AIAgentOutboundCallConfig-Intelligent Media Services(IMS)-阿里云帮助中心

Parameter	Type	Description	Example
	object	The agent template parameters.
Greeting	string	The greeting message. Changes take effect in the next session. Default value: none.	hello
EnableIntelligentSegment	boolean	Specifies whether to enable intelligent segmentation. After this feature is enabled, fragmented sentences spoken by the user are intelligently merged into a single sentence. Default value: true.	true
AsrConfig	object	The speech recognition configuration.
AsrMaxSilence	integer	The silence duration threshold for speech segmentation. If the silence duration exceeds this threshold, the speech is considered segmented. Valid values: 200 to 1200. Unit: milliseconds. Default value: 400.	400
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
AsrHotWords	array	The list of ASR hotwords. The list supports a maximum of 128 hotwords.
	string	The hotword string. Length: 1 to 10 characters.	check
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 the speech. 11: Significantly different from previous values. It causes less damage to the conversation voice during pre-processing and provides stronger anti-interference capability.	11
CustomParams	string	The pass-through parameters for the proprietary ASR integration.	mode=fast&sample=16000&format=wav
VadDuration	integer	The minimum duration threshold for voice activity detection, which is used to control the sensitivity of interruptions. A value of 0 disables this feature. Valid values: 200 to 2000. Unit: milliseconds. Common values: 200 to 500, which correspond to 1 to 4 characters. Default value: empty. This parameter does not take effect when left empty.	300
LlmConfig	object	The large language model (LLM) configuration.
LlmHistoryLimit	integer	The maximum number of retained turns for the LLM or multimodal LLM (MLLM) conversation history context. Default value: 10.	10
LlmHistory	array	The LLM or MLLM conversation history context.
	object	A single conversation.
Role	string	The role of the conversation participant. Valid values: user: User assistant: Assistant system: System function: Function plugin: Plugin tool: Tool	user
Content	string	The actual text content of the conversation, which records the specific expression or response of the role in the conversation.	hello
LlmSystemPrompt	string	The system prompt for the LLM after the call is initiated.	You are a friendly and helpful assistant, focused on providing users with accurate information and advice.
BailianAppParams	string	The parameters for Alibaba Cloud Model Studio Application Center. For the parameter format, refer to Alibaba Cloud Model Studio Application Center parameters.	"{\"biz_params\":{\"user_defined_params\":{\"your_plugin_id\":{\"article_index\":2}}},\"memory_id\":\"your_memory_id\",\"image_list\":[\"https://your_image_url\"],\"rag_options\":{\"pipeline_ids\":[\"your_id\"],\"file_ids\":[\"DocumentID1\",\"DocumentID2\"],\"metadata_filter\":{\"name\":\"ZhangSan\"},\"structured_filter\":{\"key1\":\"value1\",\"key2\":\"value2\"},\"tags\":[\"Tag1\",\"Tag2\"]}}"
OpenAIExtraQuery	string	The additional query parameters for the OpenAI-compatible LLM. Parameters must be in the key=value format. Multiple parameters are connected by an ampersand (&). All values must be of the string type.	api-version=2024-02-01&api-key=sk-xxx
LlmCompleteReply	boolean	After this feature is enabled, the complete LLM result is sent to the client after the LLM generates the result.	true
FunctionMap	array	The list of function mappings, which is used to map agent capabilities to LLM functions. Currently, only function calling with user-defined OpenAI-compatible LLMs is supported.
	object	A single mapping rule.
Function	string	The name of the built-in feature provided by the Alibaba Cloud agent system. Currently, only hangup is supported.	hangup
MatchFunction	string	The name of the LLM function that corresponds to the feature. This name is customized by the user and used to call the corresponding feature in the LLM. For the user-defined LLM protocol, refer to Standard LLM API.	hangup
OutputMinLength	integer	The minimum length of text output in characters. Text shorter than this length is cached and waiting to be concatenated. Valid values: 0 to 100. A value of 0 or empty indicates no limit. Default value: empty.	5
OutputMaxDelay	string	The maximum delay time for text output in milliseconds. If this time is exceeded, the cached text is forcibly output. Valid values: 1000 to 10000. A value of 0 or empty indicates no limit. Default value: empty.	2000
