# Cloudglue

> Cloudglue is a platform for turning video into LLM ready data..

## Docs

- [Introduction](https://docs.cloudglue.dev/introduction.md): Turn video data into a reusable, multimodal context layer for AI agents & applications.
- [Build with AI](https://docs.cloudglue.dev/getting-started/build-with-ai.md): Teach your coding agent how to build applications with Cloudglue APIs
- [Setup Cloudglue](https://docs.cloudglue.dev/getting-started/setup-cloudglue.md): Learn how to install and configure Cloudglue SDKs.
- [Video to Text](https://docs.cloudglue.dev/getting-started/video-to-text.md): Transform videos into rich, searchable text content
- [Structured Data Extraction](https://docs.cloudglue.dev/getting-started/structured-data-extraction.md): Turn your videos into structured data
- [Chat Over Collection](https://docs.cloudglue.dev/getting-started/chat-over-collection.md): Talk with videos
- [Responses API](https://docs.cloudglue.dev/getting-started/responses-api.md): Multi-turn conversations with video context
- [Webhooks](https://docs.cloudglue.dev/getting-started/webhooks.md): Use our webhooks to get notifications when your jobs are updated
- [Rate Limits](https://docs.cloudglue.dev/getting-started/rate-limits.md): Learn about our rate limits and usage quotas
- [MCP Server](https://docs.cloudglue.dev/getting-started/mcp-server.md): Integrate Cloudglue's powerful video understanding capabilities directly into Claude Desktop, Cursor, Windsurf, and other AI assistants
- [How It Works](https://docs.cloudglue.dev/data-connectors/overview.md): Connect your data sources to add files to Cloudglue
- [AWS S3](https://docs.cloudglue.dev/data-connectors/aws-s3.md): Connect your S3 buckets to Cloudglue using cross-account IAM roles
- [Dropbox](https://docs.cloudglue.dev/data-connectors/dropbox.md): Connect your Dropbox files to Cloudglue
- [Google Drive](https://docs.cloudglue.dev/data-connectors/google-drive.md): Connect your Google Drive files to Cloudglue
- [Google Cloud Storage](https://docs.cloudglue.dev/data-connectors/google-cloud-storage.md): Connect your Google Cloud Storage buckets to Cloudglue
- [Gong](https://docs.cloudglue.dev/data-connectors/gong.md): Connect your Gong recordings to Cloudglue
- [Recall.ai](https://docs.cloudglue.dev/data-connectors/recall.md): Connect your Recall.ai meeting recordings to Cloudglue
- [Zoom](https://docs.cloudglue.dev/data-connectors/zoom.md): Connect your Zoom recordings to Cloudglue
- [Grain](https://docs.cloudglue.dev/data-connectors/grain.md): Connect your Grain recordings to Cloudglue
- [iconik](https://docs.cloudglue.dev/data-connectors/iconik.md): Connect your iconik media library to Cloudglue
- [HTTP URLs](https://docs.cloudglue.dev/data-connectors/public-urls.md): Add videos from any public HTTP URL to Cloudglue
- [YouTube](https://docs.cloudglue.dev/data-connectors/youtube.md): Add YouTube URLs to Cloudglue for analysis
- [TikTok](https://docs.cloudglue.dev/data-connectors/tiktok.md): Add TikTok URLs to Cloudglue for analysis
- [Loom](https://docs.cloudglue.dev/data-connectors/loom.md): Add Loom URLs to Cloudglue for analysis
- [Local Files](https://docs.cloudglue.dev/data-connectors/local-files.md): Add video files directly from your computer
- [Files](https://docs.cloudglue.dev/core-concepts/files.md): Understanding how files work in Cloudglue
- [Segments](https://docs.cloudglue.dev/core-concepts/segments.md): Intelligent video segments that break down videos into meaningful parts using shot detection or narrative analysis
- [Entities](https://docs.cloudglue.dev/core-concepts/entities.md): Transform video content into structured, programmable data by extracting meaningful objects, events, and attributes
- [Media Description](https://docs.cloudglue.dev/core-concepts/media-description.md): Understanding media descriptions and their capabilities
- [Entity Collections](https://docs.cloudglue.dev/core-concepts/entity-collection.md): Organize and analyze extracted structured data across multiple videos
- [Media Description Collections](https://docs.cloudglue.dev/core-concepts/media-description-collection.md): Managing and utilizing collections of media descriptions
- [Chat Completions](https://docs.cloudglue.dev/core-concepts/chat-completions.md): Learn how to use Cloudglue's chat completion capabilities
