Google is giving Gemini a new creative twist. The company has added music generation to its AI app, letting users produce 30-second tracks from simple prompts. The feature runs on Lyria 3, the latest generative music model from Google DeepMind.
Music creation starts rolling out today in beta inside the Gemini app. It will be available in English, German, Spanish, French, Hindi, Japanese, Korean, and Portuguese. Anyone over 18 can try it. However, Google AI Plus, Pro, and Ultra subscribers will receive higher usage limits than free users.
Using the tool is simple. You can describe an idea in text or upload a photo or video for inspiration. Gemini then creates a short track based on your input. It can produce music with lyrics or instrumental audio, depending on what you request. You can mention a specific genre, mood, inside joke, or memory. Gemini will shape the sound to match that vibe. It also writes the lyrics automatically, so you do not need to provide them.
Google says the goal is not to craft a chart-topping masterpiece. Instead, the company wants users to have a fun and unique way to express themselves. The tracks are designed for sharing with friends or posting online. To complete the experience, cover art is generated automatically by Nano Banana.
Importantly, every track includes SynthID, Google’s invisible watermark for AI-generated content. This helps identify that the music was created by Google’s AI tools. At the same time, Google stresses that the system focuses on original expression. It does not aim to copy existing artists. If you name an artist in your prompt, Gemini treats that as broad inspiration. It will create music with a similar style or mood, not a direct imitation.
The company also says it uses filters to check outputs against existing content. These safeguards aim to prevent copyright issues. If users believe a track violates their rights, they can report it for review.
With Lyria 3 now powering Gemini, Google is clearly betting on short-form AI music as a new social tool. The feature may not replace professional studios. Still, it lowers the barrier for anyone who wants to turn an idea into sound within seconds.
