Gemini Now Lets You Create Music From Simple Prompts

Gemini brings a new feature that lets users create music using simple text or image prompts. This feature uses Google DeepMind’s latest generative music model called Lyria 3. It is currently available in beta for free, but Google AI Plus, Pro, and Ultra subscribers can enjoy higher limits.

Google pushes AI creativity further with music generation

Google continues to introduce new capabilities to the Gemini as part of its ambitions to expand AI creativity tools. Thanks to the new music generation feature, you can create songs with lyrics, vocals, and instrumental music. You just need to simply describe an idea like “a comical R&B slow jam about a sock finding their match” to generate a high-quality track in a few seconds. Moreover, you can ask Gemini to take inspiration from uploaded content for a more personalized music generation.

“The goal of these tracks isn’t to create a musical masterpiece, but rather to give you a fun, unique way to express yourself,” wrote Google in a blog post. The company also said that all tracks created in the Gemini are embedded with SynthID, an invisible watermark for identifying Google AI-generated content.

Google brings a host of improvements to Lyria 3 over earlier Lyria models. For example, you don’t need to write their own lyrics, as they are automatically generated based on the prompt. The new model also offers more creative control, letting users select elements such as style, vocals, and tempo. Moreover, Lyria 3 can create more realistic and musically complex tracks.

To use the new feature, you need to first open the Gemini app or website. From the tools section, tap on the create music option and then describe your track. The tool will create 30-second tracks with custom cover art using Nano Banana, its AI image generation and editing model. Finally, download the track or create a shareable link to share with friends.