HistorySyncWithTTS	boolean	Specifies whether the LLM message history is consistent with the text-to-speech (TTS) playback content. Default value: false. After this feature is enabled, the saved LLM messages are consistent with the TTS playback content.	false
TtsConfig	object	The speech synthesis configuration.
VoiceId	string	The voice ID. Changes take effect in the next sentence. If this parameter is not specified, the voice ID configured in the agent template is used. This parameter takes effect only for preset TTS. The input length cannot exceed 64 characters. For valid values, refer to Intelligent speech effect examples.	longcheng_v2
VoiceIdList	array	The list of available voices.
	string	The voice.	zhixiaoxia
PronunciationRules	array	The TTS pronunciation rules. The array length cannot exceed 20. The rules are executed in sequence.
	object	A TTS pronunciation rule.
Word	string	The word to be replaced. The length must be less than 10 characters. It must consist of Chinese characters and cannot contain spaces.	Dashi Lane
Pronunciation	string	The target pronunciation. The length must be less than 10 characters. It must consist of Chinese characters and cannot contain spaces.	Dashi Lane
Type	string	The specific pronunciation rule type. Valid values: replacement: The rule that directly replaces the word with the pronunciation.	replacement
ModelId	string	The model ID. Currently, only MiniMax is supported. Valid values: speech-01-turbo and speech-02-turbo.	speech-01-turbo
LanguageId	string	The language ID. Currently, only MiniMax is supported. Default value: empty. This parameter enhances the recognition capability for specified minority languages and dialects. After this parameter is set, the speech performance in the specified minority language or dialect scenarios is improved. If the minority language type is not clear, you can set this parameter to auto, and the model automatically determines the minority language type. Valid values: Supported languages Chinese: Chinese Chinese,Yue: Cantonese English: English Arabic: Arabic Russian: Russian Spanish: Spanish French: French Portuguese: Portuguese German: German Turkish: Turkish Dutch: Dutch Ukrainian: Ukrainian Vietnamese: Vietnamese Indonesian: Indonesian Japanese: Japanese Italian: Italian Korean: Korean Thai: Thai Polish: Polish Romanian: Romanian Greek: Greek Czech: Czech Finnish: Finnish Hindi: Hindi auto: Automatic detection	Chinese
Emotion	string	The emotion. Currently, only MiniMax is supported. MiniMax supports the following seven emotions: happy: Happy sad: Sad angry: Angry fearful: Fearful disgusted: Disgusted surprised: Surprised calm: Neutral	happy
SpeechRate	number	The speech rate. This parameter is supported on all platforms. For CosyVoice, the default value is 1.0, and the valid values are 0.5 to 2.0. For MiniMax, the default value is 1.0, and the valid values are 0.5 to 2.0.	1.0
InterruptConfig	object	The speech interruption policy configuration.
EnableVoiceInterrupt	boolean	Specifies whether to support speech interruption. Default value: true.	true
InterruptWords	array	The specific words or phrases that trigger conversation interruption.
	string	The specific words or phrases that trigger conversation interruption.	Just a moment
Eagerness	string
NoInterruptMode	string	The ASR processing policy in the No Interrupting mode. Valid values: cache: Caches the ASR text. After the current turn ends, the cached ASR text is processed together in the next turn. discard: Directly discards the ASR text. Default value: cache.	cache
KeepInterruptWordsForLLM	boolean	Specifies whether to retain the interrupt words and send them to the LLM. Default value: discard. Note Example: If the interrupt word is "wait", the phrase "wait how is the weather today" becomes "how is the weather today" after the interrupt word is discarded and sent to the LLM.	true
TurnDetectionConfig	object	The conversation turn detection configuration.
TurnEndWords	array	The list of keywords used to determine the end of a user turn.
	string	A keyword used to determine the end of a user turn.	I'm done talking
Mode	string	The turn detection mode. Valid values: Normal: The normal mode, which does not use AI to determine semantics. Semantic: Uses AI to determine whether the user has finished speaking based on the context semantics. Default value: Normal.	Semantic
SemanticWaitDuration	integer	The pause determination time in AI mode. Unit: milliseconds. Default value: -1. -1: AI automatically determines the appropriate waiting time. 0 to 10000: Custom waiting time. We recommend that you set this value to 0 to 1500. Note: This parameter is invalid in normal mode.	-1
