> ## Documentation Index
> Fetch the complete documentation index at: https://docs.ekly.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Lyria 2 (High Quality)

> Google's production Lyria 2 model via Vertex AI.

Google's production Lyria 2 model via Vertex AI. One \~30s, 48 kHz stereo WAV clip per request. Supports negative prompts and seed for reproducibility.

| | |
| - | - |
| Model id | `lyria-002` |
| Media | audio |
| Submit to | `POST /v1/audio` |
| Price | 24 credits per\_generation before discounts |
| Typical time | about 30.0 s |

## Request

**Required:** `prompt_tags`\
**Optional:** `duration`, `energy`, `negative_prompt`, `sample_count`, `seed`, `tempo`

```json theme={null}
{
  "model": "lyria-002",
  "prompt_tags": [
    "warm indian wedding underscore soft tablas strings hopeful"
  ],
  "duration": 30,
  "energy": "medium",
  "sample_count": 1,
  "tempo": "medium"
}
```

| Field | Allowed | Default |
| - | - | - |
| `duration` | 5.0 – 30.0 | `30` |
| `energy` | `low`, `medium`, `high` | `"medium"` |
| `negative_prompt` | text | |
| `sample_count` | 1.0 – 4.0 | `1` |
| `seed` | number | |
| `tempo` | `slow`, `medium`, `fast` | `"medium"` |

Reference inputs take asset ids from [`POST /v1/uploads`](/uploads) or an earlier output's `asset_id`.
Prices and allowed values come from the live catalog; `GET /v1/models/lyria-002` is always current.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.