Courtesy of DeepMind’s latest audio model, Google has given Gemini the ability to spit out AI-generated music. beta access lyria 3 Gemini is rolling out to the app, enabling users to generate 30-second tracks based on text, images and video without leaving the chatbot window.
The new music-creation tool is available globally starting today in English, German, Spanish, French, Hindi, Japanese, Korean, and Portuguese, with plans to expand in the future. Access is limited to Gemini app users who are 18 years of age or older.
Lyria 3’s text-to-music capabilities allow Gemini app users to create songs by describing specific genres, moods or memories, such as asking for “an Afrobeat track for my mom about the great times we had growing up.” The music generator can create instrumental audio and songs with lyrics written automatically based on user prompts. Users can also upload photos and video references, which Gemini then uses to create a track with lyrics that suits the ambiance.
“The goal of these tracks isn’t to create a musical masterpiece, but to give you a fun, unique way to express yourself,” Google said in its announcement blog.
Gemini will add custom cover art generated by Nano Banana to songs created on the app, intended to make them easier to share and download. Google is also bringing Lyria 3 to YouTube’s Dream Tracks tool, which allows creators to create custom AI soundtracks for shorts.
Dream Tracks and Lyria were initially showcased with the ability to mimic the style and voice of famous artists. Google says it took “great care” about copyright in the development of Lyria 3 and that the tool is “designed not to copy existing artists, but to inspire original expression.” When asked for a specific artist, Gemini will create a track that “shares a similar genre or mood” and uses filters to check the output against existing content.
lyria has been around since 2023, but access to the AI music creator was previously limited to Google Cloud’s Vertex platform. This expansion of the Gemini app makes Lyria more accessible, but lags far behind platforms like TikTok and Microsoft’s Copilot, which have introduced their own AI music creators.
