POST
/
describe
Create a new media description job
curl --request POST \
  --url https://api.cloudglue.dev/v1/describe \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "url": "<string>",
  "enable_summary": true,
  "enable_speech": true,
  "enable_visual_scene_description": true,
  "enable_scene_text": true,
  "thumbnails_config": {
    "enable_segment_thumbnails": true
  },
  "segmentation_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "segmentation_config": {
    "strategy": "uniform",
    "uniform_config": {
      "window_seconds": 31,
      "hop_seconds": 30.5
    },
    "shot_detector_config": {
      "threshold": 1,
      "min_seconds": 31,
      "max_seconds": 31,
      "detector": "adaptive"
    },
    "start_time_seconds": 1,
    "end_time_seconds": 1
  }
}'
{
  "job_id": "<string>",
  "status": "pending",
  "url": "<string>",
  "created_at": 123,
  "describe_config": {
    "enable_summary": true,
    "enable_speech": true,
    "enable_visual_scene_description": true,
    "enable_scene_text": true
  },
  "data": {
    "content": "<string>",
    "title": "<string>",
    "summary": "<string>",
    "speech": [
      {
        "text": "<string>",
        "start_time": 123,
        "end_time": 123
      }
    ],
    "visual_scene_description": [
      {
        "text": "<string>",
        "start_time": 123,
        "end_time": 123
      }
    ],
    "scene_text": [
      {
        "text": "<string>",
        "start_time": 123,
        "end_time": 123
      }
    ],
    "segment_summary": [
      {
        "title": "<string>",
        "summary": "<string>",
        "start_time": 123,
        "end_time": 123
      }
    ]
  },
  "error": "<string>"
}

Authorizations

Authorization
string
header
required

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

Body

application/json

Media description job parameters

url
string
required

Input video URL. Supports URIs of files uploaded to Cloudglue Files endpoint, public YouTube video URLs, public HTTP URLs, and S3 or Dropbox URIs which have been granted access to Cloudglue via data connectors.

Note that YouTube videos are currently limited to speech level understanding only. For S3 and Dropbox URI support see our documentation on data connectors for setup information.

enable_summary
boolean
default:true

Whether to generate video-level and segment-level (moment-level) summaries and titles

enable_speech
boolean
default:true

Whether to generate speech transcript

enable_visual_scene_description
boolean
default:true

Whether to generate visual scene description

enable_scene_text
boolean
default:true

Whether to generate scene text extraction

thumbnails_config
object
segmentation_id
string<uuid>

Segmentation job id to use. If not provided will use default to uniform 20s segmentation. Cannot be provided together with segmentation_config.

segmentation_config
object

Configuration for video segmentation. Cannot be provided together with segmentation_id.

Response

Successful response

job_id
string
required
status
enum<string>
required
Available options:
pending,
processing,
completed,
failed,
not_applicable
url
string

The URL of the processed video

created_at
integer

Unix timestamp of when the job was created

describe_config
object

Configuration for media description from videos

data
object
error
string

Error message if status is 'failed'