Google's Gemini AI Receives a Major Upgrade
Google has unveiled a significant update to its Gemini artificial intelligence, granting it the ability to produce 30-second music tracks from a simple text prompt or an uploaded photograph. This new feature is powered by the integration of the Lyria 3 model, which specializes in generating original musical content. This move places Google in direct competition with other AI music generators, expanding the creative tools available to the public.
The announcement was made on Wednesday, February 18. The functionality is currently rolling out in the web version of Gemini, with mobile app integration expected to follow shortly. The tool supports prompts in eight languages, including English, German, Spanish, and Japanese. While Ukrainian is not among the initial supported languages, users in Ukraine can access the feature through the English-language interface.
Extended Features and Industry Implications
In addition to audio generation, the Nano Banana model is responsible for creating accompanying cover art for the tracks, adding a visual component. All generated audio files include a SynthID watermark, a digital signature designed to identify content created by artificial intelligence. Notably, the AI is programmed to avoid precisely replicating the voices of real-life performers, emphasizing the originality of its output.
Google's Gemini update marks a pivotal step in the evolution of artificial intelligence within the realms of music and art.
The introduction of music generation from text or images could unlock new avenues for user creativity and self-expression. Given the rapid advancement of AI technology, this innovation is poised to impact the music industry by providing novel tools for composers and artists, while also democratizing content creation for a broader audience. Observing how this technology adapts to different linguistic contexts, including for Ukrainian-speaking users, will be important as it evolves.