POST
/
collections
Create a new collection to organize and process video files
curl --request POST \
  --url https://api.cloudglue.dev/v1/collections \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "collection_type": "media-descriptions",
  "name": "<string>",
  "description": "<string>",
  "describe_config": {
    "enable_summary": true,
    "enable_speech": true,
    "enable_scene_text": true,
    "enable_visual_scene_description": true
  },
  "extract_config": {
    "prompt": "<string>",
    "schema": {},
    "enable_video_level_entities": false,
    "enable_segment_level_entities": true
  },
  "transcribe_config": {
    "enable_summary": true,
    "enable_speech": true,
    "enable_scene_text": false,
    "enable_visual_scene_description": false
  },
  "default_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
  },
  "default_thumbnails_config": {
    "enable_segment_thumbnails": true
  }
}'
{
  "id": "<string>",
  "object": "collection",
  "name": "<string>",
  "description": "<string>",
  "collection_type": "media-descriptions",
  "extract_config": {
    "prompt": "<string>",
    "schema": {},
    "enable_video_level_entities": false,
    "enable_segment_level_entities": true
  },
  "transcribe_config": {
    "enable_summary": true,
    "enable_speech": true,
    "enable_scene_text": false,
    "enable_visual_scene_description": false
  },
  "describe_config": {
    "enable_summary": true,
    "enable_speech": true,
    "enable_scene_text": true,
    "enable_visual_scene_description": true
  },
  "default_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
  },
  "default_thumbnails_config": {
    "enable_segment_thumbnails": true
  },
  "created_at": 123,
  "file_count": 123
}

Authorizations

​
Authorization
string
header
required

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

Body

application/json

Collection creation parameters

​
collection_type
enum<string>
required

Type of collection, determines how videos are processed and what data is extracted.

Collection Types:

  • media-descriptions: Generate comprehensive media descriptions with speech, visual, and text analysis (use describe_config)
  • entities: Extract structured data/entities from videos (requires extract_config)
  • rich-transcripts: Generate rich transcriptions with speech and visual descriptions (use transcribe_config). For backward compatibility only, new collections should use media-descriptions instead.

⚠️ Important: Only provide the config that matches your collection_type. Other configs will be ignored.

Available options:
media-descriptions,
entities,
rich-transcripts
​
name
string
required

Name of the collection (must be unique within an organization)

​
description
string | null

Description of the collection's purpose or contents, null if none provided

​
describe_config
object

🎯 Use ONLY when collection_type = 'media-descriptions'

Configuration for comprehensive media description from videos. Optional - if not provided, default values will be used. This config will be ignored for other collection types.

​
extract_config
object

🎯 Use ONLY when collection_type = 'entities'

Configuration for automatic entity extraction from videos. Required for entities collections. This config will be ignored for other collection types.

​
transcribe_config
object

🎯 Use ONLY when collection_type = 'rich-transcripts'

Configuration for rich transcription from videos. Optional - if not provided, default values will be used. This config will be ignored for other collection types.

​
default_segmentation_config
object

Default segmentation configuration to use for files added to this collection. If not provided, a default uniform segmentation will be used.

​
default_thumbnails_config
object

Default thumbnails configuration to use for files added to this collection. If not provided, a default thumbnails configuration will be used.

Response

Successful collection creation

​
id
string
required

Unique identifier for the collection

​
object
enum<string>
required

Object type, always 'collection'

Available options:
collection
​
name
string
required

Name of the collection

​
collection_type
enum<string>
required

Type of collection, determines how videos are processed and what data is extracted

Available options:
media-descriptions,
entities,
rich-transcripts
​
created_at
integer
required

Unix timestamp of when the collection was created

​
file_count
integer
required

Number of files in the collection

​
description
string | null

Description of the collection's purpose or contents, null if none provided

​
extract_config
object

Configuration for automatic entity extraction from videos. Required when collection_type is 'entities'.

​
transcribe_config
object

Configuration for rich transcription from videos. Used when collection_type is 'rich-transcripts'. If not provided, default values will be used.

​
describe_config
object

Configuration for comprehensive media description from videos. Used when collection_type is 'media-descriptions'. If not provided, default values will be used.

​
default_segmentation_config
object

Default segmentation configuration used for files in this collection

​
default_thumbnails_config
object

Default thumbnails configuration used for files in this collection