Google’s Lyria 3: AI Music Generation Comes to Gemini

Google has integrated its latest AI music generation model, Lyria 3, directly into the Gemini app, empowering users to create 30-second songs from simple text prompts, images, or videos. The global rollout of this feature began on February 18, 2026, and is available to Gemini users aged 18 and older, initially on desktop platforms with mobile access arriving shortly thereafter .

Lyria 3: Democratizing Music Creation

Lyria 3 allows users to generate short music tracks by describing a theme, mood, or concept. The system automatically produces multiple elements of a song, including audio, lyrics, and accompanying artwork. Generated outputs include a 30-second music track, AI-generated lyrics based on user prompts, and cover art created using Google’s Nano Banana image generation tool .

Evolution of Google’s Lyria Music Model

Google first introduced the Lyria model in 2023 and subsequently applied the technology to YouTube experiments, such as Dream Track, which enabled creators to generate short background music clips for YouTube Shorts. Lyria 3 represents a significant advancement over earlier versions, introducing automatic lyric generation, increased control over musical style and vocals, and more complex and realistic audio output .

Google has confirmed that Dream Track will also transition to the Lyria 3 model, though the company has not yet specified whether creators will be able to generate tracks exceeding the current 30-second limit .

Multilingual Support and Accessibility

At launch, Lyria 3 supports multiple languages, including English, German, Spanish, French, Hindi, Japanese, Korean, and Portuguese, with plans to incorporate additional languages in the future . The feature is available to Google Workspace customers, Workspace Individual subscribers, and users with personal Google accounts who are 18 years or older and signed in to the Gemini app .

Copyright and Responsible AI

Google emphasizes that Lyria 3 is designed to foster original musical creation rather than direct replication of existing artists. When users reference a specific musician or style in a prompt, Gemini generates music inspired by similar characteristics, rather than reproducing identifiable works. Filtering systems are in place to prevent outputs from closely resembling copyrighted songs, although Google acknowledges that these safeguards are not foolproof and encourages users to report any potential copyright concerns .

Implications for Creators and Users

The integration of Lyria 3 into Gemini lowers the barrier to music creation, allowing users to generate short audio tracks without requiring specialized production software. While the current 30-second limitation positions the feature primarily for short-form content, such as social media clips and video projects, it reflects a broader industry trend toward embedding generative AI tools directly into consumer platforms, expanding creative capabilities beyond text and image generation .