Google releases Lyria 3 music generation AI

Google has launched Lyria 3, its latest AI model for music generation, now available to developers in public preview via the Gemini API and Google AI Studio. This advanced model offers high-fidelity compositions with vocals, verses, and choruses, maintaining musical consistency. Developers can choose between Lyria 3 Pro for full-length songs and Lyria 3 Clip for shorter, high-volume audio assets. The AI supports precise control through natural language prompts, tempo conditioning, time-aligned lyrics, and multimodal image-to-music input. Each generated track includes a SynthID watermark for transparency.