> This is a page from the ElevenLabs documentation. For a complete page index, fetch https://elevenlabs.io/docs/llms.txt. For the full documentation in a single file, fetch https://elevenlabs.io/docs/llms-full.txt.

# Obtenir le résumé de la conversation

GET https://api.elevenlabs.io/v1/convai/conversations/{conversation_id}/summary

Obtenir un résumé synthétique d'une conversation : son titre, le résumé de transcription généré, si l'appel a réussi et, uniquement lorsque la conversation est courte, les messages de chat simples. Les appels d'outils, leurs résultats et les mises à jour contextuelles sont omis afin de limiter la taille de la réponse. Utilisez ceci plutôt que le point de terminaison de conversation complet lorsque vous avez uniquement besoin de l'essentiel, par exemple pour un agent lisant de nombreuses conversations ; utilisez GET /v1/convai/conversations/\{conversation\_id} lorsque vous avez besoin de la transcription complète avec les appels d'outils et les mises à jour contextuelles.

Reference: https://elevenlabs.io/docs/eleven-agents/api-reference/conversations/get-summary

## Servers

- `https://api.elevenlabs.io` (Production, default)
- `https://api.us.elevenlabs.io` (Production US)
- `https://api.eu.residency.elevenlabs.io` (Production EU)
- `https://api.in.residency.elevenlabs.io` (Production India)
- `https://api.sg.residency.elevenlabs.io` (Production Singapore)

## Request

### Path parameters

- `conversation_id` (string, required) — L’ID de la conversation sur laquelle vous effectuez l’action.

### Query parameters

- `max_messages` (integer, optional, default: 40) — 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

Réponse réussie

- `conversation_id` (string, required)
- `agent_id` (string, required)
- `status` (enum, required)
  - Allowed values: `initiated`, `in-progress`, `processing`, `done`, `failed`
- `message_count` (integer, required) — Nombre de tours de messages de chat simples dans la conversation.
- `note` (string, required) — Instructions indiquant à l’agent comment obtenir la transcription complète.
- `call_summary_title` (string, optional) — Titre court généré pour la conversation.
- `transcript_summary` (string, optional) — Résumé généré de l'appel en langage naturel.
- `call_successful` (enum, optional)
  - Allowed values: `success`, `failure`, `unknown`
- `messages` (list of ConversationSummaryMessageModel, optional) — Les messages de chat bruts, rôle et texte uniquement. Inclus uniquement lorsque message_count ne dépasse pas max_messages demandé ; sinon, la valeur est null et messages_omitted est true.
- `messages_omitted` (boolean, optional, default: false) — True lorsque les messages de chat ont été omis parce que la conversation était trop longue. Récupérez la transcription complète pour obtenir les messages.

## Errors

### 422 Conversations Get Summary Request Unprocessable Entity Error

Erreur de validation

- `detail` (list of ValidationError, optional)

## Types

### ConversationSummaryMessageModel

- `role` (enum, required)
  - Allowed values: `user`, `agent`
- `message` (string, required)

### ValidationError

- `loc` (list of ValidationErrorLocItem, required)
- `msg` (string, required)
- `type` (string, required)

### ValidationErrorLocItem

- string
- integer

## Examples

**Response**

```json
{
  "conversation_id": "conversation_id",
  "agent_id": "agent_id",
  "status": "initiated",
  "message_count": 1,
  "note": "note",
  "call_summary_title": "call_summary_title",
  "transcript_summary": "transcript_summary",
  "call_successful": "success",
  "messages": [
    {
      "role": "user",
      "message": "message"
    }
  ],
  "messages_omitted": true
}
```

**SDK Code**

```python
import requests

url = "https://api.elevenlabs.io/v1/convai/conversations/21m00Tcm4TlvDq8ikWAM/summary"

querystring = {"max_messages":"1"}

response = requests.get(url, params=querystring)

print(response.json())
```

```javascript
const url = 'https://api.elevenlabs.io/v1/convai/conversations/21m00Tcm4TlvDq8ikWAM/summary?max_messages=1';
const options = {method: 'GET'};

try {
  const response = await fetch(url, options);
  const data = await response.json();
  console.log(data);
} catch (error) {
  console.error(error);
}
```

```go
package main

import (
	"fmt"
	"net/http"
	"io"
)

func main() {

	url := "https://api.elevenlabs.io/v1/convai/conversations/21m00Tcm4TlvDq8ikWAM/summary?max_messages=1"

	req, _ := http.NewRequest("GET", url, nil)

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(res)
	fmt.Println(string(body))

}
```

```ruby
require 'uri'
require 'net/http'

url = URI("https://api.elevenlabs.io/v1/convai/conversations/21m00Tcm4TlvDq8ikWAM/summary?max_messages=1")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Get.new(url)

response = http.request(request)
puts response.read_body
```

```java
import com.mashape.unirest.http.HttpResponse;
import com.mashape.unirest.http.Unirest;

HttpResponse<String> response = Unirest.get("https://api.elevenlabs.io/v1/convai/conversations/21m00Tcm4TlvDq8ikWAM/summary?max_messages=1")
  .asString();
```

```php
<?php
require_once('vendor/autoload.php');

$client = new \GuzzleHttp\Client();

$response = $client->request('GET', 'https://api.elevenlabs.io/v1/convai/conversations/21m00Tcm4TlvDq8ikWAM/summary?max_messages=1');

echo $response->getBody();
```

```csharp
using RestSharp;

var client = new RestClient("https://api.elevenlabs.io/v1/convai/conversations/21m00Tcm4TlvDq8ikWAM/summary?max_messages=1");
var request = new RestRequest(Method.GET);
IRestResponse response = client.Execute(request);
```

```swift
import Foundation

let request = NSMutableURLRequest(url: NSURL(string: "https://api.elevenlabs.io/v1/convai/conversations/21m00Tcm4TlvDq8ikWAM/summary?max_messages=1")! as URL,
                                        cachePolicy: .useProtocolCachePolicy,
                                    timeoutInterval: 10.0)
request.httpMethod = "GET"

let session = URLSession.shared
let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in
  if (error != nil) {
    print(error as Any)
  } else {
    let httpResponse = response as? HTTPURLResponse
    print(httpResponse)
  }
})

dataTask.resume()
```