Lyria 2

Lyria is a music generation model from Google. This page documents the capabilities and features of lyria-002.

Try in Agent Studio

Model ID	lyria-002
Modalities	description Text Input only photo Image Not supported mic Audio Output only videocam Video Not supported
Capabilities	Text to music Supported Image to music Not supported Vocal generation Not supported Instrumental mode Not supported Lyrics generation Not supported User-provided lyrics Not supported Negative prompting Supported Song generation Not supported Detailed structure controls Not supported Audio watermarking Not supported Filtering Not supported Prompt rewriter Not supported Content Credentials (C2PA) Not supported
Technical specifications	Audio	Maximum audio clip length: 32.8 seconds Maximum number of clips per prompt: 4 Supported sample rates: 48kHz Supported MIME types: audio/wav
Prompt languages	US English (en-us)
Supported regions	Model availability	Global: global
Quotas	Regional online prediction requests per minute per base model: 10 tokens per minute
Versions	lyria-002 Launch stage: GA Release date: 2025-10-27
Pricing	See Pricing.

For Lyria pricing information, see the Lyria section of the Cost of building and deploying AI models in Vertex AI page.