Wednesday, February 18, 2026
Google search engine
HomeTechnologyGoogle Gemini adds Lyria 3, an AI model that can create music...

Google Gemini adds Lyria 3, an AI model that can create music using words and photos

Google is once again expanding Gemini’s multimodal capabilities. Following the success of viral image generator Nano Banana, the company is launching Lyria 3, an AI model that can generate music. According to Google, you can start with your words and describe what kind of music you want to create and the model will match that.

Alternatively, you can feed in an image or even a video and Lyria 3 will generate a “high-fidelity track” with custom lyrics in tow. “From fun jingles to lo-fi beats, you can create custom 30-second soundtracks for every moment,” the company says. Lyria 3 is already rolling out to the desktop version of Gemini, which you can access via a web browser. In the coming days, it will also be expanded to the Gemini mobile app for users around the world.

Introducing Lyria 3, our new music generation model in Gemini that allows you to transform any idea, photo or video into a high-fidelity track with custom lyrics.

From fun jingles to lo-fi beats, you can create custom 30-second soundtracks for every moment.

See how it works.

– Google Gemini (@GeminiApp) February 18, 2026

What is Lyria 3 in Gemini?

Lyria was developed by Google’s DeepMind division, which is at the forefront of AI research to drive innovative innovation and research, such as using Gemini 3 Deep Think to convert sketches and ideas into 3D printing files. DeepMind is also behind SynthID technology, which can add an invisible watermark to 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 choose any topic, idea, genre, or mood and Gemini will create a 30-second example for you. All you need to do is click on the tool selector in the Gemini chat box and select the “New Music” option.

2) Image or video to tracks:

Upload a photo or video and watch Gemini analyze the content to compose a title with lyrics that match the mood.

For example, you might say, “Use these photos to create a trail about my dog ​​Duncan hiking in the woods.”

– Google Gemini (@GeminiApp) February 18, 2026

How does it work?

Just like creating images or videos with Google’s Veo engine, Lyria 3 takes your words, images or videos and creates a suitable melody from them. If you’re running out of creative ideas, there are plenty of templates where you can choose an existing title and modify it using prompts. It’s a bit like tweaking Gemini Gems or remixing mini apps built in the Nothing Playground ecosystem.

Lyria 3 in Gemini is free to use, in case you were wondering. I imagine many people share their photos and videos to create a suitable background track for posting on social media. Google won’t be the first company to offer this convenience. Suno is the biggest name in the AI ​​music generation segment and has sparked numerous controversies over alleged copyright infringements.

RELATED ARTICLES

LEAVE A REPLY

Please enter your comment!
Please enter your name here

- Advertisment -
Google search engine

Most Popular

Recent Comments