---
title: "Get Conversation Summary"
method: GET
path: "/v1/convai/conversations/{conversation_id}/summary"
tags: ["Agents Platform"]
---

# Get Conversation Summary

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

Get a lightweight summary of a conversation: its title, the generated transcript summary, whether the call was successful, and — only when the conversation is short — the plain chat messages. Tool calls, tool results, and contextual updates are omitted so the response stays small. Use this instead of the full conversation endpoint when you only need the gist (e.g. an agent reading many conversations); use GET /v1/convai/conversations/{conversation_id} when you need the full transcript with tool calls and contextual updates.

## Path parameters

- `conversation_id` string, required — The id of the conversation you're taking the action on.

## Query parameters

- `max_messages` integer — 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.

## Headers

- `xi-api-key` string, nullable — Your API key. This is required by most endpoints to access our API programmatically. You can view your xi-api-key using the 'Profile' tab on the website.

## Response `200`

Successful Response

- GetConversationSummaryResponseModel
  - `conversation_id` string, required
  - `agent_id` string, required
  - `status` 'initiated' | 'in-progress' | 'processing' | 'done' | 'failed', required
  - `call_summary_title` string, nullable — Short generated title for the conversation.
  - `transcript_summary` string, nullable — Generated natural-language summary of the call.
  - `call_successful` 'success' | 'failure' | 'unknown'
  - `message_count` integer, required — Number of plain chat message turns in the conversation.
  - `messages` ConversationSummaryMessageModel[], nullable — The plain chat messages (role and text only). Included only when message_count does not exceed the requested max_messages; otherwise null and messages_omitted is true.
    - `role` 'user' | 'agent', required
    - `message` string, required
  - `messages_omitted` boolean — True when the chat messages were omitted because the conversation was too long. Fetch the full transcript for the messages.
  - `note` string, required — Guidance telling the agent how to get the full transcript.

## Other responses

- `422` — Validation Error

---

[API](https://skmtc.net/elevenlabs/apis/elevenlabs-api-documentation.md) · [All operations](https://skmtc.net/elevenlabs/apis/elevenlabs-api-documentation/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/elevenlabs/elevenlabs-api-documentation/revisions/b96b80bcbb83/schema)