Google AI music maker
An in-depth look at how Google’s AI music maker, powered by the Lyria 3 model inside the Gemini app, is
transforming text, images, and videos into instantly generated, multimodal music experiences.
Google has expanded its artificial intelligence portfolio by introducing an advanced AI music creation feature inside the Gemini app. Powered by the Lyria 3 AI model developed by Google DeepMind, the new system enables users to generate short, 30-second music tracks directly within the Gemini interface, reinforcing Google’s growing leadership in multimodal AI innovation.
The integration of Lyria 3 into the Google Gemini app marks a significant step in AI-generated music technology. Users can now create original compositions using simple text prompts, descriptive mood settings, or genre-based instructions without leaving the chatbot environment. The model also supports image-to-music and video-to-music generation, allowing uploaded visuals to guide both instrumental arrangements and automatically generated lyrics that align with the tone and atmosphere of the reference material.
Currently available in beta, the AI music generator is rolling out globally across multiple languages, including English, German, Spanish, French, Hindi, Japanese, Korean, and Portuguese. Access is limited to users aged 18 and above, with broader feature expansion expected in future updates.
Lyria 3’s text-to-music capabilities allow users to translate ideas, memories, and emotions into customized soundtracks. Whether requesting a specific genre, a reflective mood, or a thematic composition, the system delivers AI-generated instrumental tracks or fully structured songs complete with lyrics. This multimodal approach positions the Gemini app as more than a conversational assistant—it evolves into a creative AI platform that merges language, visuals, and audio into a unified production workflow.
According to Google, the objective of this AI music creation tool is not to replace professional artistry, but to provide an accessible and expressive outlet for everyday users. By embedding advanced audio intelligence into Gemini, Google continues to redefine how generative AI can enhance digital creativity and user interaction.