A new era of music creation has begun on the Google Gemini platform

Google Gemini can now generate 30-second music tracks based on user prompts. The feature is powered by Google DeepMind’s latest generative music model, Lyria 3. It is currently available in beta within the Gemini app and supports English, German, Spanish, French, Hindi, Japanese, Korean, and Portuguese.

Anyone over the age of 18 can use the tool, while AI Plus, Pro, and Ultra subscribers benefit from higher usage limits. To create music, users simply describe an idea or upload a photo or video for inspiration. The cover artwork is generated automatically by Nano Banana.

Google emphasizes that the goal is not to create a musical masterpiece, but to offer a fun and unique way for users to express themselves. You can specify a genre, mood, inside joke, or memory to generate tracks with lyrics or instrumentals. The lyrics are also created automatically, so there’s no need to provide your own.

All tracks generated by Gemini are embedded with SynthID, Google’s invisible watermarking technology for identifying AI-generated content. The company states that the system is designed for original expression rather than imitating existing artists. If a specific artist is mentioned in a prompt, Gemini interprets it as broad creative inspiration and produces a track with a similar style or mood. Google also uses filters to compare outputs with existing content and allows users to report potential rights violations.