Google is expanding the multimodal capabilities of its Gemini AI. Following the viral Nano Banana image generator, the company is now releasing Lyria 3, an AI model designed to generate music. Users can describe the desired music in words, or provide a picture or video, and Lyria 3 will create a high-fidelity track with custom lyrics.
Developed by Google's DeepMind division, Lyria 3 is focused on creating 30-second soundtracks for any moment, from funny jingles to lo-fi beats. The feature is already available on the Gemini desktop web version and will roll out to the mobile app globally soon.
Accessing the tool is free. Users simply select the new music option in the Gemini chat box. The model works similarly to AI image generation, interpreting prompts to produce music. For inspiration, users can also modify existing track templates.
This move places Google in the competitive AI music generation space, alongside companies like Suno, and taps into both creative and controversial aspects of AI media creation.