentation at the forefront.

And better yet, it opens the way to accessible on-device generation and customisation (more on this in the coming weeks!), two aspects that are crucial to music making with AI models.

I’m particularly excited about this as it’s the only open model that enables streaming audio generation with real-time controls creating what feels like a genuinely new paradigm that is both fun and musically inspiring

More technical details to come in a paper soon, but in the meantime you can jump right into it: t.co/bFkJiDAYVl

Thanks for this! Would love to be added too :)