Google has integrated its latest music generation model, Lyria 3.5, into the Gemini consumer application, Google Flow Music, Google Vids, and Google AI Studio for developers. According to the company, Lyria 3.5 generates richer arrangements and more expressive vocal tracks compared to previous iterations. Gemini users can generate customizable tracks by specifying genre, vocal preferences, or selecting pre-built templates for background audio.
Google emphasized that Lyria 3.5 was trained exclusively on licensed content, explicitly contrasting its approach with competitors such as Suno. However, the company has not publicly detailed the exact datasets or royalty structures supporting the training corpus. The rollout expands AI audio creation tools across Google’s consumer and enterprise productivity ecosystems.
Why it matters
Brings native AI audio and music generation directly to consumer users within the mainstream Gemini app interface.
Emphasizes licensed training data as a competitive differentiator against standalone music AI startups facing copyright litigation.
Expands Google’s multimodal API ecosystem by making music generation available to enterprise developers via Google AI Studio.
Source: the-decoder.com
