Google’s Gemini can now create music

Google’s Gemini can now create 30-second music tracks based on prompts. To accomplish this, it’s using Lyria 3, Google DeepMind’s latest generative music model. Music creation is rolling out today in beta in the Gemini app in English, German, Spanish, French, Hindi, Japanese, Korean, and Portuguese.

Everyone over 18 gets access to it, but Google AI Plus, Pro, and Ultra subscribers will enjoy higher usage limits than those who aren’t paying. To use this, simply describe an idea or upload a photo or video to tell Gemini to take inspiration from it. Cover art is automatically generated by Nano Banana.

Google says “the goal of these tracks isn’t to create a musical masterpiece, but rather to give you a fun, unique way to express yourself” and share what you got with your friends. You can describe a specific genre, mood, inside joke, or memory to create tracks with lyrics or instrumental audio that “fits your vibe”. Speaking of lyrics, these will be automatically generated too, no need to provide them yourself.

The tracks generated by Gemini are embedded with SynthID, Google’s imperceptible watermark for identifying Google AI-generated content. Google says music generation is designed for original expression, not for mimicking existing artists, and if your prompt names an artist, Gemini will take that as broad creative inspiration and create a track that has a similar style or mood.

The company also assures us that it has filters in place to check outputs against existing content, but you can also report content that may violate your rights or the rights of others.

Source