Skip to main content

Google's art machine just wrote its first song

Google's art machine just wrote its first song

Share this story

Today, Google's newest machine learning project released its first piece of generated art, a 90-second piano melody created through a trained neural network, provided with just four notes up front. The drums and orchestration weren't generated by the algorithm, but added for emphasis after the fact.

It's the first tangible product of Google's Magenta program, which is designed to put Google's machine learning systems to work creating art and music systems. The program was first announced at Moogfest last week.

"We believe this area is in its infancy"

Along with the melody, Google published a new blog post delving into Magenta's goals, offering the most detail yet on Google's artistic ambitions. In the long term, Magenta wants to advance the state of machine-generated art and build a community of artists around it — but in the short term, that means building generative systems that plug in to the tools artists are already working with. "We’ll start with audio and video support, tools for working with formats like MIDI, and platforms that help artists connect to machine learning models," the team wrote in an announcement. "We want to make it super simple to play music along with a Magenta performance model."

Magenta is built on top of Google's TensorFlow system, which is already open-source, and the new project also plans to publish its code as open-source on GitHub. "We believe this area is in its infancy, and expect to see fast progress here," the announcement says.

It's not the first time Google has experimented with machine-generated art. The company's DeepDream algorithm — initially developed to visualize the actions of neural networks — has become a popular image tool in its own right and the basis for a gallery show earlier this year. Google also developed the Artists and Machine Intelligence program to sponsor further collaborations along the same lines.

The game of chat bots