- [Search](https://docs.cloudglue.dev/core-concepts/search.md): Search across video files and segments to find relevant content
- [On-Demand Describe](https://docs.cloudglue.dev/core-concepts/describe.md): Learn about on-demand describe operations
- [On-Demand Extract](https://docs.cloudglue.dev/core-concepts/extract.md): Transform individual videos into structured, programmable data using customized extraction parameters
- [Shareable Assets](https://docs.cloudglue.dev/core-concepts/shareable-assets.md): Create shareable and embeddable media links
- [Extraction Guide](https://docs.cloudglue.dev/deep-dives/extraction-guide.md): A comprehensive guide to extracting data with Cloudglue
- [Description Guide](https://docs.cloudglue.dev/deep-dives/description-guide.md): Deep dive into how to describe and analyze videos using our Describe API
- [Chat Completion with Media Description Collections](https://docs.cloudglue.dev/deep-dives/chat-completion.md): Build intelligent conversations with video content using Media Description Collections and grounded AI responses
- [Responses API](https://docs.cloudglue.dev/deep-dives/responses-api.md): Build conversational video experiences with entity-backed knowledge, streaming, and multi-turn support
- [Structured Queries](https://docs.cloudglue.dev/deep-dives/structured-queries.md): Query your extracted structured data — files, entities, and connector metadata — with read-only SQL
- [Introduction](https://docs.cloudglue.dev/api-reference/introduction.md): Cloudglue API Reference
- [Changelog](https://docs.cloudglue.dev/changelog.md): Product updates and announcements
- [Upload File](https://docs.cloudglue.dev/api-reference/endpoint/files/post.md): Upload a video, audio, or image file that can be used with Cloudglue services
- [Sync File from URL](https://docs.cloudglue.dev/api-reference/endpoint/files/sync.md): Materialize a publicly accessible URL into a Cloudglue file without a data connector or a collection. Accepts direct http(s) video/audio file URLs (e.g. `.mp4`), public Dropbox share links, TikTok video URLs, and Loom share URLs. Idempotent: syncing the same URL returns the existing file. YouTube UR…
- [Refresh Source Metadata](https://docs.cloudglue.dev/api-reference/endpoint/files/sync-source-metadata.md): Re-fetches the file's source_metadata live from its data connector (google-drive, dropbox, zoom, gong, recall, grain, or iconik) and updates the stored value. If the file belongs to any metadata collections, their search documents are re-indexed with the refreshed metadata. For iconik files without…
- [List Files](https://docs.cloudglue.dev/api-reference/endpoint/files/get.md): List files that have been uploaded to Cloudglue
- [Get File](https://docs.cloudglue.dev/api-reference/endpoint/files/get-id.md): Retrieve details about a specific file
- [Update File](https://docs.cloudglue.dev/api-reference/endpoint/files/put-id.md): Update a file
- [Delete File](https://docs.cloudglue.dev/api-reference/endpoint/files/delete.md): Delete a file
- [Extract from Video](https://docs.cloudglue.dev/api-reference/endpoint/extract/post.md): Extract structured data from a video
- [Get Extraction](https://docs.cloudglue.dev/api-reference/endpoint/extract/get.md): Retrieve the current state of an extraction job. Results are paginated with a default limit of 50 segment entities per request (maximum 100). Use limit and offset parameters to paginate through all segment entities.
- [List Extraction Jobs](https://docs.cloudglue.dev/api-reference/endpoint/extract/list.md): List all extract jobs with optional filtering
- [Delete Extraction](https://docs.cloudglue.dev/api-reference/endpoint/extract/delete.md): Delete an extraction job
- [Describe Video](https://docs.cloudglue.dev/api-reference/endpoint/describe/post.md): Get a comprehensive multimodal description of a video
- [Get Media Description](https://docs.cloudglue.dev/api-reference/endpoint/describe/get.md): Retrieve the current state of a media description job
- [Update Describe Job](https://docs.cloudglue.dev/api-reference/endpoint/describe/patch.md): Toggle the `use_in_default_index` flag on an existing describe job. Enabling this makes the file searchable by default in the deep search and response APIs.
