There’s a new way to soundtrack your life — and it only takes a prompt.
On , Gemini introduced custom music generation within its app, powered by Lyria 3, Google DeepMind’s latest generative music model. The feature, currently in beta, allows users to create 30-second original tracks by simply typing a description or uploading an image.
Imagine requesting a “comical R&. B slow jam about a sock finding its match” – now, that can actually exist.
From text to track in seconds
Lyria 3 enables users to describe a genre, mood, memory, or even an inside joke, and Gemini will transform it into a fully produced 30-second song, complete with generated lyrics if desired. Feeling nostalgic? A prompt like “Create a fun afrobeat track about my mother’s home-cooked plantains and our childhood memories” will yield a custom audio clip ready for download or sharing within seconds.
If lyrics aren’t needed, Lyria 3 will generate them automatically based on the provided idea.
More control, more complexity
Gemini states that Lyria 3 represents an advancement over its previous music models in three key areas:
- Auto-generated lyrics based on the user’s prompt.
- Greater creative control over style, vocals, and tempo.
- More realistic and musically complex tracks.
Users can also upload photos or videos to inspire a track. For example, sharing a photo of a dog on a hike will prompt Gemini to compose a song that matches the mood, complete with lyrics.
Each 30-second track includes custom cover art generated by Nano Banana, facilitating easy sharing via download or link.
The intention isn’t to produce the next chart-topping single, but to provide a fun, expressive way for users to create their own personalized soundtracks.
Shorts creators, take note
Beyond the Gemini app, Lyria 3 is also enhancing YouTube’s Dream Track for Shorts creators in the U.S., with plans for expansion to other countries. Creators will have more precise control over customizing soundtracks for their Shorts, potentially improving the overall quality of short-form content through lyrical verses and vibey backing tracks.
Built with guardrails
All music generated within the Gemini app is embedded with SynthID, Google’s imperceptible watermark designed to identify AI-generated content. The app also allows users to upload audio files to determine if they were created using Google AI.
Gemini emphasizes that Lyria 3 was developed in collaboration with the music community, with careful consideration given to copyright and partner agreements. The tool is intended for original expression, not replication of existing artists. If a user includes an artist’s name in a prompt, Gemini interprets it as broad inspiration in terms of style or mood, rather than direct imitation.
Users are required to adhere to Gemini’s Terms of Service and generative AI policies.
Who can use it?
Music generation with Lyria 3 is available to Gemini app users aged 18 and above who use English, German, Spanish, French, Hindi, Japanese, Korean, and Portuguese. The rollout is beginning on desktop, with mobile access expected in the coming days.
Subscribers to Google AI Plus, Pro, and Ultra will receive higher usage limits.
For anyone who has ever wanted to transform a memory, meme, or mood into a song, a 30-second soundtrack may be just a prompt away. The feature is available now at gemini.google.com.
