Gemini can now create music: Check features, supported languages, and how to use Lyria 3

Google has launched Lyria 3, an AI model that generates 30-second music tracks from text or media. Key features include automatic lyrics, control over musical elements, and integration with YouTube, enhancing creators' ability to produce unique soundtracks.

Aman Gupta
Published19 Feb 2026, 03:22 PM IST
Gemini can now created 30 second music using Lyria 3
Gemini can now created 30 second music using Lyria 3(REUTERS)

Google has introduced a new custom music generation model called Lyria 3. The new AI model from Google DeepMind can help users generate custom 30-second musical tracks using text prompts, photos, or videos.

"Just describe an idea or upload a photo, like “a comical R&B slow jam about a sock finding their match" and in a matter of seconds, Gemini will translate it into a high-quality, catchy track. To push the creative envelope further, you can even ask Gemini to take inspiration from something you upload." Google explained in a blogpost

What is Lyria 3? What can it do?

Google says Lyria 3 three primary improvements over the previous generation. First, the model can now automatically generate lyrics based on prompts by the user. Second, the model also provides granular control over elements like tempo, vocals, and style. Third, users can now create more musically complex and realistic tracks with Lyria 3.

Lyria 3 inside the Gemini app can generate 30-second audio clips along with custom cover art created by the company's Nano Banana image model. Additionally, Lyria 3 is being integrated into YouTube’s Dream Track, allowing creators to generate custom soundtracks for YouTube Shorts.

Google says all audio generated using Lyria 3 comed embedded with SynthID, the companys' imperceptible watermark for identifying AI-generated content. The tech giant says it is giving users more tools to to help verify AI content by expanding Gemini's verification capabilities to include an audio check tool to check for SynthID.

Google says Lyria 3 music generation is designed for original expression and not for mimicking artists. In order to address copyright concerns, if a specific artist is named, Gemini will only take ‘broad creative inspiration’ regardng style and mood. The tech giant says it has also placed filters in place to check for the outputs against existing contnet.

“We recognize that our approach might not be foolproof, so you can report content that may violate your rights or the rights of others.” the company said,

How to use Lyria 3?

In order to use Lyria 3, users can either descrie a specific genre, mood, or scenario to create tracks with custom lyrics or instrumental audio.

Alternatively, they can also upload a photo or video from their library and then allow Gemini to use that content to compose a track with lyrics that fits the mood perfrects.

Gemini Lyria 3 availability:

Lyria 3 is available in Gemini app to users aged 18 and older in English, German, Spanish, French, Hindi, Japanese, Korean, and Portuguese. While the feature is free to use, Google says AI Plus, Pro and Ultra tier users will have higher limits.

About the Author

Aman Gupta is a Digital Content Producer at LiveMint with over 3.5 years of experience covering the technology landscape. He specializes in artificial...Read More

Catch all the Technology News and Updates on Live Mint. Download The Mint News App to get Daily Market Updates & Live Business News.

Business NewsTechnologyNewsGemini can now create music: Check features, supported languages, and how to use Lyria 3
More