Eagerness	string	The eagerness level. This parameter takes effect only in Semantic mode. It controls the speed at which the AI initiates a response after detecting a pause. Valid values: Low: Waits patiently with a maximum waiting time of 6 seconds to reduce the risk of being interrupted. Medium: Balances waiting with a maximum waiting time of 4 seconds. This value is suitable for most scenarios. High: Responds quickly with a maximum waiting time of 2 seconds. This value improves speed but may increase the risk of false cuts. Default value: empty.	Low
GreetingDelay	integer	The delay time for the greeting message. Unit: milliseconds. Default value: 0. Valid values: 0 to 5000.	0
AmbientSoundConfig	object	The ambient sound configuration for calls.
ResourceId	string	The ID of the ambient sound for calls. You can obtain this ID in the advanced configurations of the agent configuration in the console.	f67901c595834************
Volume	integer	The volume of the background sound for calls. Valid values: 0 to 100. A value of 0 indicates that the background sound is disabled.	50
ExperimentalConfig	string	The parameters for experimental features. Contact technical support if you have any requirements.	""
AutoSpeechConfig	object	The automatic speech configuration module for the agent, including LLM waiting prompts and user long-time silence inquiries.
UserIdle	object	The inquiry broadcast configuration when the user is silent for a long time.
WaitTime	integer	The silence duration threshold. Unit: milliseconds. This parameter is required. An inquiry is triggered when the silence duration exceeds this threshold. Valid values: 5000 to 600000.	5000
MaxRepeats	integer	The maximum number of inquiries. Valid values: 0 to 10. This parameter is required. If this number is exceeded, no more inquiries are triggered, and the call is directly closed.	5
Messages	array	The collection of inquiry prompts. A maximum of 10 prompts are supported. The length of each prompt cannot exceed 100 characters. The sum of probabilities must be 100%.
	object	The inquiry prompt structure.
Text	string	The text of the inquiry prompt. The maximum length is 100 characters.	Are you still there?
Probability	number	The selection probability of the prompt. Valid values: 0 to 1, which correspond to 0% to 100%.	0.5
HangupEndWord	string	The hang-up closing word. It is broadcast before the call is hung up after the user does not respond for a long time. The maximum length is 200 characters.	I’m hanging up, goodbye.
LlmPending	object	The broadcast configuration when the LLM response is delayed.
WaitTime	integer	The waiting time threshold for the LLM response. If this time is exceeded, a broadcast prompt is triggered. This parameter is required. Unit: milliseconds. Valid values: 500 to 10000. Set this parameter based on the actual usage of the LLM.	3000
Mode	string
Messages	array	The collection of inquiry prompts. A maximum of 10 prompts are supported. The length of each prompt cannot exceed 100 characters. The sum of probabilities must be 100%.
	object	The inquiry prompt structure.
Text	string	The text of the inquiry prompt. The maximum length is 100 characters.	Just a moment
Probability	number	The selection probability of the prompt. Valid values: 0 to 1, which correspond to 0% to 100%.	0.5
MaxIdleTime	integer	The maximum waiting time without interaction with the agent. If this time is exceeded, the agent goes offline. Unit: seconds. Default value: 600.	600
BackChannelingConfig	object	[Deprecated] Use BackChannelingConfigs instead.
Enabled	boolean
TriggerStage	string
Probability	number
Words	object
Text	string
Probability	number
BackChannelingConfigs	array	The backchanneling feature configuration module. After this feature is enabled, the system randomly broadcasts short backchanneling words at specific trigger timings.
	object	A single backchanneling configuration.
Enabled	boolean	Specifies whether to enable the backchanneling feature. This parameter is required. Valid values: true and false.	true
TriggerStage	string	The trigger timing for backchanneling. Valid values: pause_detected: A short pause in speech is detected.	pause_detected
Probability	number	The trigger probability of the feature. Valid values: 0.0 to 1.0. This parameter is required.	0.5
Words	array	The collection of backchanneling phrases. A maximum of 10 phrases are supported. The length of each phrase cannot exceed 20 characters. The sum of probabilities must be 1.0.
	object	The backchanneling phrase configuration.
Text	string	The text of the phrase. The maximum length is 20 characters. Multiple languages are supported. Required.	ok
Probability	number	The trigger probability of the phrase. Valid values: 0.0 to 1.0. Required.	0.3

