RegisterAgent

POST

https://aigc-aiagent-api.zegotech.cn/

By calling this API, you can register an AI agent (Agent) for creating AI agent instances.

Request

Query Parameters

Action stringrequired

Possible values: [RegisterAgent]

AppId uint32required

The unique Application ID assigned to your project by ZEGOCLOUD. Get it from the ZEGOCLOUD Admin Console.

SignatureNonce stringrequired

Random string.

Timestamp int64required

Unix timestamp, in seconds. The maximum allowed error is 10 minutes.

Signature stringrequired

Signature, used to verify the legitimacy of the request. Refer to Signing the requests for how to generate an API request signature.

SignatureVersion stringrequired

Possible values: [2.0]

Signature version number, default value is 2.0.

application/json

Body

required

AgentId stringrequired

Possible values: <= 128 characters

Only supports numbers, English characters, and the following special characters: !#$%&()+-:;<=.>?@[]^_{}|~,.

Name string

Possible values: <= 256 characters

AI Agent name, with a maximum length of 256 bytes.

LLM objectrequired

Url stringrequired

The endpoint that receives the request (can be your own service or any LLM service provider's service) and must be compatible with OpenAI Chat Completions API.

For example: https://api.openai.com/v1/chat/completions

ApiKey string

The parameter used for authentication by the LLM service provider. It is empty by default, but must be provided in production environments.

Model stringrequired

The LLM model. Different LLM service providers support different models, please refer to their official documentation to select the appropriate model.

SystemPrompt string

The system prompt of the AI agent. It is the predefined information that is added at the beginning when calling the LLM, used to control the output of the LLM. It can be role settings, prompts, and answer examples.

Temperature number

Possible values: >= 0 and <= 2

Default value: 0.7

The higher the value, the more random the output; the lower the value, the more concentrated and determined the output.

TopP number

Possible values: >= 0 and <= 1

Default value: 0.9

The sampling method. The smaller the value, the stronger the determinism; the larger the value, the stronger the randomness.

Params object

Other parameters supported by the LLM service provider, such as the maximum token limit. Different LLM providers support different parameters, please refer to their official documentation and fill in as needed.

AddAgentInfo boolean

Default value: false

If this value is true, the AI Agent server will include the AI agent information in the request parameters when requesting the LLM service. You can use this parameter to execute additional business logic in your custom LLM service.

The structure of agent_info is as follows:

room_id: RTC room ID
user_id: User ID
agent_instance_id: AI agent instance ID

TTS objectrequired

Vendor stringrequired

Possible values: [Aliyun, ByteDance, ByteDanceFlowing, MiniMax, CosyVoice]

The TTS service provider. Options:

Aliyun: Aliyun
ByteDance: ByteDance (Volcano Voice - Large Model Speech Synthesis API)
ByteDanceFlowing: ByteDance (Volcano Voice - Streaming Speech Synthesis API (WebSocket))
MiniMax: MiniMax
CosyVoice: Aliyun CosyVoice

Params objectrequired

TTS configuration parameters, in JSON object format. Contains app parameters (for authentication) and other parameters (for adjusting TTS effects).

In addition to the app parameter, you can also pass in other TTS configuration parameters to adjust the speech synthesis effect. These parameters will be directly passed to the corresponding TTS service provider.

You can refer to the official documentation of the service provider for the required information according to the value of Vendor.

- Aliyun: Intelligent Speech Interaction - Overview of speech synthesis - 2. Start the synthesis task

- ByteDance: Large Model Speech Synthesis API - Parameter List - Request Parameters

- ByteDanceFlowing: "Payload request parameters" in Streaming Text-to-Speech API (WebSocket) - WebSocket Binary Protocol

- MiniMax: Voice Model - T2A v2 - WebSocket API - Interface Parameters

- CosyVoice: "Payload request parameters" in CosyVoice WebSocket API for Speech Synthesis

app object required

The TTS service authentication parameter, which is different for different Vendor values. Please refer to the requirements of each vendor for the structure of the app parameter.

oneOf

Aliyun
ByteDance
ByteDanceFlowing
MiniMax
CosyVoice

app_key stringrequired

Read the Alibaba Cloud docs Intelligent Speech Interaction - Create a project to create a project and get the AppKey from the Intelligent Speech Interaction console, and pass it here.

ak_id stringrequired

Read the Alibaba Cloud docs Intelligent Speech Interaction - Activate Intelligent Speech Interaction - Procedure to obtain the AccessKey ID and pass it here.

ak_key stringrequired

Read the Alibaba Cloud docs Intelligent Speech Interaction - Activate Intelligent Speech Interaction - Procedure to obtain the AccessKey Secret and pass it here.

appid stringrequired

Read the BytePlus docs Voice Technology - Quick Start - Console Usage FAQ under "Where can I get the following parameters: appid, cluster, token, authorization_type, secret_key?".

