Google has introduced Lyria 3, its most advanced generative music model, to the Gemini app, enabling users to create 30-second songs using simple text prompts, photos, or videos.
The feature, developed by Google DeepMind, allows users to generate short tracks within seconds by describing an idea or uploading an image for inspiration. The app can produce lyrics, instrumentals, and cover art automatically, giving users a quick way to create and share personalized audio clips.
According to the company, Lyria 3 improves on earlier versions by generating lyrics automatically, offering greater control over style, vocals, and tempo, and producing more realistic and musically complex compositions.
Users can create songs by describing a mood, memory, or genre — for example, requesting an Afrobeat track inspired by childhood memories — or by uploading images or videos that the app uses to shape the song’s lyrics and tone. Each track includes custom cover art generated by Google’s Nano Banana image system and can be shared via download or link.
Read Also: Google unveils two Gemini’s new AI-powered features
Google said creators can also access Lyria 3 through Dream Track on YouTube, where the technology is being integrated to enhance soundtracks for Shorts videos. The feature is currently available in the United States and expanding to creators in other countries.
To address authenticity and transparency concerns, Google said all audio generated in Gemini is embedded with SynthID, a digital watermark designed to identify AI-generated content. Users can also upload audio files to check whether they were created using Google’s AI tools.
The company said it has worked with the music community to develop the technology responsibly and emphasized that Lyria 3 is intended for original creative expression rather than replicating specific artists’ voices or works. Filters are in place to detect similarities with existing content, and users can report potential rights violations.
Lyria 3 is now available in the Gemini app for users aged 18 and above in multiple languages, including English, Spanish, French, Hindi, Japanese, Korean, German, and Portuguese, with broader language support planned. Subscribers to Google AI Plus, Pro, and Ultra tiers will receive higher usage limits.
