Google has released Lyria 3.5, its most advanced AI music generation model, in the Gemini app, Google AI Studio and via API, expanding access beyond the earlier Google Flow Music platform. The model can produce complete song structures with verses, choruses and bridges in high-fidelity 44.1kHz stereo audio, rather than looping a short melody. Google says Lyria 3.5 improves on melodic complexity, prompt adherence and vocal realism compared with earlier versions, and users can select genre, vocal style and templates when generating tracks.
