Captions

The Captions card transcribes audio or video into timestamped captions using Gemini. The output includes word-level timing data that can be used for subtitle overlays in the final video.

Generate captions

POST /v1/autocontentengine/{id}/cells/{cell_id}/generate?agent_id={agent_id}

Path parameters

Parameter	Type	Description
`id`	integer	The sheet ID.
`cell_id`	integer	The cell ID.

Request body

Field	Type	Required	Description
`generation_type`	string	Yes	`"captions"`.
`data.model`	string	Yes	`"gemini"`.
`data.source_resource_id`	string	Yes	ID of a previously uploaded audio or video content resource.

Example

curl -X POST "https://api.gen.pro/v1/autocontentengine/101/cells/3000/generate?agent_id=42" \
  -H "X-API-Key: your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "generation_type": "captions",
    "data": {
      "model": "gemini",
      "source_resource_id": "res_abc123"
    }
  }'

You can also generate captions on a layer:

POST /v1/autocontentengine/{id}/cells/{cell_id}/layers/{layer_id}/generate?agent_id={agent_id}

Response

Poll Check generation status until complete. The finished generation includes the captions object with timestamps in the result field.

{
  "id": 9003,
  "status": "completed",
  "result": {
    "captions": [
      {"word": "Welcome", "start": 0.0, "end": 0.45},
      {"word": "back", "start": 0.45, "end": 0.72},
      {"word": "to", "start": 0.72, "end": 0.85},
      {"word": "another", "start": 0.85, "end": 1.20},
      {"word": "episode", "start": 1.20, "end": 1.65}
    ]
  }
}

Errors

Status	Error code	Description
`422`	`validation_error`	No audio or video resource provided.
`404`	`not_found`	Sheet or cell not found.

Cell configuration

Field	Type	Description
`autoGenerate`	boolean	Auto-trigger generation when source audio/video changes.

Caption source and styling are passed in the generation data parameter.