 |
| Google Gemini uses Lyria 3 to create 30-second songs, complete with sung vocals and cover artwork. |
Google is transforming its AI platform Gemini into a versatile creative tool. By integrating Lyria 3, developed by Google DeepMind, users can now generate complete songs, including vocals and album cover artwork. As with AI-generated videos, each track is limited to 30 seconds. The feature initially launches in beta and is available to users aged 18 and over in several languages, including English, German, Spanish, French, Hindi, Japanese, Korean, and Portuguese. No separate sign-up is required—access is enabled automatically for eligible accounts as part of a gradual rollout on the web and mobile app.
As with other chatbots, users simply describe what they want, whether it is a genre, a mood, or a specific idea. Google suggests prompts such as "a comical R&B slow jam about a sock finding their match" or "a nostalgic Afrobeat song for my mother." Images or videos can also be uploaded, allowing Lyria 3 to automatically generate matching music. If requested, Gemini can also design a fitting cover using Google’s image model Nano Banana, based on the text prompt or the uploaded content. The result is a compact creative package that includes music, artwork, and a title, which can be downloaded or shared via a link. All generated songs include the invisible SynthID watermark, making AI-generated content identifiable.
What’s new in Lyria 3
Google has been testing its Lyria music model since 2023, including through projects such as YouTube Dream Track and internal trials. Until now, however, it was not integrated into the standard Gemini app. With Lyria 3, music generation is officially available to end users.
Compared with its predecessor, Lyria 3 is designed to produce more realistic and musically complex tracks. It offers greater control over style, tempo, and vocals, and can automatically generate lyrics based on the user’s prompt. According to Google, the goal is not to deliver a flawless musical masterpiece but to support creative self-expression. "The Gemini app creates 30-second tracks with custom cover art generated by Nano Banana. This makes it easy to quickly share with friends by downloading or simply clicking the share link," the company explained in its announcement.
A new way to express yourself: Gemini can now create music
https://blog.google/innovation-and-ai/products/gemini-app/lyria-3/
YouTube integration
Lyria 3 will also be integrated into YouTube Dream Track. Creators will be able to use it to produce custom soundtracks for Shorts. The feature, which was initially limited to the United States, is now rolling out to users worldwide. Google notes that the enhanced quality will allow for better customization, "whether it's creating a lyrical verse or a vibey backing track."
The company also emphasized its commitment to responsible AI development. Music generation is designed for original expression, not mimicking existing artists. If a user's prompt names a specific artist, Gemini will take this as broad creative inspiration and create a track with a similar style or mood. All outputs are checked against existing content, and users must adhere to terms of service that prohibit intellectual property violations. Google AI Plus, Pro, and Ultra subscribers will enjoy higher usage limits as the feature rolls out.
Source(s)
Google