The company is releasing Lyria 3, an AI model that can generate music. Google says you can get started with your words and describe what kind of music you want to generate, and the model will comply, El.kz cites Digital Trends.

Alternatively, you can feed it a picture or even a video, and Lyria 3 will generate a “high-fidelity track,” with custom lyrics in tow. “From funny jingles to lo-fi beats, you can create custom 30-second soundtracks for any moment,” says the company. Lyria 3 is already rolling out to the desktop version of Gemini, which you can access in a web browser. It will also be expanding to the Gemini mobile app for users in the coming days across the globe.

Lyria has been developed by Google’s DeepMind division, which is at the frontier of pushing AI for cutting-edge innovations and research, such as using Gemini 3 Deep Think for turning sketches and ideas in 3D printing files. DeepMind is also behind the SynthID tech that puts an invisible watermark on media generated by AI tools.

With Lyria 3, Google is diving into a fun and controversial side of AI usage. The idea is pretty simple. You can pick any topic, idea, genre, or mood, and Gemini will create a 30-second sample for you. All you have to do is click on the tool picker in the Gemini chat box and select the new music option.