Google adds Lyria 3 music generator to the Gemini app

Google adds Lyria 3 music generator to the Gemini app

Google has taken a significant step in developing its general-purpose AI assistant Gemini by integrating DeepMind's advanced Lyria 3 audio model into the mobile app. The new feature lets users create short musical pieces of up to 30 seconds, using a wide range of prompts as a starting point: from text descriptions to images and even video clips. Launched in beta worldwide, the feature opens new horizons for creative self-expression and strengthens Google's position in the generative AI market.

The update comes amid the rapid advance of artificial intelligence, particularly in multimedia content generation. Lyria 3 is the latest generation of audio models from DeepMind, the Google division specializing in cutting-edge AI research. The goal of bringing Lyria 3 into Gemini is to turn the assistant from a text tool into a full multimedia creative hub. Gemini had already shown impressive capabilities in image generation and text processing, and it now adds an audio component, creating a comprehensive solution for users who want to produce varied content.

A closer look at Lyria 3 shows how flexible music creation has become. Users can specify particular genres, from classic rock to ambient, and set the desired mood of a piece, from joyful and energetic to melancholic and calm. Using images or video as a starting point makes the process even more intuitive and creative.

For example, you can upload a photo of a sunset and ask the AI to generate music that matches the visual. Gemini processes these prompts and, drawing on Lyria 3, creates unique 30-second tracks. The beta is available globally in several languages, including English, German, Spanish, French, Hindi, Japanese, Korean and Portuguese, with further language support planned.

Access is limited to Gemini app users over 18, in line with Google's policy on the use of AI technologies.

The implications of this move for Google and the industry as a whole are considerable. First, it intensifies competition among large technology companies in generative AI. By building music creation directly into its main chatbot, Google offers a distinct advantage: text, images and sound in a single, accessible interface. This may attract a new audience of users looking for simple, fast ways to make music for personal projects, social media or just for fun. Second, it democratizes music creation, making it accessible even to people without professional musical skills or expensive equipment. Users can experiment with different soundscapes without leaving the Gemini app, which encourages creative exploration and innovation.

In conclusion, the integration of the Lyria 3 music generator into the Gemini app is an important stage in the evolution of AI assistants. By turning Gemini into a multimedia creative center, Google not only expands the functionality of its product but also opens new possibilities for millions of users worldwide. The innovation reflects Google's push toward more intuitive and powerful creative tools, blurring the boundaries between forms of media and making artificial intelligence even more embedded in everyday life.