Gemini app rolling out music generation for all with Lyria 3

Following text, audio overviews, images, and video, the Gemini app’s latest output is music with Lyria 3. 

Lyria 3 is Google DeepMind’s “most advanced music generation model.” Compared to earlier iterations, you no longer have to add your own lyrics as Google automatically generates them based on your prompt. The model now offers control over style, vocals, tempo, and other elements, while offering the ability to create “more realistic and musically complex tracks.”

This model and feature are “designed for original expression, not for mimicking existing artists.” Google says it has been “very mindful of copyright and partner agreements” during training. As such, if you specify an artist in the prompt, “Gemini will take this as broad creative inspiration and create a track that shares a similar style or mood.” There are also “filters in place to check outputs against existing content.”

We recognize that our approach might not be foolproof, so you can report content that may violate your rights or the rights of others. 

In the Gemini app, the “Tools” menu adds “Music.” Your prompt can “describe a specific genre, mood, inside joke, or memory to create unique tracks with lyrics or instrumental audio.” For example:

Advertisement – scroll for more content

• “I’m feeling nostalgic. Create a track for my mother about the great times we had as kids and the memories of her home cooked plantains. Make it a fun afrobeat track with a true African vibe.”

Another way to prompt is by uploading a photo or video clip that Gemini can use to “compose a track with lyrics that fit the mood perfectly.”

• “Use these photos to create a track about my dog Duncan on a hike in the woods.”

The end result is a 30-second track with Nano Banana leveraged to generate custom cover art. You can share by downloading the file or getting a link. 

On the safety front, all tracks are embedded with the SynthID watermark. You can upload an audio file to Gemini and ask if it was generated using Google AI. This joins image and video verification. 

Lyria 3 in the Gemini app is currently available “for all users 18+ in English, German, Spanish, French, Hindi, Japanese, Korean, and Portuguese.” Google AI Plus, Pro, and Ultra subscribers will have higher limits. 

In the future, Google will expand to more languages and “expand quality.”