Google DeepMind just dropped Lyria 3.5 into its Google Flow Music platform, bringing upgrades to musicality, lyrics, vocals, and creative control.
Here’s the thing: while crypto-native projects have spent years promising decentralized music platforms and on-chain royalty systems, one of the world’s largest tech companies is quietly building the future of music creation with zero blockchain involvement. That strategic omission says something.
What Lyria 3.5 actually does
The Lyria family of models has evolved quickly. Lyria 3, which launched on February 18, 2026, let users generate 30-second high-fidelity music tracks from text or image prompts through the Gemini app. Users had to be 18 or older to access it.
Lyria 3 Pro followed on March 25, 2026, expanding capabilities to full songs up to three minutes long. That version introduced structural coherence, meaning tracks could include proper intros, verses, choruses, and bridges instead of sounding like a random assemblage of musical ideas.
