# Auto Subtitles — API Reference

Model ID: `model_scenario-video-subtitles`

---

## Authentication

- **API_KEY** and **API_SECRET** are found in your [Scenario Project Settings](https://app.scenario.com/team&tab=project_api_keys) under API Keys.
- Set them as environment variables `SCENARIO_SDK_API_KEY` and `SCENARIO_SDK_API_SECRET` — both SDKs pick them up by default.
- For raw HTTP (cURL), use Basic Auth: `Authorization: Basic base64("<API_KEY>:<API_SECRET>")`.

### Install the SDK

- JavaScript / TypeScript: `npm install @scenario-labs/sdk`
- Python: `pip install scenario-sdk`

---

## Generate

**Endpoint:** `POST https://api.cloud.scenario.com/v1/generate/custom/model_scenario-video-subtitles`

### Parameters

| Parameter | Type | Required | Default | Description |
|-----------|------|----------|---------|-------------|
| `video` | assetId | yes | - | Input video to add subtitles to. |
| `initialPrompt` | string | - | - | [auto mode] Optional text prompt to bias the model's style/vocabulary. |
| `fontColor` | string | - | `#FFFFFF` | Primary font color in #RRGGBB hex (e.g. '#FFFFFF' for white). |
| `outlineColor` | string | - | `#000000` | Outline color in #RRGGBB hex. Default is black. |
| `borderStyle` | string | - | `opaque-box` | How the border color is rendered around the text. 'Outline + Shadow': each glyph is stroked with border color and an optional drop shadow; the video behind the letters stays visible. 'Opaque Box': a filled rectangle (using border color, tinted by border color transparency) is drawn behind the text, covering the video. Border color transparency mostly matters with 'Opaque Box' — with 'Outline + Shadow' you usually want a fully opaque stroke. |
| `outlineColorTransparency` | number | - | `0.2` | Outline / box transparency: 0.0 = fully opaque, 1.0 = fully transparent. |
| `modelSize` | string | - | `small` | [auto mode] Whisper model size used for transcription. |
| `language` | string | - | `` | ISO 639-1 language code (e.g. 'en', 'fr'). Leave empty for auto-detection. |
| `task` | string | - | `transcribe` | [auto mode] 'transcribe' keeps the original language, 'translate' targets English. |
| `maxSegmentDuration` | number | - | - | Limits the maximum time (in seconds) a single subtitle appears. When splitting long segments, the system uses proportional timing and prioritizes punctuation boundaries (.,!?). Typical: 5–7s. Automatically defined if omitted. |
| `maxSegmentChars` | number | - | `42` | Limits the number of characters per subtitle cue. Applied alongside duration limits; the segment will split whenever either threshold is reached. Automatically defined if omitted. |
| `fontName` | string | - | `Arial` | Subtitle font family. |
| `fontSize` | number | - | `14` | Subtitle font size in points. |
| `compressionLevel` | number | - | `23` | Video compression quality (CRF, lower = higher quality). |

### Example Requests

**cURL**

```bash
curl -X POST "https://api.cloud.scenario.com/v1/generate/custom/model_scenario-video-subtitles" \
  -H "Authorization: Basic $(echo -n '<API_KEY>:<API_SECRET>' | base64)" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'EOF'
{
  "video": "<asset_id>",
  "fontColor": "#FFFFFF",
  "outlineColor": "#000000",
  "borderStyle": "opaque-box",
  "outlineColorTransparency": 0.2,
  "modelSize": "small",
  "language": "",
  "task": "transcribe",
  "maxSegmentChars": 42,
  "fontName": "Arial",
  "fontSize": 14,
  "compressionLevel": 23
}
EOF
```

**Python**

```python
import os
from scenario_sdk import Scenario

client = Scenario(
    api_key=os.environ.get("SCENARIO_SDK_API_KEY"),
    api_secret=os.environ.get("SCENARIO_SDK_API_SECRET"),
)

body = {
    "video": "<asset_id>",
    "fontColor": "#FFFFFF",
    "outlineColor": "#000000",
    "borderStyle": "opaque-box",
    "outlineColorTransparency": 0.2,
    "modelSize": "small",
    "language": "",
    "task": "transcribe",
    "maxSegmentChars": 42,
    "fontName": "Arial",
    "fontSize": 14,
    "compressionLevel": 23
}

response = client.generate.run_model(
    model_id="model_scenario-video-subtitles",
    body=body,
)
print(response)
```

**JavaScript**

```javascript
import Scenario from "@scenario-labs/sdk";

const client = new Scenario({
  apiKey: process.env["SCENARIO_SDK_API_KEY"],
  apiSecret: process.env["SCENARIO_SDK_API_SECRET"],
});

const body = {
  "video": "<asset_id>",
  "fontColor": "#FFFFFF",
  "outlineColor": "#000000",
  "borderStyle": "opaque-box",
  "outlineColorTransparency": 0.2,
  "modelSize": "small",
  "language": "",
  "task": "transcribe",
  "maxSegmentChars": 42,
  "fontName": "Arial",
  "fontSize": 14,
  "compressionLevel": 23
};

const response = await client.generate.runModel("model_scenario-video-subtitles", { body });
console.info(response);
```

---

## Retrieve Results

After submitting a generation request, you receive a `jobId`. Poll the job until `job.status` is `"success"`. The generated asset IDs are in `job.metadata.assetIds`.

**Endpoint:** `GET https://api.cloud.scenario.com/v1/jobs/{jobId}`

### Example Requests

**cURL**

```bash
curl -X GET "https://api.cloud.scenario.com/v1/jobs/<JOB_ID>" \
  -H "Authorization: Basic $(echo -n '<API_KEY>:<API_SECRET>' | base64)"
```

**Python**

```python
job = client.jobs.retrieve(job_id="<JOB_ID>")
print(job.status)
print(job.metadata.asset_ids)
```

**JavaScript**

```javascript
// Option 1 — wait on the response from runModel using the SDK helper
const completed = await response.job.wait();
console.info(completed.status);
console.info(completed.metadata?.assetIds);

// Option 2 — retrieve a job by its ID
const job = await client.jobs.retrieve("<JOB_ID>");
console.info(job.status);
console.info(job.metadata?.assetIds);
```

**Example response:**

```json
{
  "job": {
    "jobId": "job_abc123",
    "status": "success",
    "metadata": {
      "assetIds": [
        "asset_abc123"
      ]
    }
  }
}
```

> **Important:** Generated asset URLs are **temporary** and expire after a short period. Download and store any images you wish to keep before the URL expires. More info: [Content Delivery Network (CDN)](https://docs.scenario.com/get-started/documentation/content-delivery-network-cdn).

---

*Generated by [Scenario](https://app.scenario.com)*