- [List Media Descriptions](https://docs.cloudglue.dev/api-reference/endpoint/describe/list.md): List all media description jobs with optional filtering
- [Delete Media Description](https://docs.cloudglue.dev/api-reference/endpoint/describe/delete.md): Delete a media description job
- [Segment Video](https://docs.cloudglue.dev/api-reference/endpoint/segments/post.md): Create intelligent segments for video or audio files based on shot detection or narrative analysis.
- [Get Segments](https://docs.cloudglue.dev/api-reference/endpoint/segments/get.md): Retrieve the current state of a segmentation job
- [List Segments Jobs](https://docs.cloudglue.dev/api-reference/endpoint/segments/list.md): List all segmentation jobs with optional filtering
- [Delete Segments](https://docs.cloudglue.dev/api-reference/endpoint/segments/delete.md): Delete a specific segments job
- [Create Collection](https://docs.cloudglue.dev/api-reference/endpoint/collections/post.md): Create a new collection to organize and process video files. Collections are used to group files together and process them in a consistent way.
- [List Collections](https://docs.cloudglue.dev/api-reference/endpoint/collections/get.md): List all collections
- [Get Collection](https://docs.cloudglue.dev/api-reference/endpoint/collections/get-id.md): Retrieve details about a specific collection
- [Update Collection](https://docs.cloudglue.dev/api-reference/endpoint/collections/put-id.md): Update a collection
- [Delete Collection](https://docs.cloudglue.dev/api-reference/endpoint/collections/delete.md): Delete a collection
- [Add Video to Collection](https://docs.cloudglue.dev/api-reference/endpoint/collections/files-post.md): **DEPRECATED: Use POST /collections/\{collection_id\}/media instead.**
- [Add Media to Collection](https://docs.cloudglue.dev/api-reference/endpoint/collections/media-post.md): Add a video or audio file to a collection. This is the recommended endpoint for adding media files to collections.
- [Get Collection Video Info](https://docs.cloudglue.dev/api-reference/endpoint/collections/file-get.md): Retrieve information about a specific video file in a collection
- [List Videos in Collection](https://docs.cloudglue.dev/api-reference/endpoint/collections/files-get.md): List all files in a collection
- [Remove Video from Collection](https://docs.cloudglue.dev/api-reference/endpoint/collections/files-delete.md): Remove a video file from a collection
- [Create Response](https://docs.cloudglue.dev/api-reference/endpoint/responses/post.md): Create a new response using the Response API. This endpoint provides an OpenAI Responses-compatible interface for chat completions with video collections.
- [List Responses](https://docs.cloudglue.dev/api-reference/endpoint/responses/get.md): List all responses with pagination and filtering options.
- [Get Response](https://docs.cloudglue.dev/api-reference/endpoint/responses/get-id.md): Retrieve a specific response by its ID.
- [Delete Response](https://docs.cloudglue.dev/api-reference/endpoint/responses/delete.md): Delete a response by ID. This operation is idempotent - deleting a non-existent response returns success.
- [Cancel Response](https://docs.cloudglue.dev/api-reference/endpoint/responses/cancel.md): Cancel a background response that is in progress. If the response is already completed, failed, or cancelled, this returns the response as-is.
- [Create Deep Search](https://docs.cloudglue.dev/api-reference/endpoint/deep-search/post.md): Create a new deep search over one or more collections. Deep search uses agentic retrieval and LLM summarization to find specific moments across your video data.
- [List Deep Searches](https://docs.cloudglue.dev/api-reference/endpoint/deep-search/get.md): List all deep searches with pagination and filtering options.
- [Get Deep Search](https://docs.cloudglue.dev/api-reference/endpoint/deep-search/get-id.md): Retrieve a specific deep search by its ID.
- [Delete Deep Search](https://docs.cloudglue.dev/api-reference/endpoint/deep-search/delete.md): Delete a deep search by ID. This operation is idempotent - deleting a non-existent deep search returns success.
- [Cancel Deep Search](https://docs.cloudglue.dev/api-reference/endpoint/deep-search/cancel.md): Cancel a background deep search that is in progress. If the deep search is already completed, failed, or cancelled, this returns the deep search as-is.
