Gemini hands Lyria 3.5 the mic as the music model makes its debut on the app

Google introduced its latest music generation model, Lyria 3.5, a little over a month ago. At the time of the announcement, the model was only available in Google Flow Music. Now you’ll be able to access Lyria 3.5 in a couple more places.

Starting today, Lyria 3.5 is available in the Gemini app and the Gemini API. That means you’ll now find the model on the web, mobile, and Flow Music. Developers also have access to the model in Google AI Studio and Google Vids.

With the launch of Lyria 3.5 on the Gemini app, Google says you’ll now be able to choose between short and long tracks. New templates have been added as well, in case you need some inspiration on where to start. This rollout also makes it easier to select or describe your genre and choose between vocal or instrumental styles.

As a brief overview of what Lyria 3.5 brings to the table, the model was designed to produce richer and more complex melodic structures. It better adheres to prompts, is more structurally aware, and improves upon pronunciation. And vocals are supposed to be more realistic and emotionally nuanced.