> 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.

# 列出会话

GET https://api.elevenlabs.io/v1/convai/conversations

获取用户拥有的智能体的所有对话。可选择仅获取指定智能体的对话。

Reference: https://elevenlabs.io/docs/api-reference/conversations/list

## 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

### Query parameters

- `cursor` (string, optional, nullable) — 用于获取下一页。响应中会返回游标。
- `agent_id` (string, optional, nullable) — 智能体 id（agent_…）或语音引擎外部 id（seng_），均会解析为同一底层资源。
- `visited_agent_ids` (list of string, optional, nullable) — 筛选任一指定智能体参与过的对话。最多不超过 50 个值。
- `visited_agent_branch_ids` (list of string, optional, nullable) — 筛选任一指定智能体分支参与过的对话。最多不超过 50 个值。
- `triggered_procedure_ids` (list of string, optional, nullable) — 筛选触发过任一指定流程的对话。最多不超过 50 个值。
- `call_successful` (enum, optional, nullable) — 成功评估结果
  - Allowed values: `success`, `failure`, `unknown`, `error`
- `call_start_before_unix` (integer, optional, nullable) — 用于筛选截至此开始日期对话的 Unix 时间戳（秒）。
- `call_start_after_unix` (integer, optional, nullable) — 用于筛选此开始日期之后对话的 Unix 时间戳（秒）。
- `call_duration_min_secs` (integer, optional, nullable) — 最短通话时长，单位为秒。
- `call_duration_max_secs` (integer, optional, nullable) — 最长通话时长，单位为秒。
- `rating_max` (integer, optional, nullable) — 总体评分上限（1-5）。
- `rating_min` (integer, optional, nullable) — 总体评分下限（1-5）。
- `has_feedback_comment` (boolean, optional, nullable) — 筛选含有用户反馈评论的对话。
- `user_id` (string, optional, nullable) — 按发起对话的用户 ID 筛选对话。
- `evaluation_params` (list of string, optional, nullable) — 评估筛选条件。可重复传入此参数。格式：criteria_id:result，其中 result 为 success|failure|unknown 之一。示例：eval=value_framing:success
- `data_collection_params` (list of string, optional, nullable) — 数据收集筛选条件。可重复使用该参数。格式：id:op:value，其中 op 为 eq|neq|gt|gte|lt|lte|in 之一。对于 in，使用竖线分隔值。空值匹配未收集该字段的对话（id:eq:）；使用空值的 neq 匹配已收集该字段的对话（id:neq:）。eq 表示完全相等。gt|gte|lt|lte 需要数值。
- `dynamic_variable_params` (list of string, optional, nullable) — 动态变量筛选条件。可重复使用该参数。格式：name:op:value，其中 op 为 eq|neq|gt|gte|lt|lte|in 之一。对于 in，值以竖线分隔。空值匹配未设置该变量的对话（name:eq:），使用空值的 neq 则匹配已设置该变量的对话（name:neq:）。eq 表示完全相等。gt|gte|lt|lte 需要数值。名称中包含 ':' 时无法表示。
- `data_collection_ids` (list of string, optional, nullable) — 要包含在每个对话摘要中的数据收集字段 ID。可重复使用该参数。省略时，不返回 data_collection_results。
- `evaluation_criteria_ids` (list of string, optional, nullable) — 要包含在每个对话摘要中的评估标准 ID。可重复传入此参数。省略时，不会返回 evaluation_criteria_results。
- `tool_names` (list of string, optional, nullable) — 按通话期间使用的工具名称筛选对话。
- `tool_names_successful` (list of string, optional, nullable) — 按调用成功的工具名称筛选对话。
- `tool_names_errored` (list of string, optional, nullable) — 按调用出错的工具名称筛选对话。
