Musical Innovation: Google’s AI Music Maker Debuts on Gemini App

Google has recently integrated DeepMind’s latest audio model into its Gemini app, allowing users to create AI-generated music. This new feature, called Lyria 3, enables users to generate 30-second tracks based on text, images, and videos without leaving the chatbot window.

The music-making tool, Lyria 3, is now accessible globally in English, German, Spanish, French, Hindi, Japanese, Korean, and Portuguese. This feature is exclusive to users of the Gemini app who are 18 years or older.

Lyria 3 allows Gemini app users to create songs by describing specific genres, moods, or memories. Users can request personalized tracks such as an “Afrobeat track for my mother about the great times we had growing up.” The music generator can produce instrumental audio and songs with automatically composed lyrics based on user input.

Google emphasizes that the goal of these tracks is not to create professional masterpieces but to provide users with a fun and unique way to express themselves creatively.

Gemini will automatically add custom cover art, created by Nano Banana, to the songs made on the app. This feature aims to facilitate sharing and downloading of the tracks. Additionally, Google plans to integrate Lyria 3 with YouTube’s Dream Track tool for creating custom AI soundtracks for Shorts.

Google assures users that Lyria 3 is designed for original expression and not for mimicking existing artists. The tool uses filters to ensure outputs do not infringe on existing content. Gemini will create tracks in a similar style or mood when prompted for a specific artist.

Previously limited to Google Cloud’s Vertex platform, Lyria has now been expanded to the Gemini app, making AI-generated music more accessible to users. Despite this expansion, Google is catching up to platforms like TikTok and Microsoft’s Copilot, which introduced their own AI music makers earlier.