Google Launches Lyria 3.5 Music Model for Users and Developers

Google announced today that its music generation model Lyria 3.5 is now available in the Gemini app and API, moving from an internal tool to mainstream users and developers. Developers can access it through Google AI Studio, Vertex AI, and the Gemini API. The model can create full songs with choruses and bridges.

Lyria 3.5 offers two versions: Lyria 3 Clip for 30-second loops, and Lyria 3.5 for multi-minute tracks. Output supports MP3 and WAV, and developers can use text prompts with up to 10 images. All generated content includes SynthID watermarking to resist compression and other edits for copyright tracking.