TwelveLabs logo

TwelveLabs

TwelveLabs builds video-understanding foundation models (Marengo for search and embeddings, Pegasus for analyzing video and generating text). The TwelveLabs API lets developers upload and index video, run any-to-video semantic search, generate text from video (titles, topics, hashtags, summaries, chapters, highlights, and open-ended analysis), and create multimodal embeddings over a REST interface authenticated with an x-api-key header.

5 APIs 0 Features
AIVideo UnderstandingMultimodalSearchEmbeddings

APIs

TwelveLabs Indexes API

Create, list, retrieve, update, and delete video indexes, and manage the indexed videos within them. Each index is configured with the Marengo and/or Pegasus models and the visu...

TwelveLabs Tasks (Upload) API

Upload video by file or public URL and index it into a target index. Create, list, retrieve, and delete asynchronous video indexing tasks and poll their status (validating, pend...

TwelveLabs Search API

Any-to-video semantic search across an index using text and/or media (image) queries, powered by the Marengo model, with visual / audio / transcription search options, clip or v...

TwelveLabs Analyze / Generate API

Generate text from video with the Pegasus model - open-ended analysis via the sync /analyze endpoint (with optional NDJSON streaming), async analysis tasks for longer video, plu...

TwelveLabs Embed API

Create multimodal Marengo embeddings for text, image, audio, and video in one shared vector space - synchronously for short inputs and via asynchronous embedding tasks for longe...

Event Specifications

TwelveLabs Analyze Streaming (HTTP + NDJSON)

AsyncAPI 2.6 description of TwelveLabs' **analyze (text generation) streaming** surface. TwelveLabs does not publish a WebSocket API. The only asynchronous / event-style transpo...

ASYNCAPI

Resources

👥
GitHubOrganization
GitHubOrganization
🔗
LinkedIn
LinkedIn
🔗
Website
Website
🔗
Documentation
Documentation
🔗
Plans
Plans
🔗
RateLimits
RateLimits
🔗
FinOps
FinOps

