> This page is for version v1.3 (default).
> For other versions, use one of these documentation indexes:
> - v1.3 (default): https://docs.twelvelabs.io/v1.3/llms.txt

> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.twelvelabs.io/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.twelvelabs.io/_mcp/server.

# Embed content at scale

> Create embeddings for video, audio, images, and documents asynchronously.

Create embeddings for your media files. The platform processes your files asynchronously, one file per request, and you poll each request until it completes. Use this method for long files and large collections.

Choose the guide for the type of content you want to embed. The request differs for each type.

#### [Video embeddings](/v1.3/docs/guides/create-embeddings/at-scale/video)

Embed the visual and audio content of your videos.

#### [Audio embeddings](/v1.3/docs/guides/create-embeddings/at-scale/audio)

Embed your audio files.

#### [Image embeddings](/v1.3/docs/guides/create-embeddings/at-scale/image)

Embed your images.

#### [Document embeddings](/v1.3/docs/guides/create-embeddings/at-scale/document)

Embed your documents.

> **Retention policy**
>
> Embeddings created with the asynchronous method are stored for seven days. After this, you must recreate them to obtain the results again.