THE CRUNCH
Google has released Lyria 3.5, its latest AI music generation model, directly in the Gemini app and via an API. Users can pick a genre and style, choose between vocals and instrumentals, and generate short or longer tracks. Templates for background music and personalised birthday songs are meant to help newcomers get started.
The model is not confined to Gemini: it also appears in Google Flow Music with extra features, in Google AI Studio for developers, and in Google Vids. Google says Lyria 3.5 delivers more expressive vocals and richer arrangements than its predecessor, though that is the company's own assessment.
One claim worth treating carefully: Google says the Lyria model was trained only on licensed content, in a pointed contrast with Suno's music model. It has not shared specifics about what training data it actually used.


