Google are creating entire new sounds with their new synthesiser created using machine learning technologies.

The NSynth Super is a new algorithm based neural synthesiser created by Google using their powerful machine learning technologies. The NSynth Super is capable of creating over 100,000 new sounds which can be played from any MIDI source.

The NSynth Super works from a source of 16 original sounds at a range of 15 pitches. It’s machine learning is then capable of re-imagining and combining these samples in entirely new ways to create thousands of different possibilities. It works as simply as selecting the source sound and then dragging your finger across the touchscreen to navigate through new sonic possibilities as the synth alters various elements of it’s parameters.

The synthesiser has been created as part of Google’s machine learning research project Magenta which created the original NSynth last year. The original made use of their past research in machine learning and music to create an unparalleled understanding of sounds based on deep neural networks. The NSynth Super brings this power into the hands of musicians everywhere, making it capable of being used as an instrument.

Google say: “New sounds are powerful. They can inspire musicians in creative and unexpected ways, and sometimes they might go on to define an entirely new musical style or genre. It’s impossible to predict where the new sounds generated by machine learning tools might take a musician, but we’re hoping they lead to even more musical experimentation and creativity.”

The NSynth Super has been created with an entirely open source library so that creators and musicians alike can access all of the schematics, source codes, and design templates free for download on GitHub.

Find out more here: