POST
/
extract
curl --request POST \
  --url https://api.cloudglue.dev/v1/extract \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "url": "<string>",
  "prompt": "<string>",
  "schema": {}
}'
{
  "job_id": "<string>",
  "status": "pending",
  "data": {
    "url": "<string>",
    "entities": {},
    "segment_entities": [
      {
        "segment_id": "<string>",
        "start_time": 123,
        "end_time": 123,
        "entities": {}
      }
    ]
  },
  "error": "<string>"
}

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json
Extract structured data from a video
​
url
string
required

Input video URL. Supports YouTube videos and URIs of files uploaded to cloudglue Files endpoint.

Note that YouTube videos are currently limited to speech and metadata level understanding, for fully fledge multimodal video understanding please upload a file instead to the Files API and use that object instead as input.

​
prompt
string

A natural language prompt describing the data you want to extract. Required if no schema is provided.

​
schema
object

A more rigid structure if you already know the JSON layout you want. Required if no prompt is provided.

Response

200
application/json
Successful response
​
job_id
string
required
​
status
enum<string>
required
Available options:
pending,
processing,
ready,
completed,
failed,
not_applicable
​
data
object

The structured data extracted from the video based on prompt or schema

​
error
string

Error message if status is 'failed'