ToolsSeptember 6, 2026via The Decoder
Google brings AI music generation directly into the Gemini app with its new Lyria 3.5 model
Why it matters
Google is shipping generative music as a core Gemini feature, not a separate product. Practitioners building creative workflows can now integrate music generation into existing LLM-powered apps; for enthusiasts, this signals how Google is bundling frontier model capabilities into its main consumer and developer platform.
Key signals
- Lyria 3.5 released in Gemini app, via API, Flow Music, AI Studio, and Google Vids
- Model trained only on licensed content (addressing rights concerns)
- Promises more expressive vocals and richer arrangements than prior versions
- Multi-platform availability suggests broad rollout, not limited beta
- Lyria 3.5 model now integrated into Gemini app
- Also available via API, Flow Music, AI Studio, Google Vids
- Claimed improvements: more expressive vocals, richer arrangements
- Trained on licensed content (legal/licensing stance stated)
- Multi-product distribution strategy (app + API + dedicated music tools)
The hook
Google embeds music generation directly into Gemini. Lyria 3.5 is now live for all users—and available via API.
Google has released its Lyria 3.5 music model in the Gemini app and via API. The model promises more expressive vocals and richer arrangements and is also available through Flow Music, AI Studio, and Google Vids. Google says it was trained only on licensed content.