DocsICP FilingConsole
Documentation
Home Page Intelligent Media Services Developer Reference API Reference Data structure AIAgentTemplateConfig

AIAgentTemplateConfig

Updated at:
Copy as MD
Product
My Favorites

Parameter

Type

Description

Example

object

The agent template parameters.

AvatarChat3D

object

The 3D digital human parameters.

AsrMaxSilence

integer

The threshold for speech segmentation detection. Silence exceeding this threshold is treated as a sentence break. Valid values: 200 to 1200. Unit: milliseconds. Default value: 400.

400
AvatarId

string

The ID of the digital human model.

1231
EnableIntelligentSegment

boolean

Specifies whether to enable intelligent segmentation. After this feature is enabled, sentence breaks in user speech are intelligently merged into a single sentence. Default value: true.

true
EnablePushToTalk

boolean

Specifies whether to enable the push-to-talk mode. Default value: false.

false
EnableVoiceInterrupt

boolean

Specifies whether to support voice interruption. Default value: true.

true
GracefulShutdown

boolean

Specifies whether to enable graceful shutdown. Default value: false.

  • Graceful shutdown: When the agent is stopped, it finishes broadcasting the current speech before stopping, with a maximum broadcast duration of 10 seconds.

false
Greeting

string

The greeting message, which takes effect when joining the session. If not specified, the greeting configured in the agent template is used. Maximum length: 128 characters.

Good morning, my friend!
UseVoiceprint

boolean

Specifies whether to enable voiceprint recognition. Default value: false.

false
UserOnlineTimeout

integer

The timeout period for the agent to close the task if the user does not join the session. Unit: seconds. Default value: 60.

60
VoiceId

string

The ID of the voice, which takes effect in the next sentence. If not specified, the voice ID configured in the agent template is used. This parameter applies only to preset text-to-speech (TTS). Maximum length: 64 characters. For valid values, refer to Intelligent speech effect examples.

zhixiaoxia
Volume

integer

The volume of the agent's speech.

  • If not specified: The adaptive volume mode recommended by Alibaba Cloud is used by default.

  • If specified: Valid values are 0 to 400. Output volume = Speech output volume in the workflow × volume / 100. Examples:

  1. If volume is set to 0, the output volume is 0.

  2. If volume is set to 100, the volume is the original volume.

  3. If volume is set to 200, the volume is twice the original volume.

100
VoiceprintId

string

The unique identity ID for voiceprint recognition. Default value: none.

uniqueId
BailianAppParams

string

The parameters for Alibaba Cloud Model Studio Application Center. For the parameter format, refer to Alibaba Cloud Model Studio Application Center parameters.

{}
UserOfflineTimeout

integer

The timeout period for the agent to close the task after the user leaves the session. Unit: seconds. Default value: 5.

5
MaxIdleTime

integer

The maximum waiting time without interaction with the agent. The agent goes offline upon timeout. Unit: seconds. Default value: 600.

600
WorkflowOverrideParams

string

The override parameters for the workflow. Default value: none.

{}
WakeUpQuery

string

The user's instruction before the call starts, which is used for the agent to respond immediately after the call starts.

How’s the weather today?
LlmHistory

array

The maximum number of retained turns for the LLM or MLLM historical conversation context. Default value: 10.

object

Role

string

The role of the conversation participant. Valid values:

  • user: User

  • assistant: Assistant

  • system: System

  • function: Function

  • plugin: Plug-in

  • tool: Tool

user
Content

string

The actual text of the conversation content, which records the specific expression or response of the role in the conversation.

hello
LlmHistoryLimit

integer

The maximum number of retained turns for the LLM or MLLM historical conversation context. Default value: 10.

10
VoiceIdList

array

The list of available voices.

string

The voice.

zhixiaoxia
AsrLanguageId

string

The language ID for automatic speech recognition (ASR). Valid values:

  • zh_mandarin: Chinese

  • en: English

  • zh_en: Chinese and English mixed

  • es: Spanish

  • jp: Japanese

zh_mandarin
LlmSystemPrompt

string

The system prompt for the LLM after the call starts.

You are a friendly and helpful assistant, focused on providing users with accurate information and advice.
InterruptWords

array

The list of specific words or phrases that trigger conversation interruption.

string

The specific word or phrase that triggers conversation interruption.

stop
VadLevel

integer

The interruption threshold parameter. Valid values: 0 to 11. Default value: 11.

  • 0: Disables the voice activity detection (VAD) feature.

  • 1 to 10: A higher value indicates that it is more difficult to interrupt.

  • 11: Significantly different from previous values, with lower pre-processing speech damage and stronger anti-interference.