- `include_invalid_tool_calls` (boolean, optional, default: false) — 同时匹配从未运行的工具调用。
- `main_languages` (list of string, optional, nullable) — 按检测到的主要语言（语言代码）筛选对话。
- `page_size` (integer, optional, default: 30) — 最多返回的对话数量。不能超过 100，默认为 30。
- `summary_mode` (enum, optional, default: exclude) — 是否在响应中包含转录摘要。
  - Allowed values: `exclude`, `include`
- `search` (string, optional, nullable, deprecated) — 对转录消息进行全文或模糊搜索
- `conversation_initiation_source` (enum, optional, nullable, default: unknown) — 表示对话发起来源的枚举。
  - Allowed values: `unknown`, `android_sdk`, `node_js_sdk`, `react_native_sdk`, `react_sdk`, `js_sdk`, `python_sdk`, `widget`, `sip_trunk`, `twilio`, `exotel`, `genesys`, `avaya`, `audiocodes`, `swift_sdk`, `whatsapp`, `twilio_sms`, `flutter_sdk`, `zendesk_integration`, `slack_integration`, `telegram_integration`, `intercom_integration`, `freshdesk_integration`, `salesforce_integration`, `template_preview`, `genesys_bot_connector`, `subagent_tool`
- `text_only` (boolean, optional, nullable)
- `conversation_product_type` (enum, optional, nullable) — 将结果限制为单个对话产品界面。
  - Allowed values: `agents`, `speech_engine`
- `branch_id` (string, optional, nullable) — 按分支 ID 筛选对话。
- `version_id` (string, optional, nullable) — 按版本 ID 筛选对话。
- `parent_conversation_id` (string, optional, nullable) — 按子智能体对话的父对话 ID 筛选对话。
- `topic_ids` (list of string, optional, nullable) — 按主题发现期间分配的主题 ID 筛选对话。
- `exclude_statuses` (list of enum, optional, nullable) — 排除具有指定状态的对话。适用于在列表视图中隐藏进行中/处理中对话。
  - Allowed values: `initiated`, `in-progress`, `processing`, `done`, `failed`
- `tag_ids` (list of string, optional, nullable) — 按通过 conversation-tags 端点分配的对话标签 ID 筛选对话。
- `workflow_node_entered_id` (string, optional, nullable) — 仅筛选进入指定节点的对话。
- `termination_reasons` (list of string, optional, nullable) — 按存储的 termination_reason（metadata.termination_reason）筛选对话。重复传入参数可匹配多个值中的任意一个。
- `guardrail_types` (list of enum, optional, nullable) — 筛选触发过任一指定类型护栏的对话（metadata.triggered_guardrails.guardrail_type）。重复传入参数可匹配多个值中的任意一个。
  - Allowed values: `custom`, `prompt_injection`, `self_harm_intent`, `violence_graphic`, `sexual`, `violence`, `harassment`, `sexual_minors`, `self_harm`, `self_harm_instructions`, `harassment_threatening`, `hate`, `hate_threatening`, `profanity`, `religion_or_politics`, `medical_and_legal`, `guardrail`
- `custom_guardrail_names` (list of string, optional, nullable) — 筛选触发过任一指定名称的自定义护栏的对话（metadata.triggered_guardrails.guardrail_name）。只有自定义护栏具有名称。重复传入参数可匹配多个值中的任意一个。
- `sort_direction` (enum, optional) — 按通话开始时间排序对话的方向。默认为降序（最新优先）。
  - Allowed values: `asc`, `desc`

