Following the AI-fication of videos and images, Google’s Gemini chatbot is taking aim at custom music generation. Lyria 3, Google DeepMind’s latest generative music model, is rolling out in beta within the Gemini app. It allows users to generate 30-second music tracks based on a prompt or remix an existing track to their liking.

“Just describe an idea or upload a photo — like ‘a comical R&B slow jam about a sock finding its match’ — and in a matter of seconds, Gemini will translate it into a high-quality, catchy track. To push the creative envelope further, you can even ask Gemini to take inspiration from something you upload,” the company said in a statement.

Unlike its rivals in the field, you do not have to add lyrics to your prompt. Even if your instructions are vague, the model will create suitable lyrics for the 30-second song — or, let’s say, a 30-second jingle.

You can even upload a photo or video and ask Gemini to generate a track with lyrics that match its mood. “The goal of these tracks isn’t to create a musical masterpiece, but rather to give you a fun, unique way to express yourself,” the company added.

Creators can also explore Lyria 3 via YouTube’s Dream Track. Available in the US and now rolling out to YouTube creators in other countries, Lyria 3 will enhance the quality of each unique Shorts soundtrack. Google states that all tracks generated in the Gemini app are embedded with SynthID — a watermark used for identifying Google AI-generated content.

Inevitably, questions arise regarding AI-driven music generation, particularly concerning training data, copyright, and respect for artistes. The company stated: “We’ve sought to develop this technology responsibly in collaboration with the music community.” It further noted that Google has “been very mindful of copyright and partner agreements” during the training of Lyria 3.

AI-generated music is not new; many companies offer similar services. It has reached a point where streaming services are being flooded with AI artistes, some of whom have gathered thousands of listeners.

Lyria 3 is now live on the Gemini web interface and should be available in the mobile app within a few days. It currently supports English, German, Spanish, French, Hindi, Japanese, Korean, and Portuguese, with plans to add more languages soon.