Google has introduced a new AI-powered music generation feature in its Gemini app, powered by DeepMind’s latest model, Lyria 3.
With this update, users can now ask Gemini to create original 30-second music tracks simply by typing a prompt that describes what they want. Users can also upload an image or video to help set the mood for the song. The tool interprets text descriptions such as genre, mood, or theme and then generates a complete track with instrumental sounds and lyrics.
In addition to the music, the feature creates custom cover art for each track using Google’s Nano Banana image model. It also embeds an AI watermark known as SynthID, allowing people to identify that the content was generated by artificial intelligence.
In a Google Workspace update blog titled “Create custom soundtracks with Lyria 3 in the Gemini app,” the company stated that users who already have access to the Gemini app will automatically receive access to Lyria 3. “To get started, select ‘Create music’ from the tools menu,” the blog noted.
The music generation feature is currently in beta and is available on the Gemini app for both desktop and mobile devices. It supports multiple languages, including English, German, Spanish, French, Hindi, Japanese, Korean, and Portuguese, and is available to users aged 18 and above. Subscribers to Google AI Plus, Pro, and Ultra plans are given higher usage limits.
Google is also integrating Lyria 3 into YouTube’s Dream Track tool, enabling creators to generate custom soundtracks for Shorts and other video content. The company said the feature is designed for fun and personal creative expression, not professional music production, and includes safeguards to avoid copying specific artists’ work.
