Get Media Descriptions

Retrieve media description data for a specific file in a collection. This API is only available when the collection is created with collection_type ‘media-descriptions’

GET /collections/{collection_id}/videos/{file_id}/media-descriptions

Retrieve media description data for a specific file in a collection

cURL

curl --request GET \
  --url https://api.cloudglue.dev/v1/collections/{collection_id}/videos/{file_id}/media-descriptions \
  --header 'Authorization: Bearer <token>'

200

{
  "collection_id": "<string>",
  "file_id": "<string>",
  "thumbnail_url": "<string>",
  "content": "<string>",
  "title": "<string>",
  "summary": "<string>",
  "duration_seconds": 123,
  "segment_summary": [
    {
      "title": "<string>",
      "summary": "<string>",
      "start_time": 123,
      "end_time": 123,
      "thumbnail_url": "<string>"
    }
  ],
  "chapters": [
    {
      "index": 1,
      "start_time": 1,
      "end_time": 1,
      "description": "<string>"
    }
  ],
  "shots": [
    {
      "index": 1,
      "start_time": 1,
      "end_time": 1
    }
  ],
  "total_chapters": 1,
  "total_shots": 1,
  "visual_scene_description": [
    {
      "text": "<string>",
      "start_time": 123,
      "end_time": 123
    }
  ],
  "scene_text": [
    {
      "text": "<string>",
      "start_time": 123,
      "end_time": 123
    }
  ],
  "speech": [
    {
      "speaker": "<string>",
      "text": "<string>",
      "start_time": 123,
      "end_time": 123,
      "words": [
        {
          "word": "<string>",
          "start_time": 123,
          "end_time": 123
        }
      ]
    }
  ],
  "audio_description": [
    {
      "text": "<string>",
      "start_time": 123,
      "end_time": 123
    }
  ]
}

For details on how to create a video collection, see Create Collection

Authorizations

Authorization · string · header · required

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

Path Parameters

collection_id · string · required

The ID of the collection

file_id · string · required

The ID of the file

Query Parameters

response_format · enum<string>

Format for the response

Available options: json, markdown

start_time_seconds · number

Start time in seconds to filter out results by

end_time_seconds · number

End time in seconds to filter out results by

modalities · enum<string>[]

The modalities to output in the response. Can be used to return smaller data sets. Comma separated list of strings. Defaults to all modalities available / previously extracted. Accepted values are speech,visual_scene_description,scene_text, audio_description, summary, segment_summary, title

Available options: speech, visual_scene_description, scene_text, audio_description, summary, segment_summary, title

include_thumbnails · boolean

When true, include a file-level thumbnail_url on the response and per-segment thumbnail_url on each segment_summary entry

include_word_timestamps · boolean · default: false

When true, include a words array on each speech entry with word-level start_time and end_time. Not available for YouTube sources. Only applies when response_format=json.

include_chapters · boolean · default: false

Include narrative chapters in the response (when segmentation strategy is 'narrative')

include_shots · boolean · default: false

Include shot boundaries in the response (when segmentation strategy is 'shot-detector')

Response

200

application/json

Media description data

collection_id · string · required

Unique identifier for the collection

file_id · string · required

Unique identifier for the file

thumbnail_url · string<uri>

URL of the file-level thumbnail for the video. Only present when include_thumbnails=true.

content · string

Content string returned based on formatting, e.g. set to markdown text when response_format=markdown is requested

title · string

Generated title of the video

summary · string

Generated video level summary

duration_seconds · number

Duration of the video in seconds

segment_summary · object[]

Array of summary information for each segment of the video

Show child attributes

chapters · object[]

Array of narrative chapters (only present when include_chapters=true and segmentation strategy is 'narrative')

Show child attributes

shots · object[]

Array of shot boundaries (only present when include_shots=true and segmentation strategy is 'shot-detector')

Show child attributes

total_chapters · integer

Total number of chapters (only present when include_chapters=true and segmentation strategy is 'narrative')

Required range: x >= 0

total_shots · integer

Total number of shots (only present when include_shots=true and segmentation strategy is 'shot-detector')

Required range: x >= 0

visual_scene_description · object[]

Array of visual descriptions

Show child attributes

scene_text · object[]

Array of scene text extractions

Show child attributes

speech · object[]

Array of speech transcriptions

Show child attributes

audio_description · object[]

Array of audio descriptions

Show child attributes