Get Video Caption
Library Management
Get Video Caption
Retrieve the visual (scene-by-scene) caption auto-generated for a video in your Private Video Library.
GET
Get Video Caption
Product: Visual Search
Use case: Upload videos and images, auto-index them, then search by natural language, image, or transcript phrase
Host:
https://api.memories.ai/serve/api/v1
Auth: Authorization: sk-mavi-... (no Bearer prefix)Prerequisites
- You have created a memories.ai API key.
- The video has been uploaded via the Upload API and finished parsing (
status: PARSE).
Endpoint
GET /serve/api/v1/get_video_captionRequest Example
Query Parameters
The video identifier returned by the upload API.
Response Example
Response Fields
Business status code.
0000 indicates success.Human-readable status message.
Echo of the requested video identifier.
Ordered list of scene description segments covering the full video.
Zero-based index of the segment within the video.
Natural-language description of what is visible on screen during this segment.
Segment start time in seconds, returned as a string.
Segment end time in seconds, returned as a string.
Upload-time timestamp of the underlying video, in milliseconds since epoch, returned as a string.
GCS bucket of the underlying video file. Omitted when the storage location cannot be resolved.
GCS blob (object) path of the underlying video. Use it with
video_bucket at GET /serve/api/v2/download?bucket=&blob= to fetch the file directly.true when code == "0000".Inverse of
success.Notes & Limits
- Availability:
data.transcriptionsis populated by the indexing pipeline. If the video has not yet reachedstatus: PARSE, the call may returndata: nullor an emptytranscriptionsarray — poll Get Metadata until parsing completes before depending on the result. - Numeric strings:
startTime,endTime, andcreateTimeare strings — cast withint(...)before arithmetic. - Rate limiting: Subject to the standard Visual Search rate limits. See Rate limits.
