NSynth Super

  • Mary Leonard

How can you make machine learning an accessible tool for musicians to create music?

NSynth Super is an experimental, open-source instrument that allows musicians to make music using previously unheard sounds generated by machine learning.

Using NSynth Super, musicians have the ability to explore more than 100,000 sounds generated with the NSynth algorithm. The aim of the experiment was to translate the machine learning algorithm from a white paper into something accessible, approachable and helpful for musicians — a synthesizer.
We needed to design an interface and product form that visualize the generated sounds and provide an intuitive way for musicians to navigate them.
NSynth Super is built using open source libraries, including TensorFlow and openFrameworks, to enable a wider community of artists, coders, and researchers to experiment with machine learning in their creative process.

The open-source version of the NSynth Super prototype including all of the source code, schematics, and design templates are available for download on GitHub.
NSynth Super was launched at Google I/O 2018 through a live performance that was streamed by over 4 million people globally. For this event, we created a live data visualisation which reacted in realtime to the musician's performance.

NSynth Super has been honoured with numerous awards including a D&AD Yellow Pencil for Product Design.
Learn more about NSynth Super at nsynthsuper.withgoogle.com