Google DeepMind Releases Lyria 3 Music Generator
Google DeepMind is rolling out Lyria 3, a generative music model, in beta today within the Gemini app, producing 30-second tracks with auto-generated lyrics and Nano Banana cover art. The release includes SynthID audio watermarking, verification tools, and YouTube Dream Track integration, and supports eight languages and higher limits for Google AI Plus/Pro/Ultra subscribers. Gemini will roll out on desktop today and to mobile over the next several days.
Key Points
- 1Launches Lyria 3 generative music model producing 30-second tracks with auto-generated lyrics and cover art
- 2Includes SynthID watermark and verification tool to identify Google AI-generated audio, images, and videos
- 3Enables creators to customize style, vocals, tempo; available in eight languages with YouTube integration
Scoring Rationale
Official Google release with significant generative-audio novelty and creator integration; limited by short 30-second clips and initial language coverage.
Practice interview problems based on real data
1,625 SQL & Python problems across 15 industry datasets — the exact type of data you work with.
Try 250 free problems
