Lyria 3.5 Clip Preview is Google's model optimized for generating short musical clips, loops, and previews. It generates 30-second high-quality, 44.1 kHz stereo audio from text prompts or image inputs. Try in Google AI Studio
Documentation
Visit the Music Generation guide for full coverage of features and capabilities.
lyria-3.5-clip-preview
| Property | Description |
|---|---|
| Model code | lyria-3.5-pro-preview |
| Supported data types | Inputs Text and Image Output Audio (MP3), Text (Lyrics) |
| Token limits[1](https://ai.google.dev/gemini-api/docs/tokens)^ | Input token limit 131,072 |
| Capabilities | Audio generation Supported Caching Not supported Code execution Not supported File search Not supported Function calling Not supported Grounding with Google Maps Not supported Image generation Not supported Live API Not supported Search grounding Not supported Structured outputs Not supported Thinking Not supported URL context Not supported |
| Consumption options | Batch API Not supported Flex inference Not supported Priority inference Not supported |
| Versions | Read the model version patterns for more details. - Preview: lyria-3.5-clip-preview - Preview: lyria-3.5-pro-preview |
| Latest update | September 2026 |
[*] ↩︎