Google DeepMind
@GoogleDeepMind
We just dropped Lyria 3: our latest generative music model. 🔊 It can turn photos and text into dynamic tracks - complete with vocals and lyrics. 🧵
231retweets
View on XLyria 3 Brings AI Music Generation with Lyrics to the Gemini App
Google DeepMind· Updated
Google DeepMind's Lyria 3 is live in the Gemini app - describe a mood or upload a photo and get a 30-second track with AI-generated lyrics and vocals. It's Lyria's first wide public release after two years of controlled experiments.
Lyria 3, Google DeepMind's music generation model, is now live in the Gemini app. Describe a genre and mood, upload a photo, or both - Gemini generates a 30-second track with auto-written lyrics, vocals, and custom cover art. You control tempo and vocal style. Every output is embedded with SynthID, Google's invisible watermark for AI-generated audio.
Three upgrades over earlier Lyria versions: lyrics generate automatically from your prompt, controls over tempo and vocal style are granular, and tracks are musically more complex. YouTube creators can also access Lyria 3 through Dream Track for custom Shorts soundtracks, rolling out globally.
It's in beta now, free in the Gemini app for users 18+ across eight languages — open it, describe a vibe, and generate your first track. If you create YouTube Shorts, Dream Track puts the same capability directly in the YouTube workflow.
Every HeadsUpAI update is written based on its original source and reviewed before it's published. Read our editorial standards →
