asset_caption

Analysis

Caption Asset

Generate a caption for a Scenario image asset. Fast, purpose-built captioning. Args: - asset_id: required — the image to caption - details_level: optional — 'action' or 'action+style' - parameters: optional — advanced controls (modelId, seed, temperature, topP, unwantedSequences) - dry_run: optional — true returns a cost estimate without running or charging credits - team_id, project_id: required for OAuth callers Returns: captions (one per image) plus the job record. With dry_run=true, returns a cost estimate. For instruction-driven or interactive analysis (specific questions, custom output format), use asset_analyze (Scenario LLM) instead — it is more flexible than this fixed caption endpoint.

read-onlyidempotentopen-world

Parameters

Name	Type	Required	Description
asset_id	string	✓	Scenario asset ID of the image to caption.
details_level	enum(action \| action+style)	—	Caption detail: 'action' (subject + action) or 'action+style' (also describes style).
parameters	record	—	Advanced caption controls passed through to the API (modelId, seed, temperature, topP, unwantedSequences).
dry_run	boolean	—	Estimate cost without running. Sends ?dryRun=true so the API returns the cost estimate without executing or charging credits.
team_id	string	—	Team ID. Required if user belongs to multiple teams.
project_id	string	—	Project ID to scope the operation to.
response_format	enum(json \| markdown)	json	Output format: 'json' for structured data, 'markdown' for human-readable text.

Example Request

JSON

{
  "asset_id": "asset_img001",
  "team_id": "team_abc123",
  "project_id": "proj_xyz789"
}

Example Response

JSON

{
  "source_asset_id": "asset_img001",
  "captions": [
    "A red sports car on a wet city street at night"
  ],
  "detailsLevel": "action"
}

Common Use Cases

Auto-caption game assets for searchability and accessibility
Generate alt text for a batch of generated images