curl -X GET 'https://api.elevenlabs.io/v1/convai/users?agent_id=agent-id&branch_id=branch-id&call_start_before_unix=10&call_start_after_unix=10&search=example-search&page_size=30&sort_by=last_contact_unix_secs&sort_direction=asc&cursor=example-cursor' \
  -H "xi-api-key: $ELEVENLABS_API_KEY"

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

> Get Conversation Users

## 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 GET 'https://api.elevenlabs.io/v1/convai/users?agent_id=agent-id&branch_id=branch-id&call_start_before_unix=10&call_start_after_unix=10&search=example-search&page_size=30&sort_by=last_contact_unix_secs&sort_direction=asc&cursor=example-cursor' \
  -H "xi-api-key: $ELEVENLABS_API_KEY"

## Parameters
| Name | In | Type | Required | Description |
| :--- | :--- | :--- | :--- | :--- |
| agent_id | query | string | No | Agent id (agent_…) or speech engine external id (seng_),... |
| branch_id | query | string | No | Filter conversations by branch ID. |
| call_start_before_unix | query | integer | No | Unix timestamp (in seconds) to filter conversations up to... |
| call_start_after_unix | query | integer | No | Unix timestamp (in seconds) to filter conversations after... |

## Response (200 OK)
{"users":[{}],"next_cursor":"string"}

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

GET

/v1/convai/users

ElevenLabs API

Get Conversation Users

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
→ 232 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 GET 'https://api.elevenlabs.io/v1/convai/users?agent_id=agent-id&branch_id=branch-id&call_start_before_unix=10&call_start_after_unix=10&search=example-search&page_size=30&sort_by=last_contact_unix_secs&sort_direction=asc&cursor=example-cursor' \  -H "xi-api-key: $ELEVENLABS_API_KEY"

Get a free ElevenLabs API key → sponsored

Parameters

Name	In	Type	Required	Description
agent_id	query	string	No	Agent id (agent_…) or speech engine external id (seng_), resolved to the same underlying resource.
branch_id	query	string	No	Filter conversations by branch ID.
call_start_before_unix	query	integer	No	Unix timestamp (in seconds) to filter conversations up to this start date.
call_start_after_unix	query	integer	No	Unix timestamp (in seconds) to filter conversations after to this start date.
search	query	string	No	Search/filter by user ID (exact match).
page_size	query	integer	No	How many users to return at maximum. Defaults to 30.
sort_by	query	string	No	The field to sort the results by. Defaults to last_contact_unix_secs.
sort_direction	query	string	No	The direction to sort the results
cursor	query	string	No	Used for fetching next page. Cursor is returned in the response.

Response 200 OK

{
  "users": [
    {
      "user_id": "string",
      "last_contact_unix_secs": 0,
      "first_contact_unix_secs": 0,
      "conversation_count": 0,
      "last_contact_agent_id": "string",
      "last_contact_conversation_id": "string",
      "last_contact_agent_name": "string",
      "sentiment": {
        "scored_conversation_count": 0,
        "positive_count": 0,
        "neutral_count": 0,
        "negative_count": 0,
        "average_sentiment_score": 0,
        "average_frustration_score": 0,
        "recent_scored_conversation_count": 0,
        "recent_positive_count": 0,
        "recent_neutral_count": 0,
        "recent_negative_count": 0,
        "recent_average_sentiment_score": 0,
        "recent_average_frustration_score": 0
      },
      "most_frustrated_conversations": [
        {
          "conversation_id": "string",
          "agent_id": "string",
          "start_time_unix_secs": 0,
          "overall_label": "positive",
          "overall_sentiment_score": 0,
          "overall_frustration_score": 0
        }
      ]
    }
  ],
  "next_cursor": "string",
  "has_more": true
}