Sources

Raw ↑
aid: twelvelabs
url: https://raw.githubusercontent.com/api-evangelist/twelvelabs/refs/heads/main/apis.yml
name: TwelveLabs
kind: company
description: TwelveLabs builds video-understanding foundation models (Marengo for
  search and embeddings, Pegasus for analyzing video and generating text). The
  TwelveLabs API lets developers upload and index video, run any-to-video semantic
  search, generate text from video (titles, topics, hashtags, summaries, chapters,
  highlights, and open-ended analysis), and create multimodal embeddings over a
  REST interface authenticated with an x-api-key header.
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
tags:
- AI
- Video Understanding
- Multimodal
- Search
- Embeddings
created: '2026-06-20'
modified: '2026-06-20'
specificationVersion: '0.19'
apis:
- aid: twelvelabs:twelvelabs-indexes-api
  name: TwelveLabs Indexes API
  tags:
  - Indexes
  - Videos
  - Catalog
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.twelvelabs.io/v1.3/api-reference/indexes/list
  baseURL: https://api.twelvelabs.io/v1.3
  properties:
  - url: https://docs.twelvelabs.io/v1.3/docs/concepts/indexes
    type: Documentation
  - url: https://docs.twelvelabs.io/v1.3/api-reference/indexes/list
    type: APIReference
  - url: openapi/twelvelabs-openapi.yml
    type: OpenAPI
  - url: collections/twelvelabs.postman_collection.json
    type: PostmanCollection
  description: Create, list, retrieve, update, and delete video indexes, and manage
    the indexed videos within them. Each index is configured with the Marengo
    and/or Pegasus models and the visual/audio modalities to enable.
- aid: twelvelabs:twelvelabs-tasks-upload-api
  name: TwelveLabs Tasks (Upload) API
  tags:
  - Tasks
  - Upload
  - Indexing
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.twelvelabs.io/v1.3/api-reference/upload-content/tasks/create
  baseURL: https://api.twelvelabs.io/v1.3
  properties:
  - url: https://docs.twelvelabs.io/v1.3/docs/filtering-indexes-and-tasks
    type: Documentation
  - url: https://docs.twelvelabs.io/v1.3/api-reference/upload-content/tasks/create
    type: APIReference
  - url: openapi/twelvelabs-openapi.yml
    type: OpenAPI
  - url: collections/twelvelabs.postman_collection.json
    type: PostmanCollection
  description: Upload video by file or public URL and index it into a target index.
    Create, list, retrieve, and delete asynchronous video indexing tasks and poll
    their status (validating, pending, indexing, ready, failed).
- aid: twelvelabs:twelvelabs-search-api
  name: TwelveLabs Search API
  tags:
  - Search
  - Semantic Search
  - Marengo
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.twelvelabs.io/v1.3/api-reference/any-to-video-search/make-search-request
  baseURL: https://api.twelvelabs.io/v1.3
  properties:
  - url: https://docs.twelvelabs.io/v1.3/docs/guides/search
    type: Documentation
  - url: https://docs.twelvelabs.io/v1.3/api-reference/any-to-video-search/make-search-request
    type: APIReference
  - url: openapi/twelvelabs-openapi.yml
    type: OpenAPI
  - url: collections/twelvelabs.postman_collection.json
    type: PostmanCollection
  description: Any-to-video semantic search across an index using text and/or media
    (image) queries, powered by the Marengo model, with visual / audio /
    transcription search options, clip or video grouping, and token-paginated
    results.
- aid: twelvelabs:twelvelabs-analyze-generate-api
  name: TwelveLabs Analyze / Generate API
  tags:
  - Analyze
  - Generate
  - Pegasus
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.twelvelabs.io/v1.3/api-reference/analyze-videos/analyze
  baseURL: https://api.twelvelabs.io/v1.3
  properties:
  - url: https://docs.twelvelabs.io/v1.3/docs/guides/generate-text-from-video/summaries-chapters-and-highlights
    type: Documentation
  - url: https://docs.twelvelabs.io/v1.3/api-reference/analyze-videos/analyze
    type: APIReference
  - url: openapi/twelvelabs-openapi.yml
    type: OpenAPI
  - url: asyncapi/twelvelabs-asyncapi.yml
    type: AsyncAPI
  - url: collections/twelvelabs.postman_collection.json
    type: PostmanCollection
  description: Generate text from video with the Pegasus model - open-ended analysis
    via the sync /analyze endpoint (with optional NDJSON streaming), async
    analysis tasks for longer video, plus gist (titles, topics, hashtags) and
    summarize (summaries, chapters, highlights) generation.
- aid: twelvelabs:twelvelabs-embed-api
  name: TwelveLabs Embed API
  tags:
  - Embeddings
  - Multimodal
  - Marengo
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.twelvelabs.io/v1.3/api-reference/create-embeddings-v2/create-embeddings
  baseURL: https://api.twelvelabs.io/v1.3
  properties:
  - url: https://www.twelvelabs.io/blog/introducing-twelve-labs-embed-api-open-beta
    type: Documentation
  - url: https://docs.twelvelabs.io/v1.3/api-reference/create-embeddings-v2/create-embeddings
    type: APIReference
  - url: openapi/twelvelabs-openapi.yml
    type: OpenAPI
  - url: collections/twelvelabs.postman_collection.json
    type: PostmanCollection
  description: Create multimodal Marengo embeddings for text, image, audio, and
    video in one shared vector space - synchronously for short inputs and via
    asynchronous embedding tasks for longer audio and video, for use in search,
    RAG, classification, and recommendation pipelines.
common:
- type: GitHubOrganization
  url: https://github.com/twelvelabs-io
- type: LinkedIn
  url: https://www.linkedin.com/company/twelvelabs
- type: Website
  url: https://www.twelvelabs.io
- type: Documentation
  url: https://docs.twelvelabs.io
- type: Plans
  url: plans/twelvelabs-plans-pricing.yml
- type: RateLimits
  url: rate-limits/twelvelabs-rate-limits.yml
- type: FinOps
  url: finops/twelvelabs-finops.yml
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com