Google has unveiled a groundbreaking generative AI audio tool, Lyria 3, now accessible within the Gemini app. This cutting-edge technology, developed by Google DeepMind, empowers users to compose their own music with ease. By simply inputting an idea, uploading a photo, or sharing personal inspiration, users can witness their creative visions come to life in the form of unique audio tracks. Lyria 3 builds upon previous audio generation capabilities, offering a more sophisticated approach to music creation. Users can now dictate the style, vocals, and tempo, resulting in highly realistic and personalized music tracks. The process is straightforward: describe the genre, mood, or even an inside joke, and Lyria 3 will generate tracks accordingly. For added context, users can upload photos or videos, allowing the AI to create tracks that perfectly capture the mood depicted in the visual content. The Gemini app facilitates the creation of 30-second tracks with custom cover art, making it effortless to share these creations with others via download or link. Google's vision with Lyria 3 is to provide a fun, personalized soundtrack for daily life, rather than professional-grade tracks. Additionally, Lyria 3 is accessible through YouTube's Dream Track feature, currently available in the US, with plans to expand globally in the coming months. This feature enables users to create custom soundtracks for their Shorts or uploaded videos. To ensure transparency, SynthID is embedded in the audio tracks, clearly indicating their AI-generated nature. Gemini will also introduce new tools to help users identify AI-generated content, including audio. Lyria 3 is available in multiple languages, catering to a diverse user base. Google AI Plus, Pro, and Ultra subscribers will benefit from higher usage limits, although specific details are yet to be disclosed. Experience Lyria 3 today at gemini.google.com.
