Google has introduced Lyria 3, a generative music model now available in beta inside the Gemini app, allowing users to create short songs from text prompts or images. The tool produces 30-second tracks complete with lyrics, style controls and custom cover art in seconds.
The model improves realism and creative control compared with earlier versions and automatically generates lyrics if none are provided. All audio includes SynthID watermarking to identify AI-generated content and support copyright safeguards. Google says the feature aims to enable everyday creative expression rather than replace professional music production.
Want to know more? Check out the source code here.











