AI-generated music has been in the spotlight lately, between a track that seemingly featured vocals from Drake and The Weeknd gaining traction to Spotify reportedly removing thousands of songs over concerns that people were using them to game the system. Now, Google is wading further into that space as the company is opening up access to its text-to-music AI, which is called MusicLM.
Google detailed the system back in January when it published research on MusicLM. At the time, the company said it didn’t have any plans to offer the public access to MusicLM due to ethical concerns related to copyrighted material, some of which the AI copied directly into the songs it generated.
The generative AI landscape has shifted dramatically this year, however, and now Google feels comfortable enough to let the public try MusicLM. “We’ve been working with musicians like Dan Deacon and hosting workshops to see how this technology can empower the creative process,” Google Research product manager Hema Manickavasagam and Google Labs product manager Kristin Yim wrote in a blog post.
As TechCrunch points out, the current public version of MusicLM doesn’t allow users to generate music with specific artists or vocals. That could help Google to avoid copyright issues and stop users from generating fake “unreleased songs” from popular artists and selling them for thousands of dollars.
You can now sign up to try MusicLM through AI Test Kitchen on the web, Android and iOS. Google suggests that you can try prompts based on mood, genre and instruments, such as “soulful jazz for a dinner party” or “two nylon string guitars playing in flamenco style.” The experimental AI will generate two tracks and you can identify your favorite by selecting a trophy icon. Google says doing so will help it to improve the model.
Follow all of the news from Google I/O 2023 right here.