curl -X GET 'https://api.elevenlabs.io/v1/convai/conversations/conversation-id/summary?max_messages=40' \
  -H "xi-api-key: $ELEVENLABS_API_KEY"

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

> Get Conversation Summary

## 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/conversations/conversation-id/summary?max_messages=40' \
  -H "xi-api-key: $ELEVENLABS_API_KEY"

## Parameters
| Name | In | Type | Required | Description |
| :--- | :--- | :--- | :--- | :--- |
| conversation_id | path | string | Yes | The id of the conversation you're taking the action on. |
| max_messages | query | integer | No | Maximum number of chat message turns to include inline. W... |

## Response (200 OK)
{"conversation_id":"string","agent_id":"string"}

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

GET

/v1/convai/conversations/{conversation_id}/summary

ElevenLabs API

Get Conversation Summary

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
→ 192 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/conversations/conversation-id/summary?max_messages=40' \  -H "xi-api-key: $ELEVENLABS_API_KEY"

Get a free ElevenLabs API key → sponsored

Parameters

Name	In	Type	Required	Description
conversation_id	path	string	Yes	The id of the conversation you're taking the action on.
max_messages	query	integer	No	Maximum number of chat message turns to include inline. When the conversation has more than this, the messages are omitted and messages_omitted is set.

Response 200 OK

{
  "conversation_id": "string",
  "agent_id": "string",
  "status": "initiated",
  "call_summary_title": "string",
  "transcript_summary": "string",
  "call_successful": "success",
  "message_count": 0,
  "messages": [
    {
      "role": "user",
      "message": "string"
    }
  ],
  "messages_omitted": false,
  "note": "string"
}