token stringrequired

Read the BytePlus docs Voice Technology - Quick Start - Console Usage FAQ under "Where can I get the following parameters: appid, cluster, token, authorization_type, secret_key?".

cluster required

Possible values: [volcano_tts, volcano_mega, volcano_icl]

Default value: volcano_tts

BytePlus cluster configuration

appid stringrequired

Read the BytePlus Voice docs Voice Console Guide - Step 2: Trial Use to get the App ID, and pass it here.

token stringrequired

Read the BytePlus Voice docs Voice Console Guide - Step 2: Trial Use to get the App ID, and pass it here.

resource_id required

Possible values: [volc.service_type.10029, volc.megatts.default, volc.megatts.concurr]

Default value: volc.service_type.10029

BytePlus resource ID

voice string

The voice of the speaker, default is xiaoyun. Except for the app parameter, the other parameters are only for demonstration of the transparent transmission parameter level. You can add or delete them according to your own needs.

volume number

Possible values: >= 0 and <= 100

The volume, range [0, 100]. Except for the app parameter, the other parameters are only for demonstration of the transparent transmission parameter level. You can add or delete them according to your own needs.

speech_rate number

Possible values: >= -500 and <= 500

The speech rate, range [-500, 500]. Except for the app parameter, the other parameters are only for demonstration of the transparent transmission parameter level. You can add or delete them according to your own needs.

FilterText object[]

Filter the text within the specified punctuation marks from the content returned by the LLM, and then perform speech synthesis.Note:- The content that should be placed within the specified punctuation marks must be defined in LLM > SystemPrompt.- This parameter cannot be updated when updating the AI agent instance.

Array[

BeginCharacters stringrequired

The start punctuation mark of the filtered text. For example, if you want to filter the content in (), set it to (.

EndCharacters stringrequired

The end punctuation mark of the filtered text. For example, if you want to filter the content in (), set it to ).

]

ASR object

HotWord string

The hot word list is used to improve the recognition accuracy. Format: Hotword1|Weight1,Hotword2|Weight2,Hotword3|Weight3

A single hot word cannot exceed 30 characters, cannot contain spaces, and the weight range is [-1, 11]. Up to 128 hot words are supported.

Params object

Extended parameters, please contact ZEGOCLOUD technical support for details.

VADSilenceSegmentation number

Possible values: >= 200 and <= 2000

Default value: 500

Set the time after which the user's speech is no longer considered as a sentence. The unit is ms, range [200, 2000], default is 500.

PauseInterval number

Possible values: >= 200 and <= 2000

Set the time within which two sentences are considered as one sentence, i.e., ASR multi-sentence concatenation. The unit is ms, range [200, 2000]. Only when this value is greater than VADSilenceSegmentation, ASR multi-sentence concatenation will be enabled.

Responses

Success

application/json

Schema
Example (from schema)

Schema

Code integer

Return code. 0 indicates success, other values indicate failure. For more information on error codes and response handling recommendations, please refer to Return Codes.

Message string

Explanation of the request result

RequestId string

Request ID

{
  "Code": 0,
  "Message": "Success",
  "RequestId": "8825223157230377926"
}

Copied!

CURL

Copied!

Base URL

https://aigc-aiagent-api.zegotech.cn

Unified access address (no regional distinction)

Parameters

Actionqueryrequired

AppIdqueryrequired

SignatureNoncequeryrequired

Timestampqueryrequired

Signaturequeryrequired

SignatureVersionqueryrequired

Bodyrequired

Example (from schema)
Example

{
  "AgentId": "Jacky",
  "Name": "Jacky",
  "LLM": {
    "Url": "https://ark.cn-beijing.volces.com/api/v3/chat/completions",
    "ApiKey": "zego_test",
    "Model": "doubao-1-5-lite-32k-250115",
    "SystemPrompt": "You are a friendly assistant",
    "Temperature": 0.7,
    "TopP": 0.9,
    "Params": {
      "max_tokens": 16384
    },
    "AddAgentInfo": false
  },
  "TTS": {
    "Vendor": "ByteDance",
    "Params": {
      "app": {
        "appid": "zego_test",
        "token": "zego_test",
        "cluster": "volcano_tts"
      },
      "audio": {
        "voice_type": "zh_female_qingxinnvsheng_mars_bigtts",
        "loudness_ratio": 1,
        "speed_ratio": 1
      }
    },
    "FilterText": [
      {
        "BeginCharacters": "(",
        "EndCharacters": ")"
      }
    ]
  },
  "ASR": {
    "HotWord": "ZEGO|10,AI|10,Agent|10",
    "Params": {},
    "VADSilenceSegmentation": 500,
    "PauseInterval": 800
  }
}

RESPONSEClear

Click the "Send" button above and see the response here!