Google brings AI music generation directly into the Gemini app with its new Lyria 3.5 model
decoder ·
Google has launched its Lyria 3.5 music generation model, making it available directly in the Gemini app and via API. According to Google, this version offers more expressive vocals and richer musical arrangements than its predecessor. In the Gemini app, users can select genre and style, choose between vocals and instrumentals, and generate tracks of varying lengths. To help newcomers, templates for background music and personalized birthday songs are provided. Beyond Gemini, Lyria 3.5 is also integrated into Google Flow Music, Google AI Studio for developers, and Google Vids. Google states that, unlike Suno's model, Lyria was trained exclusively on licensed content, though it has not disclosed details about the specific training data used.
decoder