Skip to main content
POST
/
v1
/
video
/
describe
Describe video content using AI vision (async)
curl --request POST \
  --url https://api.urltodata.ai/v1/video/describe \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "url": "<string>"
}
'
{
  "jobId": "<string>"
}

Documentation Index

Fetch the complete documentation index at: https://docs.urltodata.ai/llms.txt

Use this file to discover all available pages before exploring further.

Authorizations

Authorization
string
header
default:your-api-key
required

API key as Bearer token (e.g. Bearer mp_abc123_secret)

Body

application/json
url
string<uri>
required

Video URL

mode
enum<string>

Processing mode

Available options:
describe,
ocr
prompt
string

Custom prompt

maxFrames
integer

Max frames to analyze

Required range: 1 <= x <= 20
maxResolution
integer

Max frame resolution

Required range: 64 <= x <= 2048
includeTranscript
boolean

Include video transcript

callbackUrl
string<uri>

Webhook callback URL

Response

Job created

jobId
string