# Lyria 3 Pro Preview

Lyria 3 Pro generates full-length songs from text or image prompts, returning high-fidelity MP3 audio with vocals, lyrics, and song structure.

## API Information

- **Model Slug:** lyria-3-pro-preview
- **Branded URL:** https://www.eachlabs.ai/google/gemini/lyria-3-pro-preview
- **Provider:** Google
- **Category:** Music Generation
- **Output Type:** audio
- **Status:** active
- **Base Cost:** $0.08 per execution
- **Estimated Processing Time:** 60 seconds
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/lyria-3-pro-preview

## Pricing

- **Charge Type:** dynamic
- **Estimate:** $0.08 per execution
- **Pricing Details:** default: $0.08

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| prompt | string | Yes | - | - | Music prompt describing the style, mood, instrumentation, structure, lyrics, or timing. Lyria 3 Pro generates full-length songs, with duration controlled through the prompt. |
| image_urls | array | No | - | - | Optional image URLs to guide the music. Lyria 3 supports up to 10 image inputs alongside the text prompt. |

## Example Request

```bash
curl -X POST https://api.eachlabs.ai/v1/prediction/ \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "lyria-3-pro-preview",
  "input": {
    "prompt": "A cinematic indie-pop song with warm analog synths, atmospheric electric guitar, soft piano, deep rounded bass, and expressive live drums. Dreamy female vocals with an intimate, emotional delivery gradually build into a powerful uplifting chorus. Nostalgic yet modern production, spacious reverb, subtle vocal harmonies, rich stereo atmosphere, emotional nighttime-drive feeling. Start minimal and intimate, then slowly expand into a wide cinematic climax. 105 BPM."
  }
}'
```

## Output Schema

Response returned by `GET /v1/prediction/{id}` when the job completes:

```json
{
  "status": "success",
  "predictionID": "string",
  "output": "string (URL of generated audio)",
  "metrics": {
    "predict_time": "number (seconds)"
  }
}
```

## Polling

```bash
curl https://api.eachlabs.ai/v1/prediction/{PREDICTION_ID} \
  -H "Authorization: Bearer YOUR_API_KEY"
```

| Status | Meaning |
|--------|---------|
| `processing` | Still running — poll again |
| `success` | Done — read `output` |
| `error` | Failed — read `message` / `details` |

## Webhook (alternative to polling)

Pass `"webhook_url": "https://your.host/path"` in the create request. Eachlabs POSTs this payload when the job ends:

```json
{
  "exec_id": "prediction-uuid",
  "status": "succeeded",
  "output": "https://...",
  "error": ""
}
```

`status` is `"succeeded"` or `"failed"`. `exec_id` equals the `predictionID` from create. Return 2xx within 30 seconds.

## Errors

Error body: `{ "status": "error", "message": "...", "details": "..." }`

| Code | Meaning |
|------|---------|
| `400` | Invalid input |
| `401` | Missing / invalid `Authorization` bearer token |
| `404` | Unknown model or prediction id |
| `429` | Rate limit — 100 creates / min, 10 concurrent per key |
| `5xx` | Retry with backoff |

## Usage Notes

- API Base URL: `https://api.eachlabs.ai/v1`
- Authentication: send `Authorization: Bearer YOUR_API_KEY`. Generate a key from the Eachlabs dashboard at https://www.eachlabs.ai/dashboard/api-keys.
- File-typed parameters (`*_url`, `image_url`, `video_url`, `audio_url`, etc.) accept publicly-reachable HTTPS URLs only. Upload your asset first (GCS / S3 / your CDN) and pass the resulting URL. Data-URIs and localhost URLs are rejected.
- For structured parameters (arrays / objects) send real JSON values, not stringified payloads.
- Monetary values are reported in USD; per-token / per-megapixel rates may be billed in micro-cents internally.
- Prefer `webhook_url` over polling for long-running predictions — see the Webhook Callback section.