Google has given Gemini the ability to spit out AI-generated music, courtesy of DeepMind’s latest audio model. Beta access to Lyria 3 is rolling out in the Gemini app, enabling users to generate 30-second tracks based on text, images, and videos, without having to leave the chatbot window.
The new music-making 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 or older.
Lyria 3’s text-to-music capabilities allow Gemini app users to make songs by describing specific genres, moods, or memories, such as asking for an “Afrobeat track for my mother about the great times we had growing up.” The music generator can make instrumental audio and songs with lyrics composed automatically based on user prompts. Users can also upload photographs and video references, which Gemini then uses to generate a track with lyrics that fit the vibe.
“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 its announcement blog.
Gemini will add custom cover art generated by Nano Banana to songs created on the app, which aims to make them easier to share and download. Google is also bringing Lyria 3 to YouTube’s Dream Track tool, which allows creators to make custom AI soundtracks for Shorts.
Dream Track and Lyria were initially demonstrated with the ability to mimic the style and voice of famous performers. Google says it’s been “very mindful” of copyright in the development of Lyria 3 and that the tool “is designed for original expression, not for mimicking existing artists.” When prompted for a specific artist, Gemini will make a track that “shares a similar style or mood” and uses filters to check outputs against existing content.
Lyria has been around since 2023, but access to the AI music maker was previously limited to Google Cloud’s Vertex platform. This expansion to the Gemini app makes Lyria more accessible, but arrives significantly behind platforms like TikTok and Microsoft’s Copilot introducing their own AI music makers.