Google Integrates Music Creation Feature into Gemini App

Google announced on Wednesday that it is introducing a music generation feature to its Gemini app. This new capability is powered by DeepMind's Lyria 3 music generation model and is currently in beta.

To create a song, users simply describe what they want. The app will then generate a track complete with lyrics. For example, you could ask Gemini to compose a "comical R&B slow jam about a sock finding its match," and it will produce a 30-second song along with cover art created by Nano Banana.

Google also stated that users can upload a photo or video, and the AI tool will craft a song to match the mood of that media.

Loading the player…

The company highlighted that Lyria 3 represents a significant improvement over previous models, producing more realistic and complex music. Users have additional control to adjust elements like style, vocals, and tempo.

In addition to launching Lyria 3 in Gemini, Google is making the model available to YouTube creators globally through the Dream Track feature, a tool for generating AI music tracks. Previously, this option was limited to creators in the U.S.

Google clarified that the tool is not designed to mimic specific artists. If a user includes an artist's name in their prompt, Gemini will use it as broad creative inspiration to generate a track in a similar style or mood. (It remains unclear if this could make it easier to decode a particular artist's musical 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.

Google noted that all songs created with Lyria 3 will include a SynthID watermark to identify them as AI-generated. The company is also adding capabilities within Gemini to detect AI-generated music using SynthID, allowing users to upload tracks and ask if they were AI-created.

The music generation feature is rolling out worldwide to all Gemini users aged 18 and over, with support for English, German, Spanish, French, Hindi, Japanese, Korean, and Portuguese.

The rise of AI-generated music has sparked mixed reactions. While platforms like YouTube and Spotify are embracing AI and striking deals with labels to monetize such content, AI companies face lawsuits from the music industry over copyright issues related to training data. Other services, like Deezer, have released tools to label AI-generated music to prevent fraudulent streaming.