Google Introduces Lyria 3 In Gemini, Bringing AI‑Generated Music To Millions Of Users

Technology company Google announced that it has rolled out Lyria 3 in Gemini, the company’s new AI music‑generation model that allows users to turn a text prompt or photo into customized 30‑second tracks with automatically generated lyrics and cover art. The update introduces the latest version of Google DeepMind’s generative music system directly into the Gemini app, marking its broadest consumer release to date.

Lyria 3 builds on earlier iterations of the model and is designed to give users greater control over musical output. The system can generate lyrics without user input, adjust stylistic elements such as genre, tempo, and vocal tone, and produce more realistic and musically complex audio. Users can describe an idea, memory, or mood, or upload a photo or video, and the model will create a track that reflects the content. The Gemini app produces 30‑second clips accompanied by custom cover art generated by Nano Banana, making the results easy to download or share.

The model supports two primary modes of creation. Text‑to‑track generation allows users to specify a genre or emotional tone to produce a song with lyrics or instrumental audio. Visual‑to‑track generation uses uploaded photos or videos as inspiration for the composition, with the system crafting lyrics that match the imagery. Google positions these features as tools for casual creative expression rather than professional‑grade music production.

Creators on YouTube will also gain access to Lyria 3 through Dream Track for Shorts. The feature, already available in the United States and expanding to additional regions, enables the creation of customized soundtracks for short‑form videos. The model can generate lyrical verses or atmospheric backing tracks, offering creators more flexibility in shaping the audio accompanying their posts.

Google Expands AI Music Oversight With SynthID Watermarking And New Verification Tools

All audio generated in the Gemini app includes SynthID, Google’s imperceptible watermark for identifying AI‑produced content. The app now allows users to upload audio files to check whether they contain SynthID, expanding verification tools that previously applied only to images and video. Gemini will analyze the file and determine whether it was created using Google’s AI systems.

Google emphasizes that Lyria 3 was developed with a focus on responsible use and collaboration with the music industry. The company notes that the model is intended for original expression rather than imitating specific artists. If a prompt references a known performer, the system will generate music inspired by general stylistic elements rather than replicating a particular voice or catalog. Filters are in place to prevent outputs that resemble existing copyrighted works, and users can report content that may infringe on rights. All use of the system remains subject to Google’s Terms of Service and generative AI policies.

Lyria 3 is now available in the Gemini app for users aged 18 and older in English, German, Spanish, French, Hindi, Japanese, Korean, and Portuguese. Google plans to expand language support and improve quality over time. The model is rolling out on desktop immediately and will reach the mobile app in the coming days, with Google AI Plus, Pro, and Ultra subscribers receiving higher usage limits.

The post Google Introduces Lyria 3 In Gemini, Bringing AI‑Generated Music To Millions Of Users appeared first on Metaverse Post.