Wispr Flow-Now on Android!
Mini toolsLyria 3
By Google
Lyria 3 is Google DeepMind’s latest generative music model, available in the Gemini app, that generates 30-second songs from user prompts. Google describes it as improving musical quality and control, including automatic lyric generation and options to steer style, vocals, and tempo, and it generates matching cover art for tracks with sharing options. Audio outputs are embedded with SynthID watermarking, and Gemini’s verification features are expanded to include audio detection.
New
Audio
Gen 3
Overview
Lyria 3 is Google DeepMind’s music generation model that lets Gemini app users create 30-second tracks from text prompts or from uploaded photos and video.
About Google
At Google, we think that AI can meaningfully improve people's lives and that the biggest impact will come when everyone can access it.
View Company Profile
Last updated: February 25, 2026
