Google launches AI music generation tool on Gemini

Google has upgraded its Gemini AI tool so that it can now generate short pieces of music based on prompts.

Working with AI company DeepMind’s latest audio model, Google’s new Lyria 3 tool can produce 30-second tracks based on images, videos and text descriptions. It’s currently being rolled out for Beta access via Google’s Gemini app, with access only open to users who are aged 18 or older.

The new music-making tool is available globally as of this week, and can understand prompts in English, French, German, Spanish, Hindi, Japanese, Korean, and Portuguese. There are plans to expand its language base in the future.

Lyria 3 can make instrumentals, as well as songs with lyrics, based on user prompts. Users can also upload photographs and video references, which Gemini then uses to produce a track that suits what is going on in the image or video.

“The goal of these tracks isn’t to create a musical masterpiece, but rather to give you a fun, unique way to express yourself,” Google said in a blog announcing the new tool.

The news comes amidst growing global concern around the rise of AI-generated music on streaming platforms. Apple Music, Deezer and Spotify have all sought to remove fraudulent AI “spam” tracks in recent months. Meawhile, Bandcamp recently banned AI-generated music altogether. 

Last year, it was revealed that 60 million people used AI to create music in 2024, according to an IMS Business Report.