Google has added Lyria 3.5, its most advanced music generation model yet, to the Gemini app. Previously available through Google's AI filmmaking tool Flow, the model is now rolling out to all Gemini users, making it easier to generate polished songs, instrumentals, and soundtracks from simple text prompts or even photos.
Google says Lyria 3.5 delivers richer arrangements, more expressive vocals, and better prompt comprehension than previous versions. The model builds out full songs with actual verses, choruses, and bridges, rather than just looping a short melodic clip. Inside Gemini, you can pick or describe a genre, choose between vocal or instrumental styles, and decide whether you want a short clip or a longer track. Beginners can use templates to generate background music for videos, custom jingles, or personalized ringtones. Note that once a track is generated, you can't edit it mid-prompt. Google is also making Lyria 3.5 available through the Gemini API for developers.
Lyria 3.5 arrives at a chaotic moment for AI music. AI-generated songs now make up 44% of daily uploads on Deezer, and a large share of streams were later found fraudulent. That's why every Lyria track carries a SynthID watermark - an invisible marker flagging it as AI-generated. Lyria's guardrails block cloning an artist's voice or reproducing copyrighted lyrics, following a recent European court ruling against AI music company Suno. That ruling isn't final and may be appealed, so the legal picture around AI music remains unsettled.
For ordinary users, Lyria 3.5 means the barrier to music creation has been lowered again. You don't need to know music theory or arrangement - just describe what you want and get a complete song. But it also means more "AI-flavored" content in the music market, and the SynthID watermark plus copyright guardrails are attempts to draw boundaries for human creativity in the AI wave.