Create Music with Lyria 3, Our Newest Generation Model

The new music generation model Lyria 3 is now available for developers in public preview through the Gemini API and Google AI Studio. You can choose between Lyria 3 Pro for full songs or Lyria 3 Clip for shorter musical snippets, and control tempo, lyrics, and even use images to influence the music.

Lyria 3 and Lyria 3 Pro provide developers with the ability to create high-quality compositions, including vocals, verses, and choruses, with a high level of musical consistency. The Lyria 3 Pro model is designed for creating tracks up to three minutes long with professional-grade structural awareness, while Lyria 3 Clip is optimized for rapid prototyping and generating high-quality 30-second clips.

Both models support realistic vocals and offer improved sound clarity. Developers can create music across various genres and in multiple languages, from pop to funk and Motown. Additionally, Lyria 3 introduces precise controls, allowing you to set tempo and outline song lyrics with high accuracy.

To showcase the capabilities of Lyria 3, example applications have been developed in Google AI Studio, such as background music for videos and an alarm clock that plays a new song each morning based on current information like the weather and calendar events. This highlights how AI can serve as an additive force for human creativity.

Every track generated by Lyria 3 includes a SynthID digital watermark, ensuring transparency and trust by allowing identification and verification of audio generated by Google AI. Developers can start experimenting with Lyria 3 in Google AI Studio, using an API key to access advanced features like image-to-music conversion.