Lyria is a music generation model from Google. This page
documents the capabilities and features of lyria-002
.
Model ID
lyria-002
Capabilities
- Supported
- Not supported
Supported audio format
- WAV
Supported sample rate
- 48kHz
Prompt languages
- US English (
en-us)
Limits
- API calls (prompts per project per minute): Refer to the Quotas and limits documentation for standard Vertex AI Inference limits.
- Maximum audio clips returned per request: Up to 4
- Audio length per clip: 32.8 seconds
For Lyria pricing information, see the Lyria section of the Cost of building and deploying AI models in Vertex AI page.
