Vibeleaderboard
← All Intel
Intel / post

Lyria 3 music generation arrives in the Gemini app

Source
x.com
Date
Google AI@GoogleAI

Today we introduced Lyria 3, @GoogleDeepMind's latest music generation model, which you can use to turn your ideas into musical tracks through prompts or even photos. Here are 3 tips (and fun facts!) to help you make the most out today's launch: 1. We intentionally built this model to have extremely high customization character limits, so you can feel the full freedom of flexibility. From a pithy haiku to an emotional short story, Lyria 3 allows you to lose yourself in the details. 2. Get creative! When designing this model, we wanted to cater a broad and diverse range of musical tastes (not just pop music). Whether it's unique combinations of instruments or blends of seemingly clashing genres, feel free to experiment. 3. When creating a track, you can prompt the style of music and Gemini can suggest lyrics that fit your theme. Or, you could request specific lyrics transforming the most mundane messages into your very own musical. For example, when testing the model, the team found success in creating tracks with critically acclaimed lyrics like "Check your email" or "Please RSVP to my event.” Lyria 3 is rolling out today in beta in the @GeminiApp for 18+ users. Have fun!

Context

Lyria 3, Google DeepMind's music-generation model, lets Gemini users turn an idea or photo into a short musical track. At its February 18, 2026 beta launch, the app generated 30-second tracks, with prompts controlling features such as style, vocals and tempo. It could generate lyrics from the requested theme, reducing the need to begin with a finished song text. Launch explanation.

The announcement's prompting tips also describe supplying specific lyrics or combining instruments and genres. The creative starting point can therefore be either the words themselves or a description of the musical result.

More from Google AI
Recommended reads
Comments

Checking sign-in…

Loading comments…