Available in VPC
Request a VLM-based scene summary using the latest index for an asset. Since the latest index for each asset is automatically selected, request the scene summary without specifying an index ID. Once the scene summary is complete, a natural language text summary will be generated for each scene.
- Scene summaries can only be requested for assets that have been fully indexed.
- The initial analysis must be run on the entire scene. Once the full analysis is complete, you can perform a partial reanalysis by specifying specific scenes.
- If a scene summary is already in progress, a new request will fail.
- The language (
locale) for the summary results can only be specified during the full analysis and is fixed for subsequent scene summaries. It cannot be specified during a partial reanalysis and will inherit the existing language. Language changes are only possible through a full reanalysis.
Request
This section describes the request format. The method and URI are as follows:
| Method | URI |
|---|---|
| POST | /api/v1/workspaces/{workspace_name}/projects/{project_id}/assets/{asset_id}/scene-summary |
Request headers
For information about the headers common to all Media Intelligence APIs, see Media Intelligence request headers.
Request path parameters
You can use the following path parameters with your request:
| Field | Type | Required | Description |
|---|---|---|---|
workspace_name |
String | Required | Workspace name |
project_id |
String | Required | Project ID
|
asset_id |
String | Required | Media asset ID
|
Request body
You can include the following data in the body of your request:
| Field | Type | Required | Description |
|---|---|---|---|
scenes |
Array<Integer> | Optional | List of scene IDs to be reanalyzed
|
locale |
String | Optional | Summary results language
|
Request example
The request example is as follows:
curl --location --request POST 'https://mi.apigw.ntruss.com/api/v1/workspaces/my-workspace/projects/1234/assets/5678/scene-summary' \
--header 'x-ncp-apigw-timestamp: {Timestamp}' \
--header 'x-ncp-iam-access-key: {Access Key}' \
--header 'x-ncp-apigw-signature-v2: {API Gateway Signature}' \
--header 'Content-Type: application/json' \
--data '{
"scenes": [12, 13]
}'
Response
This section describes the response format.
Response body
The response body includes the following data:
| Field | Type | Required | Description |
|---|---|---|---|
code |
String | - | API processing result code |
message |
String | - | API processing result message |
result |
Object | - | Scene summary request information |
result.sceneSummaryId |
Integer | - | Scene summary request ID |
result.indexId |
Integer | - | Analysis target index ID
|
result.locale |
String | - | Summary results language
|
result.targetScenes |
Array<Integer> | - | List of scene IDs to be analyzed
|
result.createdTime |
String | - | Analysis request creation date and time
|
result.createdUserName |
String | - | Username of the user who requested the analysis |
Response status codes
For information about the HTTP status codes common to all Media Intelligence APIs, see Media Intelligence response status codes.
| Error code | Message | Description |
|---|---|---|
| 400 | Invalid scenes | Invalid scene ID. |
| 400 | Full analysis required before partial analysis | scenes specified while full analysis is incomplete |
| 400 | Language cannot be specified for partial analysis | locale specified for partial reanalysis |
| 409 | Scene summary already in progress | A scene summary is already in progress. |
Response example
The response example is as follows:
{
"code": "0",
"message": "success",
"result": {
"sceneSummaryId": 101,
"indexId": 23844,
"locale": "ko-KR",
"targetScenes": [12, 13],
"createdTime": "2026-07-01T11:00:00",
"createdUserName": "username"
}
}