An open source research project exploring the role of machine learning as a tool in the creative process.

There are times in life when you find a tool that open up a whole new palette of possibilites. This was the case for me with Magenta.
Powered by the massive and free library for machine learning in JavaScript TensorFlow.js. Magenta is freely distributed in in two flavours: as an open source Python library or as an open source JavaScript API for using the pre-trained Magenta models in the browser.

Magenta will help you get started making music and art with machine learning, and give you some resources if you want to explore on your own.

Check for example: Beatblender

Or Magenta Studio, a collection of music plugins, that can be integrated into Ableton, built on Magenta’s open source tools and models.

Drumbot lets you play real-time music with a Machine Learning drummer that drums based on your melody.

The Google Experiment A.I. Duet lets you play a duet with the computer. Just play some notes, and the computer will respond to your melody.

Or take it one step further with Fruit Genie: