Google has unveiled a groundbreaking generative AI audio tool, Lyria 3, now accessible within the Gemini app. This cutting-edge technology empowers users to craft their own music by merely describing an idea, uploading a photo, or drawing inspiration from personal memories. Lyria 3 builds upon Google DeepMind's previous audio generation capabilities, offering a more refined experience. It generates lyrics based on user prompts, allowing customization of style, vocals, and tempo, resulting in highly realistic music tracks. The process is straightforward: users simply provide details about the genre, mood, or inside jokes, and Lyria 3 generates tracks with or without lyrics, ensuring a personalized soundtrack. The Gemini app facilitates sharing these creations, offering 30-second tracks with custom cover art, making it easy to share with others. Google's vision behind this generative AI audio tool is to create a 'fun, custom soundtrack to your daily life,' rather than professional-grade tracks. Additionally, Lyria 3 can be accessed via YouTube's Dream Track, currently available in the US, enabling users to create custom soundtracks for their videos. The tracks are embedded with SynthID, ensuring they are identified as Google AI-generated content. Gemini will also introduce new tools to help users distinguish AI-generated audio. Lyria 3 is available in multiple languages, including English, German, Spanish, French, Hindi, Japanese, Korean, and Portuguese, with plans to expand further. Google AI Plus, Pro, and Ultra subscribers will have enhanced limits, though specific details are yet to be disclosed. Experience Lyria 3 today at gemini.google.com.