object

The agent template parameters.

Greeting

string

The greeting message. Changes take effect in the next session. Default value: none.

hello

EnableIntelligentSegment

boolean

Specifies whether to enable intelligent segmentation. After this feature is enabled, fragmented sentences spoken by the user are intelligently merged into a single sentence. Default value: true.

true

AsrConfig

object

The speech recognition configuration.

AsrMaxSilence

integer

The silence duration threshold for speech segmentation. If the silence duration exceeds this threshold, the speech is considered segmented. Valid values: 200 to 1200. Unit: milliseconds. Default value: 400.

400

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

AsrHotWords

array

The list of ASR hotwords. The list supports a maximum of 128 hotwords.

string

The hotword string. Length: 1 to 10 characters.

check

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 the speech.
11: Significantly different from previous values. It causes less damage to the conversation voice during pre-processing and provides stronger anti-interference capability.

11

CustomParams

string

The pass-through parameters for the proprietary ASR integration.

mode=fast&sample=16000&format=wav

VadDuration

integer

The minimum duration threshold for voice activity detection, which is used to control the sensitivity of interruptions. A value of 0 disables this feature. Valid values: 200 to 2000. Unit: milliseconds. Common values: 200 to 500, which correspond to 1 to 4 characters. Default value: empty. This parameter does not take effect when left empty.

300

LlmConfig

object

The large language model (LLM) configuration.

LlmHistoryLimit

integer

The maximum number of retained turns for the LLM or multimodal LLM (MLLM) conversation history context. Default value: 10.

10

LlmHistory

array

The LLM or MLLM conversation history context.

object

A single conversation.

Role

string

The role of the conversation participant. Valid values:

user: User
assistant: Assistant
system: System
function: Function
plugin: Plugin
tool: Tool

user

Content

string

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

hello

LlmSystemPrompt

string

The system prompt for the LLM after the call is initiated.

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

BailianAppParams

string

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

"{\"biz_params\":{\"user_defined_params\":{\"your_plugin_id\":{\"article_index\":2}}},\"memory_id\":\"your_memory_id\",\"image_list\":[\"https://your_image_url\"],\"rag_options\":{\"pipeline_ids\":[\"your_id\"],\"file_ids\":[\"DocumentID1\",\"DocumentID2\"],\"metadata_filter\":{\"name\":\"ZhangSan\"},\"structured_filter\":{\"key1\":\"value1\",\"key2\":\"value2\"},\"tags\":[\"Tag1\",\"Tag2\"]}}"

OpenAIExtraQuery

string

The additional query parameters for the OpenAI-compatible LLM. Parameters must be in the key=value format. Multiple parameters are connected by an ampersand (&). All values must be of the string type.

api-version=2024-02-01&api-key=sk-xxx

LlmCompleteReply

boolean

After this feature is enabled, the complete LLM result is sent to the client after the LLM generates the result.

true

FunctionMap

array

The list of function mappings, which is used to map agent capabilities to LLM functions. Currently, only function calling with user-defined OpenAI-compatible LLMs is supported.

object

A single mapping rule.

Function

string

The name of the built-in feature provided by the Alibaba Cloud agent system. Currently, only hangup is supported.

hangup

MatchFunction

string

The name of the LLM function that corresponds to the feature. This name is customized by the user and used to call the corresponding feature in the LLM. For the user-defined LLM protocol, refer to Standard LLM API.

hangup

OutputMinLength

integer

The minimum length of text output in characters. Text shorter than this length is cached and waiting to be concatenated. Valid values: 0 to 100. A value of 0 or empty indicates no limit. Default value: empty.

5

OutputMaxDelay

string

The maximum delay time for text output in milliseconds. If this time is exceeded, the cached text is forcibly output. Valid values: 1000 to 10000. A value of 0 or empty indicates no limit. Default value: empty.

2000

HistorySyncWithTTS

boolean

Specifies whether the LLM message history is consistent with the text-to-speech (TTS) playback content. Default value: false. After this feature is enabled, the saved LLM messages are consistent with the TTS playback content.

false

TtsConfig

object

The speech synthesis configuration.

