Client Project: Sounds Studio

AI and music creation come together in this novel cloud-based DAW; now in open beta

Sounds Studio is a a modern music production platform, powered by Artificial Intelligence (AI). The team has been working for a few years on some of the most cutting edge AI models and features in the music space. Most notably their collaboration with media artist Holly Herndon on her project Holly+, a custom voice model made from the artist’s voice and owned by her community. For more on this particular project, you can watch Holly’s TED talk from last year. Recently, Sounds Studio has been creating a Digital Audio Workstation (DAW) to bridge the technical gap for any music producer to use these tools. And after many months they are soft opening their platform, which is still in beta, to anyone.

Now I am no AI expert, but I have had the privilege to work with the Sounds Studio team this year. In the lead up to their beta and continuing through the end of the year, I clean up, workshop, design, and build simple interactions and modules to use the awesome AI tools they have built. It is a rewarding and challenging experience because they are trying to make intuitive tools for novel features. As such, the present interface sits somewhere between Google Drive, Ableton, Figma, and Finder.

In the studio you can drag audio files into your session. You can cut, stretch, crop, fade, and export tracks with a couple of clicks like in other DAWs like Garage Band. But, you can also do things found in no other applications: split tracks into stems, write text prompts that generate full audio tracks, and modulate vocals to tenor or soprano. For the moment, this is totally free.

If you try it out, I would love to hear what you think. Or if you prefer to give feedback directly within the Sounds Studio app, then the whole team can learn from your experience.

—Jono