MUSIC WRITTEN BY teams, David Byrne once wrote, is arguably more accessible than that written by a sole composer. Collaborations, he mused, may result in more “universal” sentiments. But what if your partner isn’t human at all, but artificial intelligence? Now music producers are enlisting AI to crank out hits.
Created by Sony’s Computer Science Laboratories, Flow Machines analyzes tracks from around the world, then suggests scores that artists—including electropop musician ALB and jazz vocalist Camille Bertault—interpret into songs. For its debut album, Hello World, the AI also surveyed syllables and words from existing music to create original (albeit gibberish) vocals.
Recommended track: The Beatles-inspired “Daddy’s Car“
Jukedeck was originally developed to compose background tracks for user-generated videos; now it’s being adopted by K-pop stars like Kim Bo-hyung and Highteen. Using deep neural networks, the AI predicts note sequences to compose brand new songs. After users select parameters such as mood, genre, and beats per minute, the AI cranks out a track that artists can embellish.
Recommended track: Highteen’s ultra-processed hit “Digital Love“
The Artificial Intelligence Virtual Artist, aka Aiva, combs through the works of composers such as Bach, Beethoven, and Mozart and uses the principles of music theory to make predictions and generate musical models. The program, developed by computer scientist Pierre Barreau, reconfigures those models into an original piece and arranges new sheet music.
Recommended track: “Among the Stars,” in the style of composer John Williams
Landr automates the audio mastering process in minutes. The AI compares nearly finished tracks to a database of 7 million already mastered singles and tweaks each song based on previous adjustments. By processing the tracks as a batch, Landr hones a unified sound.
Recommended track: R&B single “Your World,” produced by Kosine