VoiceId

string

The voice ID. Changes take effect in the next sentence. If this parameter is not specified, the voice ID configured in the agent template is used. This parameter takes effect only for preset TTS. The input length cannot exceed 64 characters. For valid values, refer to Intelligent speech effect examples.

longcheng_v2

VoiceIdList

array

The list of available voices.

string

The voice.

zhixiaoxia

PronunciationRules

array

The TTS pronunciation rules. The array length cannot exceed 20. The rules are executed in sequence.

object

A TTS pronunciation rule.

Word

string

The word to be replaced. The length must be less than 10 characters. It must consist of Chinese characters and cannot contain spaces.

Dashi Lane

Pronunciation

string

The target pronunciation. The length must be less than 10 characters. It must consist of Chinese characters and cannot contain spaces.

Dashi Lane

Type

string

The specific pronunciation rule type. Valid values:

replacement: The rule that directly replaces the word with the pronunciation.

replacement

ModelId

string

The model ID. Currently, only MiniMax is supported. Valid values: speech-01-turbo and speech-02-turbo.

speech-01-turbo

LanguageId

string

The language ID. Currently, only MiniMax is supported. Default value: empty. This parameter enhances the recognition capability for specified minority languages and dialects. After this parameter is set, the speech performance in the specified minority language or dialect scenarios is improved. If the minority language type is not clear, you can set this parameter to auto, and the model automatically determines the minority language type. Valid values:

Supported languages

Chinese: Chinese
Chinese,Yue: Cantonese
English: English
Arabic: Arabic
Russian: Russian
Spanish: Spanish
French: French
Portuguese: Portuguese
German: German
Turkish: Turkish
Dutch: Dutch
Ukrainian: Ukrainian
Vietnamese: Vietnamese
Indonesian: Indonesian
Japanese: Japanese
Italian: Italian
Korean: Korean
Thai: Thai
Polish: Polish
Romanian: Romanian
Greek: Greek
Czech: Czech
Finnish: Finnish
Hindi: Hindi
auto: Automatic detection

Chinese

Emotion

string

The emotion. Currently, only MiniMax is supported. MiniMax supports the following seven emotions:

happy: Happy
sad: Sad
angry: Angry
fearful: Fearful
disgusted: Disgusted
surprised: Surprised
calm: Neutral

happy

SpeechRate

number

The speech rate. This parameter is supported on all platforms. For CosyVoice, the default value is 1.0, and the valid values are 0.5 to 2.0. For MiniMax, the default value is 1.0, and the valid values are 0.5 to 2.0.

1.0

InterruptConfig

object

The speech interruption policy configuration.

EnableVoiceInterrupt

boolean

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

true

InterruptWords

array

The specific words or phrases that trigger conversation interruption.

string

The specific words or phrases that trigger conversation interruption.

Just a moment

Eagerness

string

NoInterruptMode

string

The ASR processing policy in the No Interrupting mode. Valid values:

cache: Caches the ASR text. After the current turn ends, the cached ASR text is processed together in the next turn.
discard: Directly discards the ASR text.

Default value: cache.

cache

KeepInterruptWordsForLLM

boolean

Specifies whether to retain the interrupt words and send them to the LLM. Default value: discard.

Note

Example: If the interrupt word is "wait", the phrase "wait how is the weather today" becomes "how is the weather today" after the interrupt word is discarded and sent to the LLM.

true

TurnDetectionConfig

object

The conversation turn detection configuration.

TurnEndWords

array

The list of keywords used to determine the end of a user turn.

string

A keyword used to determine the end of a user turn.

I'm done talking

Mode

string

The turn detection mode. Valid values:

Normal: The normal mode, which does not use AI to determine semantics.
Semantic: Uses AI to determine whether the user has finished speaking based on the context semantics.

Default value: Normal.

Semantic

SemanticWaitDuration

integer

The pause determination time in AI mode. Unit: milliseconds. Default value: -1.

-1: AI automatically determines the appropriate waiting time.
0 to 10000: Custom waiting time. We recommend that you set this value to 0 to 1500.

Note: This parameter is invalid in normal mode.

