Google's Gemini has introduced the ability to create 30-second music tracks based on user prompts. This feature is powered by Lyria 3, the latest generative music model from Google DeepMind. The music creation tool is rolling out today in beta through the Gemini app, available in English, German, Spanish, French, Hindi, Japanese, Korean, and Portuguese.
All users aged 18 and older can access this feature, though Google AI Plus, Pro, and Ultra subscribers will benefit from higher usage limits compared to standard users. To create music, you can either describe an idea or upload a photo or video for Gemini to draw inspiration from. Additionally, cover art is automatically generated by Nano Banana.
Google emphasizes that the intention behind these tracks is not to craft musical masterpieces but rather to provide a fun and unique means of self-expression that users can share with friends. You can specify a genre, mood, inside joke, or memory to generate tracks featuring lyrics or instrumental audio that resonate with your style. Notably, the lyrics are also generated automatically, saving you the effort of providing them yourself.
The tracks produced by Gemini incorporate SynthID, Google's invisible watermark designed to identify AI-generated content. Google assures users that the music generation is aimed at fostering original expression rather than imitating existing artists. If a prompt references a specific artist, Gemini will use that as broad creative inspiration to generate a track that captures a similar style or mood.
The company also states that filters are in place to ensure outputs do not infringe on existing content, and users have the option to report any content that may violate their rights or those of others.
Source
