# Scenario Caption Studio — API Reference

Model ID: `model_scenario-caption-studio`

---

## 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-caption-studio`

### Parameters

| Parameter | Type | Required | Default | Description |
|-----------|------|----------|---------|-------------|
| `video` | assetId | yes | - | The video you want to caption. |
| `subtitles` | assetId | - | - | Optional. Upload an existing subtitle file (.srt) to use. Leave it empty and the audio will be transcribed automatically. |
| `targetLanguage` | string | - | `auto` | Translate captions into this language. Leave on Auto to keep the original spoken language. |
| `stylePreset` | string | - | `` | Pick a ready-made caption style (TikTok Bouncy, Karaoke Fill, Cinematic Fade, and more). Leave empty for the default look. |
| `themeTsx` | string | - | - | Advanced: supply your own custom caption theme to fully replace the preset. If you also add a Style Prompt, it refines this theme. |
| `stylePrompt` | string | - | - | Describe the caption look you want in plain words and the model will build a matching style. |
| `maxSegmentDuration` | number | - | - | The longest a single caption can stay on screen, in seconds. |
| `maxSegmentChars` | number | - | - | The most characters a caption can hold before it splits into the next one. |
| `maxSegmentWords` | number | - | - | The most words per caption. Set to 1 to show one word at a time, great for karaoke-style captions. |
| `fontColor` | string | - | `#FFFFFF` | Main text colour, as a hex code (e.g. #FFFFFF for white). |
| `accentColorStart` | string | - | `#FF8A3D` | Colour used to highlight or animate words (e.g. karaoke and pop styles). This is where the gradient begins. Hex code, e.g. #FF8A3D. |
| `accentColorEnd` | string | - | `#FF3D8A` | The colour the accent gradient ends on. Set it to a different colour from the start to create a gradient. Hex code, e.g. #FF3D8A. |
| `textPosition` | string | - | `bottom` | Where captions sit on screen — top, middle, or bottom. |
| `fontSizePx` | number | - | - | Caption font size in pixels. Leave empty to size automatically. |
| `maxLines` | number | - | `2` | The most lines a caption can wrap onto. |
| `textWidthPct` | number | - | - | How much of the screen width captions can fill, as a percentage. |
| `transcriptionPrompt` | string | - | - | Optional hint to improve transcription — list names, brands, or technical terms used in the video so they're spelled correctly. |
| `modelSize` | string | - | `medium` | Transcription quality. Larger sizes are more accurate but slower and cost more. |
| `compressionLevel` | number | - | `23` | Output quality. Lower numbers mean higher quality and larger files. |
| `outputVideo` | boolean | - | `true` | Return the finished video with captions burned in. |
| `outputSrt` | boolean | - | `false` | Also return the captions as a separate .srt file you can reuse or edit. |
| `outputTsx` | boolean | - | `false` | Advanced: also return the caption theme used to render the video. |
| `outputSubtitles` | string | - | `video_image` | How captions appear in the video. Burn Into Video bakes the styled captions permanently into the picture, so they always show and keep their style — but can't be turned off. Soft Subtitle Track adds captions as a separate track the viewer can switch on or off; it's faster, but shows plain text without the preset styling. Only applies when Output Video is on. |

### Example Requests

**cURL**

```bash
curl -X POST "https://api.cloud.scenario.com/v1/generate/custom/model_scenario-caption-studio" \
  -H "Authorization: Basic $(echo -n '<API_KEY>:<API_SECRET>' | base64)" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'EOF'
{
  "video": "<asset_id>",
  "targetLanguage": "auto",
  "stylePreset": "",
  "fontColor": "#FFFFFF",
  "accentColorStart": "#FF8A3D",
  "accentColorEnd": "#FF3D8A",
  "textPosition": "bottom",
  "maxLines": 2,
  "modelSize": "medium",
  "compressionLevel": 23,
  "outputVideo": true,
  "outputSrt": false,
  "outputTsx": false,
  "outputSubtitles": "video_image"
}
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>",
    "targetLanguage": "auto",
    "stylePreset": "",
    "fontColor": "#FFFFFF",
    "accentColorStart": "#FF8A3D",
    "accentColorEnd": "#FF3D8A",
    "textPosition": "bottom",
    "maxLines": 2,
    "modelSize": "medium",
    "compressionLevel": 23,
    "outputVideo": True,
    "outputSrt": False,
    "outputTsx": False,
    "outputSubtitles": "video_image"
}

response = client.generate.run_model(
    model_id="model_scenario-caption-studio",
    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>",
  "targetLanguage": "auto",
  "stylePreset": "",
  "fontColor": "#FFFFFF",
  "accentColorStart": "#FF8A3D",
  "accentColorEnd": "#FF3D8A",
  "textPosition": "bottom",
  "maxLines": 2,
  "modelSize": "medium",
  "compressionLevel": 23,
  "outputVideo": true,
  "outputSrt": false,
  "outputTsx": false,
  "outputSubtitles": "video_image"
};

const response = await client.generate.runModel("model_scenario-caption-studio", { 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)*