- [Run Structured Query](https://docs.cloudglue.dev/api-reference/endpoint/query/post.md): Run a synchronous read-only SQL query over the structured data extracted from one or more collections. Queries execute against three virtual tables — files, entities, and segment_entities — built from each file's most recent completed extraction.
- [Get Query Schema](https://docs.cloudglue.dev/api-reference/endpoint/query/schema.md): Introspect the virtual tables and per-collection extracted fields available to SQL queries over the given collections. Use this to discover column names, entity field names, types, and levels, plus each collection's verbatim extract schema and prompt, before writing a query.
- [Get Query Result](https://docs.cloudglue.dev/api-reference/endpoint/query/get.md): Retrieve a stored query run by its ID, including its result rows. Results larger than the inline storage cap are replayed truncated (truncated: true).
- [List Query Results](https://docs.cloudglue.dev/api-reference/endpoint/query/list.md): List all query runs with pagination and filtering options. List items omit the columns and rows payloads — fetch an individual run via GET /query/{id} for the full result.
- [Cancel Query Export](https://docs.cloudglue.dev/api-reference/endpoint/query/cancel.md): Cancel an in-progress background export. The run is marked cancelled synchronously, the export stream is aborted mid-flight (the partial upload is discarded), and the reserved credits are refunded. A run that has already completed or failed is returned unchanged.
- [Search Content](https://docs.cloudglue.dev/api-reference/endpoint/search/post.md): Search for videos or video segments in collections to find relevant videos or moments/clips in a video
- [List Search Responses](https://docs.cloudglue.dev/api-reference/endpoint/search/get.md): Get a list of search responses. Order by `created_at` in descending order by default.
- [Get Search Response](https://docs.cloudglue.dev/api-reference/endpoint/search/get-id.md): Get a search response by search_id.
- [Chat Completions](https://docs.cloudglue.dev/api-reference/endpoint/chat/completions.md): Generate a model response to a conversation that can include references to video content
- [List Chat Completions](https://docs.cloudglue.dev/api-reference/endpoint/chat/completions-get.md): List all chat completions with optional filtering
- [Get Chat Completion](https://docs.cloudglue.dev/api-reference/endpoint/chat/completions-get-id.md): Retrieve a chat completion
- [Get Media Descriptions](https://docs.cloudglue.dev/api-reference/endpoint/collections/files-media-descriptions.md): 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'
- [Batch Fetch Media Descriptions](https://docs.cloudglue.dev/api-reference/endpoint/collections/list-collection-media-descriptions.md): List all media description data for files in a collection. This API is only available when a collection is created with collection_type 'media-descriptions'
- [Get Video Entities](https://docs.cloudglue.dev/api-reference/endpoint/collections/files-entities.md): Retrieve extracted entities for a specific file in a collection. Results are paginated with a default limit of 50 segment entities per request (maximum 100). Use limit and offset parameters to paginate through all results. This API is only available when the collection is created with collection_typ…
- [Batch Fetch Video Entities](https://docs.cloudglue.dev/api-reference/endpoint/collections/list-collection-entities.md): List all extracted entities for files in a collection. This API is only available when a collection is created with collection_type 'entities'
- [Get Video Face Detections](https://docs.cloudglue.dev/api-reference/endpoint/collections/files-face-detections.md): Retrieve face detections for a specific file in a collection. Results are paginated with a default limit of 50 faces per request (maximum 100). Use limit and offset parameters to paginate through all results. This API is only available when the collection is created with collection_type 'face-analys…
- [List File Thumbnails](https://docs.cloudglue.dev/api-reference/endpoint/files/thumbnails-get.md): Get all thumbnails for a file
- [Get Segmentation Thumbnails](https://docs.cloudglue.dev/api-reference/endpoint/segmentations/thumbnails-get.md): Get all thumbnails for a segmentation
- [Create File Segmentation](https://docs.cloudglue.dev/api-reference/endpoint/files/segmentations-post.md): Create a new segmentation for a file using the specified segmentation configuration
- [List File Segmentations](https://docs.cloudglue.dev/api-reference/endpoint/files/segmentations-get.md): List all segmentations for a specific file
- [Get Segmentation](https://docs.cloudglue.dev/api-reference/endpoint/segmentations/get.md): Retrieve details about a specific segmentation including its segments
- [Delete Segmentation](https://docs.cloudglue.dev/api-reference/endpoint/segmentations/delete.md): Delete a specific segmentation
- [List Segmentation Describes](https://docs.cloudglue.dev/api-reference/endpoint/segmentations/describes-list.md): List all describe jobs that referenced the specified segmentation. Returns describe job records associated with the segmentation.
