YouTube on Thursday said it is testing new generative AI features that’ll let people create music tracks using just a text prompt or a simple hummed tune.
The company introduced Dream Track, an experiment on YouTube Shorts which is powered by Google DeepMind’s most advanced music generation model to date, Lyria.
“At this initial phase, the experiment is designed to help explore how the technology could be used to create deeper connections between artists and creators, and ultimately, their fans,” said Lyor Cohen, global head of music at YouTube.
Nine artists including Alec Benjamin, Charlie Puth, Charli XCX, Demi Lovato, John Legend, Papoose, Sia, T-Pain, and Troye Sivan have chosen to collaborate in this experiment and work with YouTube to shape the future of AI in music.
“They are giving a small group of select US creators the chance to create unique soundtracks of up to 30 seconds for their Shorts,” Cohen added.
YouTube is also experimenting with AI tools that can generate music tracks from a hum.
“The artists, songwriters, and producers in the Music AI Incubator are helping us test, learn, gain feedback, and hear ideas so that we can develop the best experiences possible for our community of artists, viewers, and fans,” said the company.
Imagine being able to more seamlessly turn one’s thoughts and ideas into music; like creating a new guitar riff just by humming it or taking a pop track you are working on and giving it a reggaeton feel.
“We’re developing prospective tools that could bring these possibilities to life and Music AI Incubator participants will be able to test them out later this year,” YouTube said.