0
CharBreak

boolean

AsrHotWords

array

The list of hotwords for ASR. The hotword list supports a maximum of 128 words.

string

The hotword string. Length: 1 to 10 characters.

check
VisionChat

object

The visual agent parameters.

AsrMaxSilence

integer

The threshold for speech segmentation detection. Silence exceeding this threshold is treated as a sentence break. Valid values: 200 to 1200. Unit: milliseconds. Default value: 400.

400
EnableIntelligentSegment

boolean

Specifies whether to enable intelligent segmentation. After this feature is enabled, sentence breaks in user speech are intelligently merged into a single sentence. Default value: true.

true
EnablePushToTalk

boolean

Specifies whether to enable the push-to-talk mode. Default value: false.

false
EnableVoiceInterrupt

boolean

Specifies whether to support voice interruption. Default value: true.

true
GracefulShutdown

boolean

Specifies whether to enable graceful shutdown. Default value: false.

Graceful shutdown: When the agent is stopped, it finishes broadcasting the current speech before stopping, with a maximum broadcast duration of 10 seconds.

false
Greeting

string

The greeting message, which takes effect when joining the session. If not specified, the greeting configured in the agent template is used. Maximum length: 128 characters.

Good morning, my friend!

UseVoiceprint

boolean

Specifies whether to enable voiceprint recognition. Default value: false.

false
UserOnlineTimeout

integer

The timeout period for the agent to close the task if the user does not join the session. Unit: seconds. Default value: 60.

60
VoiceId

string

The ID of the voice, which takes effect in the next sentence. If not specified, the voice ID configured in the agent template is used. This parameter applies only to preset text-to-speech (TTS). Maximum length: 64 characters. For valid values, refer to Intelligent speech effect examples.

zhixiaoxia
Volume

integer

The volume of the agent's speech.

If not specified: The adaptive volume mode recommended by Alibaba Cloud is used by default.

If specified: Valid values are 0 to 400. Output volume = Speech output volume in the workflow × volume / 100. Examples:

If volume is set to 0, the output volume is 0.

If volume is set to 100, the volume is the original volume.

If volume is set to 200, the volume is twice the original volume.

100
VoiceprintId

string

The unique identity ID for voiceprint recognition. Default value: none.

uniqueId
BailianAppParams

string

The parameters for Alibaba Cloud Model Studio Application Center. For the parameter format, refer to Alibaba Cloud Model Studio Application Center parameters.

{}
UserOfflineTimeout

integer

The timeout period for the agent to close the task after the user leaves the session. Unit: seconds. Default value: 5.

5
MaxIdleTime

integer

The maximum waiting time without interaction with the agent. The agent goes offline upon timeout. Unit: seconds. Default value: 600.

600
WorkflowOverrideParams

string

The override parameters for the workflow. Default value: none.

{}
WakeUpQuery

string

The user's instruction before the call starts, which is used for the agent to respond immediately after the call starts.

How’s the weather today?
LlmHistory

array

The maximum number of retained turns for the LLM or MLLM historical conversation context. Default value: 10.

object

Role

string

The role of the conversation participant. Valid values:

  • user: User

  • assistant: Assistant

  • system: System

  • function: Function

  • plugin: Plug-in

  • tool: Tool

user
Content

string

The actual text of the conversation content, which records the specific expression or response of the role in the conversation.

hello
LlmHistoryLimit

integer

The maximum number of retained turns for the LLM or MLLM historical conversation context. Default value: 10.

10
VoiceIdList

array

The list of available voices.

string

The voice.

zhixiaoxia
AsrLanguageId

string

The language ID for automatic speech recognition (ASR). Valid values:

  • zh_mandarin: Chinese

  • en: English

  • zh_en: Chinese and English mixed

  • es: Spanish

  • jp: Japanese

zh_mandarin
LlmSystemPrompt

string

The system prompt for the LLM after the call starts.

You are a friendly and helpful assistant, focused on providing users with accurate information and advice.
InterruptWords

array

The list of specific words or phrases that trigger conversation interruption.

string

The specific word or phrase that triggers conversation interruption.

stop
VadLevel

integer

The interruption threshold parameter. Valid values: 0 to 11. Default value: 11.

  • 0: Disables the voice activity detection (VAD) feature.

  • 1 to 10: A higher value indicates that it is more difficult to interrupt.

  • 11: Significantly different from previous values, with lower pre-processing speech damage and stronger anti-interference.

0
CharBreak

boolean

AsrHotWords

array

The list of hotwords for ASR. The hotword list supports a maximum of 128 words.

string

The hotword string. Length: 1 to 10 characters.

check
VoiceChat

object

The voice call parameters.

