The Gemini music generator is here, and I think this is where everyday AI gets fun
What you need to know
- Gemini now generates 30-second songs with words from text commands or images.
- Google’s Lyria 3 model enables feature, word processing, style control, and realistic sound.
- Type in information or upload a photo/video, and Gemini turns it into a song ready to share with custom cover art.
The Gemini app goes beyond text and images. Starting today, it wants to write your next song.
Gemini introduced music generation in beta, using Lyria 3, Google DeepMind’s new music production model. This means you can now create a 30 second track with lyrics in seconds, just by providing information or a picture.
Google says Lyria 3 improves on previous versions in three main ways: it can automatically generate lyrics, it lets you control style, vocals, and tempo more closely, and it creates tracks that sound more realistic and layered. In simple words, you don’t have to be a songwriter. Just describe the vibe, like “happy afrobeat on mom’s cooking” or “a funky R&B jam about a lonely sock,” and you’ll get a polished little track in return.
Photo or video to follow
You can also upload a photo or video, and Gemini will turn that moment into a song with the same lyrics. For example, a picture of your dog hiking can be a forest song with words. The app even creates custom cover art using Nano Banana, so your track is ready to share right from the app.
Since its launch, Gemini has added more creative tools, from photos to video. Music is the next step. However, Google is not trying to replace Spotify or Hit Maker. The goal is to create a fun way to add music to your everyday life without using complicated software or hiring a producer.
There is also something for creators. Lyria 3 comes to Dream Track on YouTube Shorts, which premiered in the US and was broadcast worldwide. This means you can get better, more customizable backing tracks and shorter video clips, which is important as sound can really affect engagement.
Of course, AI music raises copyright concerns. Google says Lyria 3 has been carefully trained in copyright and partner agreements, and is designed for original expression, not copying. When talking about a certain artist, Gemini uses it as inspiration, not as a direct guide. There are filters to check existing content, and users can report possible violations.
Each track produced includes SynthID, Google’s invisible watermark for identifying AI-generated content. Gemini’s authentication tools now work with audio, so you can upload a file and ask if it’s made with Google AI. The program checks the SynthID and uses its analysis before responding.
Lyria 3 is now available on the Gemini app for users 18 and older, in several languages such as English, German, Spanish, French, Hindi, Japanese, Korean, and Portuguese. It’s launching on desktop first, with mobile coming soon. Google AI Plus, Pro, and Ultra subscribers have higher usage limits.
Android Central Take
Personally, I think this is one of the most effective AI changes we’ve seen. Not because it will replace artists – it won’t – but because it lowers the barrier to artistic expression in a way that feels playful instead of intimidating. If you’ve ever wanted a custom birthday song, a theme for your group chat, or a quirky song to post on Short, now you can find one in seconds. For users, that means innovation on demand, and that’s a compelling direction for AI to take.
