With Lyria 3, Google DeepMind’s latest generative music model, Google’s Gemini creates 30-second music tracks based on prompts. The music creation will unveil in beta in the Gemini app in English, German, Spanish, French, Hindi, Japanese, Korean, and Portuguese. It’s accessible to anyone above 18.
Subscribers of Google AI Plus, Pro, and Ultra, will enjoy higher usage. You can access it by uploading a photo or video, then asking Gemini to take inspiration from it. Nano Banana automatically generates cover art.
According to Google, the goal of the tracks is to have fun in a unique way as you express yourself among friends. The feature also allows you to create tracks with lyrics or instrumental audio that fit your vibe. This happens when you describe a specific genre, mood, inside joke or memory. You don’t need to provide the lyrics as they will be automatically generated too.
These Gemini-generated tracks are embedded with SynthID, Google’s imperceptible watermark for identifying Google AI-generated content. Gemini creates a track that has a similar style or mood, if your prompt names an artist.
The feature comes with filters. These filters check outputs against existing content. Though you can report content that is likely to violate your rights.
