Magenta, the research project within Google that explores the role of machine learning in the process of creating art and music, has developed a machine learning algorithm that uses a deep neural network to learn the characteristics of sounds, called NSynth.
After the release of NSynth, Magenta created NSynth Super in collaboration with Google Creative Lab, a hardware to control the algorithm which gives musicians the ability to make music using completely new sounds generated by the NSynth. It doesn’t generate notes, but rather, the actual sound of an instrument.
The NSynth Super features a central X/Y pad, allowing users to morph between four different sounds assigned to each corner of the pad, and it can be played via any MIDI source. The device is not for sale but the directions for building your own are available on Github.
Check out the videos about NSynth and NSynth Super below.