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

Google has expanded the reach of its innovative music generation model, Lyria 3.5, which was initially unveiled just over a month ago. Previously exclusive to Google Flow Music, this advanced model is now accessible through the Gemini app and the Gemini API, allowing users to explore its capabilities across web and mobile platforms.

Enhanced Features for Users

With the introduction of Lyria 3.5 in the Gemini app, users can now select from both short and long music tracks, catering to a variety of creative needs. To further facilitate the creative process, Google has rolled out new templates designed to inspire users and streamline their musical endeavors. This update also simplifies the selection of genres and the choice between vocal and instrumental styles, making it easier than ever for creators to find their unique sound.

At its core, Lyria 3.5 is engineered to deliver richer and more intricate melodic structures. The model demonstrates improved adherence to user prompts, enhanced structural awareness, and better pronunciation. Notably, the vocal outputs are crafted to be more realistic and emotionally nuanced, elevating the overall quality of the generated music.

In addition to its availability in the Gemini app, developers can access Lyria 3.5 through Google AI Studio and Google Vids, further broadening the model’s utility in various creative contexts.

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