Google Gemini users can generate AI music through app

Google announced this week that users could generate AI music through their Gemini app, with the new feature powered by the company’s most advanced music generation model, Lyria 3.

Lyria 3 will help users generate 30-second-long clips in a variety of styles and with multi-lingual lyrics, based on their text, image, or uploaded prompts.

“Just describe an idea or upload a photo, like “a comical R&B slow jam about a sock finding their 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,” stated Google in a blog post.

The company added that cover art for the track would be generated by its Nano Banana AI model. Lyria 3 is available in the Gemini app for all users aged 18 and above. The languages currently covered include English, German, Spanish, French, Hindi, Japanese, Korean, and Portuguese.

On the question of copyright and originality, Google noted that all tracks generated in the Gemini app would be embedded with the SynthID AI watermark. The company also said that Lyria 3’s music generation feature was “designed for original expression, not for mimicking existing artists”.

AI-generated music is a contentious topic in the creative industry, with artistes and musicians objecting to AI generators misusing their content without permission to make profits.

There are also fears of AI generated music being monetised via illicit “spamming” tactics on streaming platforms, leaving human musicians in the lurch.

Google remarked that the goal of Lyria 3 was not to create a musical masterpiece, but rather just allow people to express themselves in a “fun” and “unique” way.