1. API Description

Domain name for API request: trtc.intl.tencentcloudapi.com.

Initiate AI conversation task, where the AI bot enters the TRTC room to engage in AI conversation with specified members in the room. This is suitable for scenarios such as intelligent customer service and AI language teachers. The TRTC AI conversation feature has built-in speech-to-text capabilities , allowing customers to flexibly specify third-party AI model (LLM) services and text-to-speech (TTS) services. For more feature details.

A maximum of 20 requests can be initiated per second for this API.

2. Input Parameters

The following request parameter list only provides API request parameters and some common parameters. For the complete common parameter list, see Common Request Parameters.

 { 
   "LLMType": "Large model type", // String required, such as: "openai" 
   "Model": "Your model name", // String required, specify the model to be used
 "APIKey": "Your LLM API key", // String required 
   "APIUrl": "https://api.xxx.com/chat/completions", // String required, URL for LLM API access
   "Streaming": true // Boolean optional, specify whether to use streaming
  } 

{ 
   "AppId": your application ID, // Integer Required
   "TTSType": "TTS type", // String TTS type, fixed to "tencent"
   "SecretId": "Your key ID", // String Required
   "SecretKey": "Your keyKey", // String Required
   "VoiceType": 101001, // Integer Required, voice ID, including standard voice and premium voice. Premium voice has higher fidelity and different price from standard voice. For details, please refer to Overview of Speech Synthesis Billing. For a complete list of timbre IDs, see List of speech synthesis timbre IDs. 
   "Speed": 1.25, // Integer Optional, speaking speed, range: [-2, 6], corresponding to different speaking speeds: -2: 0.6 times -1: 0.8 times 0: 1.0 times (default) 1: 1.2 times 2: 1.5 times 6: 2.5 times If a more detailed speaking speed is required, 2 decimal places can be retained, such as 0.5/1.25/2.81, etc. For the conversion between parameter value and actual speech speed, please refer to Speed Conversion
   "Volume": 5, // Integer Optional, volume size, range: [0, 10], corresponding to 11 levels of volume, the default value is 0, representing normal volume. 
   "PrimaryLanguage": "zh-CN" // String Optional, primary language
  }

3. Output Parameters

4. Example

Example1 Start an AI robot conversation task

Input Example

POST / HTTP/1.1
Host: trtc.intl.tencentcloudapi.com
Content-Type: application/json
X-TC-Action: StartAIConversation
<Common request parameters>

{
    "SdkAppId": 12345678,
    "RoomId": "room_987654321",
    "RoomIdType": 1,
    "AgentConfig": {
        "UserId": "user_12345",
        "UserSig": "user_signature_example",
        "MaxIdleTime": 120,
        "TargetUserId": "target_user_54321"
    },
    "SessionId": "session_1234567890abcdef",
    "STTConfig": {
        "Language": "en-US",
        "AlternativeLanguage": [
            "en-US",
            "zh"
        ]
    },
    "LLMConfig": "{\"LLMType\": \"openai\", \"Model\": \"gpt-3.5-turbo\", \"APIKey\": \"xxx\", \"APIUrl\": \"http://xxxx-api.woa.com/v1/chat/completions\", \"Streaming\": true}",
    "TTSConfig": "{\"TTSType\": \"tencent\", \"AppId\": 130000000, \"SecretId\": \"AKIDxxxxx\", \"SecretKey\": \"HlDxxxxxx\", \"VoiceType\": 1008, \"Speed\": 1}"
}

Output Example

{
    "Response": {
        "TaskId": "abc",
        "RequestId": "abc"
    }
}

5. Developer Resources

SDK

TencentCloud API 3.0 integrates SDKs that support various programming languages to make it easier for you to call APIs.

• Tencent Cloud SDK 3.0 for Python
• Tencent Cloud SDK 3.0 for Java
• Tencent Cloud SDK 3.0 for PHP
• Tencent Cloud SDK 3.0 for Go
• Tencent Cloud SDK 3.0 for Node.js
• Tencent Cloud SDK 3.0 for .NET
• Tencent Cloud SDK 3.0 for C++

Command Line Interface

• Tencent Cloud CLI 3.0

6. Error Code

The following only lists the error codes related to the API business logic. For other error codes, see Common Error Codes.