Google adds the Lyria 3 music generator to the Gemini app

Google Added Music Generator Lyria 3 to Gemini App

Google has taken a significant step in developing its universal AI assistant Gemini by integrating DeepMind's advanced audio model Lyria 3 into the mobile application. This new feature allows users to create short musical compositions lasting up to 30 seconds based on diverse prompts: from text descriptions to images and even videos. The innovation, launched in beta mode worldwide, opens new horizons for creative self-expression and strengthens Google's position in the generative AI services market.

The background to this update lies in the rapid development of artificial intelligence technologies, particularly in the field of multimedia content generation. Lyria 3 represents the latest generation of audio models from DeepMind, Google's subsidiary specializing in advanced AI research. The goal of integrating Lyria 3 into Gemini is to transform the AI assistant from a tool for working with text into a full-fledged multimedia creative hub. Previously, Gemini had already demonstrated impressive capabilities in image generation and text processing, and now it complements them with an audio component, creating a comprehensive solution for users seeking to create diverse content.

A deep dive into Lyria 3's functionality shows how flexible the music creation process has become. Users can specify particular genres, from classical rock to ambient, indicate the desired mood of the composition—from joyful and energetic to melancholic and calm. The ability to use images or videos as a starting point makes the process even more intuitive and creative.

For example, one can upload a sunset photograph and ask the AI to generate music corresponding to that visual image. Gemini processes these prompts and, drawing on Lyria 3's capabilities, creates unique 30-second tracks. The beta version of the feature is available globally in several languages, including English, German, Spanish, French, Hindi, Japanese, Korean, and Portuguese, with prospects for further expansion of language support.

Access to the feature is limited to Gemini app users over 18 years old, 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 quite significant. First, it intensifies competition between major technology companies in the field of generative AI. By integrating music creation directly into its main chatbot, Google offers a unique advantage by combining work with text, images, and sound in a single, accessible interface.

This could attract a new audience of users looking for simple and quick ways to create musical content for personal projects, social networks, or simply for entertainment. Second, it democratizes the music creation process, making it accessible even to those without professional musical skills or expensive equipment. Users can experiment with different sound landscapes without leaving the Gemini application, which stimulates creative exploration and innovation.

In conclusion, the integration of the Lyria 3 music generator into the Gemini app represents an important stage in the evolution of AI assistants. By transforming Gemini into a multimedia creative center, Google not only expands the functional capabilities of its product but also opens new possibilities for millions of users around the world. This innovation underscores Google's commitment to creating more intuitive and powerful tools for creativity, blurring the boundaries between different forms of media and making artificial intelligence even more integrated into everyday life.