> 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.

# Create embeddings v2

> Create vector embeddings for text, images, audio, video, and documents. Enable semantic search and content understanding.

Use the `Embed.V2` interface to create embeddings for text, images, audio, video, and documents. Embeddings are vector representations that enable semantic search and content understanding.

# Choose a method

#### [Create sync embeddings](/v1.3/sdk-reference/node-js/create-embeddings-v-2/create-sync-embeddings#create-embeddings)

Embed a query for retrieving matching content with the `embed.v2.create` method. It returns the result immediately and accepts text, images, and audio or video up to 30 seconds with Marengo 3.5.

#### [Create an async embedding task](/v1.3/sdk-reference/node-js/create-embeddings-v-2/create-async-embeddings#create-an-async-embedding-task)

Embed content at scale, such as the media files you want to make searchable, with the `embed.v2.tasks.create` method. It runs in the background and accepts audio, video, images, and 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.