Google is adding music creation capabilities to the Gemini app

Google announced on Wednesday that it is adding a music creation feature to the Gemini app. The company is using DeepMind’s Lyria 3 music generation model to power the feature, which is still in beta.

To use this feature, you have to describe the song you want to create, and the app will create a track with the lyrics. For example, you can ask Gemini to create a “slow R&B comedy jam about finding a sock that matches,” and the app will create a 30-second track along with cover art designed by Nano Banana.

You can also upload a photo or video, and the AI-powered tool will create a song to match the mood of the media file, Google said.

Lyria 3 improves on the previous generation of models, creating more realistic and complex music pieces, the company said. Users can also change and control other elements such as style, vocals, and tempo.

Along with rolling out Lyria 3 on the Gemini app, Google is making the model available to YouTube creators through YouTube’s Dream Track feature, a tool that helps creators create AI-generated tracks. This option has only been available to YouTube creators in the US until now. But with this release, Google is expanding the availability of Dream Track globally.

Google said you can’t completely imitate an artist, but if you add an artist’s name to your claim, Gemini will create a track in a similar style or mood. (It is not clear whether generation would make it easier for others to decode a particular artist’s musical style.)

“Generating music with Lyria 3 is designed for original expression, not to imitate existing artists. If your claim references 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 the output against existing content,” the company said in a blog post.

Google has noted that all songs created with the Lyria 3 model will have a SynthID watermark to identify AI-generated content. The company said it is also adding capabilities to identify AI-generated music using SynthID within Gemini. Users will be able to upload audio clips and ask Gemini if ​​they were created by artificial intelligence.

Music Generation is rolling out to all Gemini users over the age of 18 worldwide with support for English, German, Spanish, French, Hindi, Japanese, Korean and Portuguese.

AI-generated music has created mixed feelings among artists and listeners. On the one hand, companies like YouTube and Spotify are embracing AI and signing contracts with music labels to monetize AI-generated music. On the other hand, AI modeling and tools companies are facing lawsuits from the music industry over copyright of training materials. Platforms like Deezer have deployed AI-generated music tagging tools to curb fraudulent streams of this type of music.