curl -X POST 'https://api.elevenlabs.io/v1/convai/knowledge-base/crawl' \
  -H "xi-api-key: $ELEVENLABS_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "url": "string",
  "max_depth": 3,
  "max_pages": 1000,
  "pattern": "string",
  "sitemap_urls": [
    "string"
  ],
  "parent_folder_id": "string",
  "enable_auto_sync": false,
  "auto_remove": false,
  "minimum_frequency_days": 0
}'

# POST /v1/convai/knowledge-base/crawl (ElevenLabs API)
Base URL: https://api.elevenlabs.io
Auth: xi-api-key: <ELEVENLABS_API_KEY>
Last verified: 2026-09-03

> Create Crawl Job

## Critical Gotchas
* Authentication uses the non-standard `xi-api-key` header, not `Authorization: Bearer`. Sending a Bearer token returns HTTP 401.
* Text-to-speech responses are raw binary audio, not JSON. Write the body to a file (`--output speech.mp3`) rather than parsing it.

## cURL
curl -X POST 'https://api.elevenlabs.io/v1/convai/knowledge-base/crawl' \
  -H "xi-api-key: $ELEVENLABS_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{"url":"string","max_depth":3}'

## Parameters
| Name | In | Type | Required | Description |
| :--- | :--- | :--- | :--- | :--- |
| url | body | string | Yes | URL to a page of documentation that t... |
| max_depth | body | integer | No | Maximum depth for crawling (1-5), def... |
| max_pages | body | integer | No | Maximum number of pages to crawl (1-1... |

## Response (200 OK)
{"id":"string","type":"discovery"}

---
Need an API key? Get one at https://elevenlabs.io/app/sign-up

POST

/v1/convai/knowledge-base/crawl

ElevenLabs API

Create Crawl Job

Base URL: https://api.elevenlabs.io
Auth: xi-api-key: <ELEVENLABS_API_KEY>
Last verified: 2026-09-03 · upstream hash matched

Actions

Agents: curl -H "Accept: text/markdown" this URL
→ 215 tokens · Vary: Accept

Critical gotchas

Authentication uses the non-standard xi-api-key header, not Authorization: Bearer. Sending a Bearer token returns HTTP 401.

Text-to-speech responses are raw binary audio, not JSON. Write the body to a file (--output speech.mp3) rather than parsing it.

cURL

curl -X POST 'https://api.elevenlabs.io/v1/convai/knowledge-base/crawl' \  -H "xi-api-key: $ELEVENLABS_API_KEY" \  -H 'Content-Type: application/json' \  -d '{  "url": "string",  "max_depth": 3,  "max_pages": 1000,  "pattern": "string",  "sitemap_urls": [    "string"  ],  "parent_folder_id": "string",  "enable_auto_sync": false,  "auto_remove": false,  "minimum_frequency_days": 0}'

Get a free ElevenLabs API key → sponsored

Parameters

Name	In	Type	Required	Description
url	body	string	Yes	URL to a page of documentation that the agent will have access to in order to interact with users.
max_depth	body	integer	No	Maximum depth for crawling (1-5), defaults to 3.
max_pages	body	integer	No	Maximum number of pages to crawl (1-10,000), defaults to 1000.
pattern	body	string	No	If set, only URLs that match this pattern are included.
sitemap_urls	body	string[]	No	List of URLs to crawl from sitemap (optional, overrides automatic URL discovery).
parent_folder_id	body	string	No	If set, the created document or folder will be placed inside the given folder.
enable_auto_sync	body	boolean	No	Whether to enable auto-sync for this URL document.
auto_remove	body	boolean	No	Whether to automatically remove the document if the URL becomes unavailable. Only applicable when auto-sync is enabled.
minimum_frequency_days	body	integer	No	Minimum frequency (in days) at which the underlying eligible documents are refreshed. The actual interval may be shorter, never longer. Defaults to 7, tightened to the parent folder's frequency if that is stricter. Only applicable when auto-sync is enabled.

Response 200 OK

{
  "id": "string",
  "type": "discovery",
  "root_folder_id": "string",
  "status": "string",
  "created_at": 0,
  "folder_path": [
    {
      "id": "string"
    }
  ]
}