Google recently announced that it’s adding a music-generation feature to the Gemini app.  DeepMind’s Lyria 3 music-generation model is being used to power the feature, which is currently in beta.

AI-Generated Music

Users will simply describe the song they want to create, and the feature will generate a track and lyrics. For instance, you could ask Gemini to create a “comical R&B slow jam about a sock finding its match,” and the app will generate a 30-second track along with cover art.

According to Google, users can even upload a photo or video, and the AI-powered tool will create a song to match the mood of the file. The style, vocals, and tempo of the song can also be changed and controlled by users.

In addition to unveiling Lyria 3 in the Gemini app, Google is also making the model available to YouTube creators through the Dream Track feature, which is a tool that allows creators to make AI-generated tracks. Though this option was previously only available to U.S.-based YouTube creators, Google is expanding its availability globally.

Addititionally, the feature can’t outright mimic a specific artist, if you add an artist’s name to the prompt, Gemini will create a track with a similar mood or style.

“Music generation with Lyria 3 is designed for original expression, not for mimicking existing artists. If your prompt names a specific artist, Gemini will take this as broad creative inspiration and create a track that shares a similar style or mood. We also have filters in place to check outputs against existing content,” the company said in a blog post.

All songs created with the Lyria 3 model will have a SynthID watermark to identify AI-generated content. Google is also adding additional capabilities to identify AI-generated music within Gemini. For example, users will be able to upload tracks and ask Gemini if it’s AI-generated.