- [Get File Segments](https://docs.cloudglue.dev/api-reference/endpoint/files/segments-get.md): Get a file segment
- [Update File Segments](https://docs.cloudglue.dev/api-reference/endpoint/files/segments-put.md): Update a file segment
- [List File Segments](https://docs.cloudglue.dev/api-reference/endpoint/files/segments-list.md): List all segments for a specific file
- [List Segment Describes](https://docs.cloudglue.dev/api-reference/endpoint/files/segment-describes-list.md): List all describe outputs for a specific file segment
- [Get Segment Describe](https://docs.cloudglue.dev/api-reference/endpoint/files/segment-describes-get.md): Get a specific describe output for a file segment by job ID
- [Create File Frame Extraction](https://docs.cloudglue.dev/api-reference/endpoint/files/frames-post.md): Create a new frame extraction for a file using the specified frame extraction configuration. This is an async operation that returns immediately with a 'pending' status. Results are cached, so identical requests will return the same frame extraction.
- [List File Frame Extractions](https://docs.cloudglue.dev/api-reference/endpoint/files/frames-get.md): List all frame extractions for a specific file
- [Get Frame Extraction](https://docs.cloudglue.dev/api-reference/endpoint/frames/get.md): Retrieve details about a specific frame extraction including its frames
- [Delete Frame Extraction](https://docs.cloudglue.dev/api-reference/endpoint/frames/delete.md): Delete a specific frame extraction
- [Find Face Match in Video](https://docs.cloudglue.dev/api-reference/endpoint/face-match/post.md): Search for a source face in a target video using facial recognition
- [Get Face Match Results](https://docs.cloudglue.dev/api-reference/endpoint/face-match/get.md): Retrieve face match results including detected faces and similarity scores
- [List Face Match Jobs](https://docs.cloudglue.dev/api-reference/endpoint/face-match/list.md): List all face match jobs
- [Delete Face Match Analysis](https://docs.cloudglue.dev/api-reference/endpoint/face-match/delete.md): Delete a specific face match analysis
- [Detect Faces in Video](https://docs.cloudglue.dev/api-reference/endpoint/face-detect/post.md): Analyze video to detect all faces
- [Get Face Detection Results](https://docs.cloudglue.dev/api-reference/endpoint/face-detect/get.md): Retrieve face detection results including all detected faces
- [List Face Detection Jobs](https://docs.cloudglue.dev/api-reference/endpoint/face-detect/list.md): List all face detection jobs
- [Delete Face Detection Analysis](https://docs.cloudglue.dev/api-reference/endpoint/face-detect/delete.md): Delete a specific face detection analysis
- [Create Shareable Asset](https://docs.cloudglue.dev/api-reference/endpoint/share/post.md): Create a shareable asset. Public assets (the default) are viewable by anyone with the link; private assets are restricted to members of the owning account and stream via a signed, token-gated playback url. A file (or file segment) can have at most one active share per visibility — one public and one…
- [Get Shareable Asset](https://docs.cloudglue.dev/api-reference/endpoint/share/get.md): Get a shareable asset
- [List Shareable Assets](https://docs.cloudglue.dev/api-reference/endpoint/share/list.md): List shareable assets
- [Update Shareable Asset](https://docs.cloudglue.dev/api-reference/endpoint/share/put.md): Update a shareable asset
- [Delete Shareable Asset](https://docs.cloudglue.dev/api-reference/endpoint/share/delete.md): Delete a shareable asset
- [Create Tag](https://docs.cloudglue.dev/api-reference/endpoint/tags/post.md): Create a new tag
- [List Tags](https://docs.cloudglue.dev/api-reference/endpoint/tags/get.md): List all tags
- [Get Tag](https://docs.cloudglue.dev/api-reference/endpoint/tags/get-id.md): Get a tag
- [Update Tag](https://docs.cloudglue.dev/api-reference/endpoint/tags/put.md): Update a tag
- [Delete Tag](https://docs.cloudglue.dev/api-reference/endpoint/tags/delete.md): Delete a tag
