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

Lyria 3 is now available on desktop, and will be rolling out to the Gemini mobile app in the coming days.

By Nadeem Sarwar Published February 18, 2026

Making music with Gemini Lyria 3. — Google/DigitalTrends

Google is expanding the multimodal capabilities of Gemini, once again. Following the success of the viral Nano Banana image generator, 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.

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.

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

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

See how it works. 🧵
— Google Gemini (@GeminiApp) February 18, 2026

What is Lyria 3 in Gemini?

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.

Recommended Videos

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.

2) Image or Video to Tracks:

Upload a photo or video and watch Gemini analyze the content to compose a track with lyrics that fit the vibe.

For example, you could prompt, “Use these photos to create a track about my dog Duncan on hikes in the woods.”
— Google Gemini (@GeminiApp) February 18, 2026

How does it work?

Just like image generation, or making videos in using Google’s Veo engine, Lyria 3 will take your words, images, or videos, and create a fitting tune. If you are running out of creative ideas, there are plenty of templates where you can pick an existing track and modify it using prompts. It’s somewhat like tweaking Gemini Gems or remixing mini-apps created in the Nothing Playground ecosystem.

Using Lyria 3 in Gemini is free, in case you are wondering. I can imagine a lot of people sharing 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 courted plenty of controversy for alleged copyright infringement.

Managing Editor

Nadeem is the Managing Editor at Digital Trends.

Topics

Computing

Google Earth’s AI misadventure lasted only a day. It was a tale of dangerous ignorance.

Nuclear reactors, tanks, and historical destruction on a life-like satellite map? Yeah, that's bad.

Nano Banana AI image generator representation.

Technology behemoths are clearly not reading the room, or they are just moving faster than they should when it comes to AI deployment. Google has already stuffed its Gemini AI in every corner of its software stack, from Android to daily productivity tools like Gmail that are used by hundreds of millions of users every day. AI is everywhere. Not all of it is bad, mind you. But in a few places, it just feels forced.

In its latest AI-fication experiment, the company targeted Google Earth. The idea was to let the audience use its Nano Banana 2 AI image generator and make images that can be placed on the map view. On paper, it's a cool idea. What would the Colosseum of Rome look like in your urban neighborhood? Yeah, fun stuff like that.

Computing

AMD is apparently gearing up to raise GPU prices right after Nvidia’s steep hike

AMD has reportedly told AIB partners about a price hike that goes into effect in. August.

AMD RX 7800

AMD is next in line to raise the asking price of its Radeon GPUs, merely days after the news of a similar hike coming for Nvidia graphics cards started making waves. As per ChannelGate on Weibo (h/t VideoCardz), AMD has informed its board partners that the price of GPU and memory bundles will go up by at least 10% in August.

Is a similar price hike coming for standalone graphics cards? I won't be surprised if that happens. The situation is so bad that AMD is planning to bring back graphics cards with 4GB of onboard memory. AMD just introduced the RX 9050 GPU, which costs $279. Notably, it's just $20 less than the RX 9060 XT that offers double the graphics memory.

Computing

Microsoft will make Windows work well with just 8GB RAM. We desperately need it

The dream of a reliable and affordable Windows laptop hinges on the next milestone at Microsoft.

Surface laptop on wooden table

The year 2026 has marked a huge course correction for Microsoft after years of frustrating users with plenty of confusing processes, unoptimized UI elements, and just the generous bloatware that can bring any Windows system to a crawl. Microsoft has finally shifted into a new phase. From fixing the right-click behavior to speeding up the Search system, the company has fixed plenty of papercuts.

The next major milestone is making Windows 11 run smoothly on Windows PCs with just 8GB of RAM. That directly means entry-level and budget laptops will at least get the basics right, even if that means sacrificing the on-device AI bells and whistles. Let's face it. The increasingly AI-first approach to computing on a Windows 11 machine is a little too taxing on the hardware at hand.