AsrMaxSilence

integer

The threshold for speech segmentation detection. Silence exceeding this threshold is treated as a sentence break. Valid values: 200 to 1200. Unit: milliseconds. Default value: 400.

400
EnableIntelligentSegment

boolean

Specifies whether to enable intelligent segmentation. After this feature is enabled, sentence breaks in user speech are intelligently merged into a single sentence. Default value: true.

true
EnablePushToTalk

boolean

Specifies whether to enable the push-to-talk mode. Default value: false.

false
EnableVoiceInterrupt

boolean

Specifies whether to support voice interruption. Default value: true.

true
GracefulShutdown

boolean

Specifies whether to enable graceful shutdown. Default value: false.

  • Graceful shutdown: When the agent is stopped, it finishes broadcasting the current speech before stopping, with a maximum broadcast duration of 10 seconds.

false
Greeting

string

The greeting message, which takes effect when joining the session. If not specified, the greeting configured in the agent template is used. Maximum length: 128 characters.

Good morning, my friend
UseVoiceprint

boolean

Specifies whether to enable voiceprint recognition. Default value: false.

false
UserOnlineTimeout

integer

The timeout period for the agent to close the task if the user does not join the session. Unit: seconds. Default value: 60.

60
VoiceId

string

The ID of the voice, which takes effect in the next sentence. If not specified, the voice ID configured in the agent template is used. This parameter applies only to preset text-to-speech (TTS). Maximum length: 64 characters. For valid values, refer to Intelligent speech effect examples.

zhixiaoxia
Volume

integer

The volume of the agent's speech.

  • If not specified: The adaptive volume mode recommended by Alibaba Cloud is used by default.

  • If specified: Valid values are 0 to 400. Output volume = Speech output volume in the workflow × volume / 100. Examples:

  1. If volume is set to 0, the output volume is 0.

  2. If volume is set to 100, the volume is the original volume.

  3. If volume is set to 200, the volume is twice the original volume.

100
VoiceprintId

string

The unique identity ID for voiceprint recognition. Default value: none.

uniqueId
BailianAppParams

string

The parameters for Alibaba Cloud Model Studio Application Center. For the parameter format, refer to Alibaba Cloud Model Studio Application Center parameters.

{}
UserOfflineTimeout

integer

The timeout period for the agent to close the task after the user leaves the session. Unit: seconds. Default value: 5.

5
AvatarUrl

string

The URL of the agent avatar for voice calls. Default value: none.

http://example.com/a.jpg
AvatarUrlType

string

The type of the agent avatar URL. Default value: none.

USER
MaxIdleTime

integer

The maximum waiting time without interaction with the agent. The agent goes offline upon timeout. Unit: seconds. Default value: 600.

600
WorkflowOverrideParams

string

The override parameters for the workflow. Default value: none.

{}
WakeUpQuery

string

The user's instruction before the call starts, which is used for the agent to respond immediately after the call starts.

How’s the weather today?
LlmHistory

array

The historical conversation context of the LLM or MLLM.

object

Role

string

The role of the conversation participant. Valid values:

  • user: user

  • assistant: assistant

  • system: system

  • function: function

  • plugin: plug-in

  • tool: tool

user
Content

string

The actual text of the conversation content, which records the specific expression or response of the role in the conversation.

hello
LlmHistoryLimit

integer

The maximum number of retained turns for the LLM or MLLM historical conversation context. Default value: 10.

10
VoiceIdList

array

The list of available voices.

string

The voice.

zhixiaoxia
AsrLanguageId

string

The language ID for automatic speech recognition (ASR). Valid values:

  • zh_mandarin: Chinese

  • en: English

  • zh_en: Chinese and English mixed

  • es: Spanish

  • jp: Japanese

zh_mandarin
LlmSystemPrompt

string

The system prompt for the LLM after the call starts.

You are a friendly and helpful assistant, focused on providing users with accurate information and advice.
InterruptWords

array

The list of specific words or phrases that trigger conversation interruption.

string

The specific word or phrase that triggers conversation interruption.

stop
VadLevel

integer

The interruption threshold parameter. Valid values: 0 to 11. Default value: 11.

  • 0: Disables the voice activity detection (VAD) feature.

  • 1 to 10: A higher value indicates that it is more difficult to interrupt.

  • 11: Significantly different from previous values, with lower pre-processing speech damage and stronger anti-interference.

11
CharBreak

boolean

AsrHotWords

array

The list of hotwords for ASR. The hotword list supports a maximum of 128 words.

string

The hotword string. Length: 1 to 10 characters.

check
Previous：AIAgentRuntimeConfigNext：AiRtcAuthCodeDTO