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
· Updated
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.