-1

Eagerness

string

The eagerness level. This parameter takes effect only in Semantic mode. It controls the speed at which the AI initiates a response after detecting a pause. Valid values:

Low: Waits patiently with a maximum waiting time of 6 seconds to reduce the risk of being interrupted.
Medium: Balances waiting with a maximum waiting time of 4 seconds. This value is suitable for most scenarios.
High: Responds quickly with a maximum waiting time of 2 seconds. This value improves speed but may increase the risk of false cuts.

Default value: empty.

Low

GreetingDelay

integer

The delay time for the greeting message. Unit: milliseconds. Default value: 0. Valid values: 0 to 5000.

0

AmbientSoundConfig

object

The ambient sound configuration for calls.

ResourceId

string

The ID of the ambient sound for calls. You can obtain this ID in the advanced configurations of the agent configuration in the console.

f67901c595834************

Volume

integer

The volume of the background sound for calls. Valid values: 0 to 100. A value of 0 indicates that the background sound is disabled.

50

ExperimentalConfig

string

The parameters for experimental features. Contact technical support if you have any requirements.

""

AutoSpeechConfig

object

The automatic speech configuration module for the agent, including LLM waiting prompts and user long-time silence inquiries.

UserIdle

object

The inquiry broadcast configuration when the user is silent for a long time.

WaitTime

integer

The silence duration threshold. Unit: milliseconds. This parameter is required. An inquiry is triggered when the silence duration exceeds this threshold. Valid values: 5000 to 600000.

5000

MaxRepeats

integer

The maximum number of inquiries. Valid values: 0 to 10. This parameter is required. If this number is exceeded, no more inquiries are triggered, and the call is directly closed.

5

Messages

array

The collection of inquiry prompts. A maximum of 10 prompts are supported. The length of each prompt cannot exceed 100 characters. The sum of probabilities must be 100%.

object

The inquiry prompt structure.

Text

string

The text of the inquiry prompt. The maximum length is 100 characters.

Are you still there?

Probability

number

The selection probability of the prompt. Valid values: 0 to 1, which correspond to 0% to 100%.

0.5

HangupEndWord

string

The hang-up closing word. It is broadcast before the call is hung up after the user does not respond for a long time. The maximum length is 200 characters.

I’m hanging up, goodbye.

LlmPending

object

The broadcast configuration when the LLM response is delayed.

WaitTime

integer

The waiting time threshold for the LLM response. If this time is exceeded, a broadcast prompt is triggered. This parameter is required. Unit: milliseconds. Valid values: 500 to 10000. Set this parameter based on the actual usage of the LLM.

3000

Mode

string

Messages

array

The collection of inquiry prompts. A maximum of 10 prompts are supported. The length of each prompt cannot exceed 100 characters. The sum of probabilities must be 100%.

object

The inquiry prompt structure.

Text

string

The text of the inquiry prompt. The maximum length is 100 characters.

Just a moment

Probability

number

The selection probability of the prompt. Valid values: 0 to 1, which correspond to 0% to 100%.

0.5

MaxIdleTime

integer

The maximum waiting time without interaction with the agent. If this time is exceeded, the agent goes offline. Unit: seconds. Default value: 600.

600

BackChannelingConfig

object

[Deprecated] Use BackChannelingConfigs instead.

Enabled

boolean

TriggerStage

string

Probability

number

Words

object

Text

string

Probability

number

BackChannelingConfigs

array

The backchanneling feature configuration module. After this feature is enabled, the system randomly broadcasts short backchanneling words at specific trigger timings.

object

A single backchanneling configuration.

Enabled

boolean

Specifies whether to enable the backchanneling feature. This parameter is required. Valid values: true and false.

true

TriggerStage

string

The trigger timing for backchanneling. Valid values:

pause_detected: A short pause in speech is detected.

pause_detected

Probability

number

The trigger probability of the feature. Valid values: 0.0 to 1.0. This parameter is required.

0.5

Words

array

The collection of backchanneling phrases. A maximum of 10 phrases are supported. The length of each phrase cannot exceed 20 characters. The sum of probabilities must be 1.0.

object

The backchanneling phrase configuration.

Text

string

The text of the phrase. The maximum length is 20 characters. Multiple languages are supported. Required.

ok

Probability

number

The trigger probability of the phrase. Valid values: 0.0 to 1.0. Required.

0.3