For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
Sample appsIntegrationsDiscordPlaygroundDevEx repo
GuidesSDK ReferenceAPI Reference
GuidesSDK ReferenceAPI Reference
  • TwelveLabs API
    • Introduction
    • Authentication
  • API Reference
    • Manage indexes
    • Upload content
    • Index content
    • Manage videos
    • Manage entities
    • Any-to-video search
    • Create embeddings v2
      • POSTCreate sync embeddings
      • POSTCreate an async embedding task
      • GETList async embedding tasks
      • GETRetrieve task status and results
    • Create embeddings v1
    • Analyze and segment videos
    • Error codes
LogoLogo
Sample appsIntegrationsDiscordPlaygroundDevEx repo
On this page
  • Choose an endpoint
API Reference

Create embeddings v2

Was this page helpful?
Previous

Create sync embeddings

Next
Built with

Use the Embed API v2 to create embeddings for text, images, audio, and video content. Embeddings are vector representations that enable semantic search and content understanding.

Choose an endpoint

  • For text, images, or audio/video under 10 minutes use the POST method of the /embed-v2 endpoint.
  • For audio and video up to 4 hours, use the POST method of the /embed-v2/tasks endpoint.
Retention policy

Embeddings created through the async endpoints (/embed-v2/tasks) are stored for seven days. After this period, you must recreate the embedding task to obtain the results again.