Google is expanding the creative capabilities of Gemini, as the AI assistant can now generate 30-second music tracks from simple text prompts. The new feature is powered by Lyria 3, the latest generative music model developed by Google DeepMind, and is rolling out in beta starting today.

Music creation inside the Gemini app is currently available in English, German, Spanish, French, Hindi, Japanese, Korean, and Portuguese. Access is open to users aged 18 and above. However, those subscribed to Google AI Plus, Pro, or Ultra plans will benefit from higher usage limits compared to free-tier users.

Using the feature is straightforward. Users can describe a concept, mood, genre, inside joke, or even a personal memory to generate a custom 30-second track. Alternatively, you can upload a photo or video and ask Gemini to create music inspired by that visual input. The system automatically produces lyrics if needed, meaning you don’t have to write them yourself. For visual presentation, cover art is also generated automatically by Nano Banana, adding a polished touch to each track.

Google emphasizes that the goal of this feature is not to replace professional musicians or produce chart-topping masterpieces. Instead, it’s designed as a creative tool for personal expression and fun social sharing. Whether you want a lo-fi instrumental that matches your late-night vibe or a playful song built around an inside joke, Gemini aims to deliver something unique and personalized.

To ensure transparency, all tracks generated by Gemini are embedded with SynthID, Google’s imperceptible watermarking technology used to identify AI-generated content. The company also notes that the music generation system is built for original expression rather than imitation. If a user includes the name of an existing artist in a prompt, Gemini interprets it as broad stylistic inspiration and produces a track with a similar mood or feel rather than directly copying any specific work.

Google says it has implemented safeguards and filtering systems to compare generated outputs against existing content in order to reduce the risk of infringement. Additionally, users can report any content that may violate their rights or the rights of others.

With this update, Gemini continues its evolution from a conversational AI assistant into a broader creative platform, now capable of generating not just text and images, but also original music on demand.