## Response

### 200

成功响应

- `conversations` (list of ConversationSummaryResponseModel, required)
- `has_more` (boolean, required)
- `next_cursor` (string, optional, nullable)

## Errors

### 422 Unprocessable Entity Error

验证错误。

- `detail` (list of ValidationError, optional)

## Types

### ConversationSummaryResponseModel

- `agent_id` (string, required)
- `conversation_id` (string, required)
- `start_time_unix_secs` (integer, required)
- `call_duration_secs` (integer, required)
- `message_count` (integer, required)
- `status` (enum, required)
  - Allowed values: `initiated`, `in-progress`, `processing`, `done`, `failed`
- `call_successful` (enum, required)
  - Allowed values: `success`, `failure`, `unknown`
- `branch_id` (string, optional, nullable)
- `version_id` (string, optional, nullable)
- `agent_name` (string, optional, nullable)
- `termination_reason` (string, optional, default: )
- `call_success_score` (double, optional, nullable)
- `transcript_summary` (string, optional, nullable)
- `call_summary_title` (string, optional, nullable)
- `main_language` (string, optional, nullable)
- `conversation_initiation_source` (enum, optional, nullable, default: unknown) — 表示对话发起来源的枚举。
  - Allowed values: `unknown`, `android_sdk`, `node_js_sdk`, `react_native_sdk`, `react_sdk`, `js_sdk`, `python_sdk`, `widget`, `sip_trunk`, `twilio`, `exotel`, `genesys`, `avaya`, `audiocodes`, `swift_sdk`, `whatsapp`, `twilio_sms`, `flutter_sdk`, `zendesk_integration`, `slack_integration`, `telegram_integration`, `intercom_integration`, `freshdesk_integration`, `salesforce_integration`, `template_preview`, `genesys_bot_connector`, `subagent_tool`
- `tool_names` (list of string, optional, nullable)
- `direction` (enum, optional, nullable, default: inbound)
  - Allowed values: `inbound`, `outbound`
- `rating` (double, optional, nullable)
- `sentiment_analysis` (ConversationSentimentAnalysis, optional, nullable)
- `data_collection_results` (map from string to any, optional, nullable)
- `evaluation_criteria_results` (map from string to EvaluationCriteriaSummaryResult, optional, nullable)
- `tag_ids` (list of string, optional) — 分配给此对话的对话标签 ID。

### ValidationError

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

### ConversationSentimentAnalysis

- `overall_label` (enum, required)
  - Allowed values: `positive`, `neutral`, `negative`
- `overall_sentiment_score` (double, required)
- `overall_frustration_score` (double, required)
- `min_user_sentiment_score` (double, required)
- `max_user_frustration_score` (double, required)
- `num_scored_user_turns` (integer, required)

### EvaluationCriteriaSummaryResult

- `result` (enum, required)
  - Allowed values: `success`, `failure`, `unknown`
- `score` (integer, optional, nullable)
- `max_score` (integer, optional, nullable)

### ValidationErrorLocItems

- string
- integer

## Examples

**Response**

```json
{
  "conversations": [
    {
      "agent_id": "string",
      "conversation_id": "string",
      "start_time_unix_secs": 1,
      "call_duration_secs": 1,
      "message_count": 1,
      "status": "initiated",
      "call_successful": "success",
      "branch_id": "string",
      "version_id": "string",
      "agent_name": "string",
      "termination_reason": "",
      "call_success_score": 1.1,
      "transcript_summary": "string",
      "call_summary_title": "string",
      "main_language": "string",
      "conversation_initiation_source": "unknown",
      "tool_names": [
        "string"
      ],
      "direction": "inbound",
      "rating": 1.1,
      "sentiment_analysis": {
        "overall_label": "positive",
        "overall_sentiment_score": 0,
        "overall_frustration_score": 0.5,
        "min_user_sentiment_score": 0,
        "max_user_frustration_score": 0.5,
        "num_scored_user_turns": 1
      },
      "data_collection_results": {},
      "evaluation_criteria_results": {},
      "tag_ids": [
        "string"
      ]
    }
  ],
  "has_more": true,
  "next_cursor": "string"
}
```

**SDK Code**

```python
import requests

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

querystring = {"agent_id":"agent_3701k3ttaq12ewp8b7qv5rfyszkz","call_successful":"success"}

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

print(response.json())
```

```javascript
const url = 'https://api.elevenlabs.io/v1/convai/conversations?agent_id=agent_3701k3ttaq12ewp8b7qv5rfyszkz&call_successful=success';
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?agent_id=agent_3701k3ttaq12ewp8b7qv5rfyszkz&call_successful=success"

	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?agent_id=agent_3701k3ttaq12ewp8b7qv5rfyszkz&call_successful=success")

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?agent_id=agent_3701k3ttaq12ewp8b7qv5rfyszkz&call_successful=success")
  .asString();
```

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

$client = new \GuzzleHttp\Client();

$response = $client->request('GET', 'https://api.elevenlabs.io/v1/convai/conversations?agent_id=agent_3701k3ttaq12ewp8b7qv5rfyszkz&call_successful=success');

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

```csharp
using RestSharp;

var client = new RestClient("https://api.elevenlabs.io/v1/convai/conversations?agent_id=agent_3701k3ttaq12ewp8b7qv5rfyszkz&call_successful=success");
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?agent_id=agent_3701k3ttaq12ewp8b7qv5rfyszkz&call_successful=success")! 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()
```