- [List File Tags](https://docs.cloudglue.dev/api-reference/endpoint/files/tags-get.md): List all tags for a specific file
- [List File Segment Tags](https://docs.cloudglue.dev/api-reference/endpoint/files/segment-tags-get.md): List all tags for a specific file segment
- [List Data Connectors](https://docs.cloudglue.dev/api-reference/endpoint/data-connectors/list.md): List all active data connectors configured for your account
- [List Data Connector Files](https://docs.cloudglue.dev/api-reference/endpoint/data-connectors/list-files.md): Browse files available in a connected data source. Returns URIs compatible with Cloudglue's file import system, and per-file provider metadata (see the `metadata` field) so you can inspect participants, hosts, durations, and AI summaries before importing. Supports pagination and filtering: `from`/`t…
- [Sync Data Connector File](https://docs.cloudglue.dev/api-reference/endpoint/data-connectors/sync.md): Materialize a connector URI (e.g. `grain://recording/<id>`) into a Cloudglue file without starting a downstream job. Idempotent: syncing the same URI returns the existing file. For Grain, Zoom, Recall, Google Drive, Dropbox, and Gong the file's `source_metadata` is populated from the provider (see t…
- [Get Data Connector Source Metadata](https://docs.cloudglue.dev/api-reference/endpoint/data-connectors/source-metadata.md): Fetch source metadata for a connector URI directly from the upstream source, without creating a Cloudglue file. Supported for Grain, Zoom, Recall, Google Drive, Dropbox, and Gong; S3/GCS return 501 (plain object stores have no richer metadata). Returns 502 when the upstream provider's response can't…
- [Create Webhook](https://docs.cloudglue.dev/api-reference/endpoint/webhooks/post.md): Create a webhook
- [List Webhooks](https://docs.cloudglue.dev/api-reference/endpoint/webhooks/get.md): List all webhooks
- [Get Webhook](https://docs.cloudglue.dev/api-reference/endpoint/webhooks/get-id.md): Get a webhook by ID
- [Update Webhook](https://docs.cloudglue.dev/api-reference/endpoint/webhooks/put.md): Update a webhook
- [Delete Webhook](https://docs.cloudglue.dev/api-reference/endpoint/webhooks/delete.md): Delete a webhook
- [Transcribe Video](https://docs.cloudglue.dev/api-reference/endpoint/transcribe/post.md): Creates a new transcription job for video content.
- [Get Transcript](https://docs.cloudglue.dev/api-reference/endpoint/transcribe/get.md): Retrieve the current state of a transcription job
- [List Transcripts](https://docs.cloudglue.dev/api-reference/endpoint/transcribe/list.md): List all transcription jobs with optional filtering
- [Get Rich Transcripts](https://docs.cloudglue.dev/api-reference/endpoint/collections/files-rich-transcripts.md): Retrieve rich transcription data for a specific file in a collection. This API is only available when the a collection is created with collection_type 'rich-transcripts'
- [Batch Fetch Rich Transcripts](https://docs.cloudglue.dev/api-reference/endpoint/collections/list-collection-rich-transcripts.md): List all rich transcription data for files in a collection. This API is only available when a collection is created with collection_type 'rich-transcripts'
- [Overview](https://docs.cloudglue.dev/sdks/overview.md): Cloudglue makes it easy to turn video into LLM ready data
- [JavaScript](https://docs.cloudglue.dev/sdks/javascript.md): The Cloudglue JavaScript SDK is a wrapper around the Cloudglue API which makes it easy to turn video into LLM ready data.
- [Python](https://docs.cloudglue.dev/sdks/python.md): Cloudglue Python SDK is a wrapper around the Cloudglue API which makes it easy to turn video into LLM ready data

## OpenAPI Specs

- [openapi](https://docs.cloudglue.dev/api-reference/openapi.json)
- [package](https://docs.cloudglue.dev/package.json)

## Optional

- [Playground](https://app.cloudglue.dev/home/playground)
- [Schema Builder](https://app.cloudglue.dev/tools/extract-schema-helper)
- [Changelog](https://docs.cloudglue.dev/changelog)