com.tencentcloudapi.ccc.v20200210.models

Class CreateAICallRequest

java.lang.Object

com.tencentcloudapi.common.AbstractModel

com.tencentcloudapi.ccc.v20200210.models.CreateAICallRequest

public class CreateAICallRequest
extends AbstractModel

Field Summary

Fields inherited from class com.tencentcloudapi.common.AbstractModel

header, skipSign

Constructor Summary

Constructors

Constructor and Description
CreateAICallRequest()
CreateAICallRequest(CreateAICallRequest source) NOTE: Any ambiguous key set via .set("AnyKey", "value") will be a shallow copy, and any explicit key, i.e Foo, set via .setFoo("value") will be a deep copy.

Method Summary

Modifier and Type	Method and Description
String	getAPIKey() Get Model API key, for authentication information, please refer to the respective model's official website - OpenAI protocol: [GPT](https://help.openai.com/en/articles/4936850-where-do-i-find-my-openai-api-key), [Hunyuan](https://intl.cloud.tencent.com/document/product/1729/111008?from_cn_redirect=1), [DeepSeek](https://api-docs.deepseek.com/zh-cn/); - Azure protocol: [Azure GPT](https://learn.microsoft.com/en-us/azure/ai-services/openai/chatgpt-quickstart?tabs=command-line%2Ctypescript%2Cpython-new&pivots=programming-language-studio#key-settings); - Minimax:[Minimax](https://platform.minimaxi.com/document/Fast%20access?key=66701cf51d57f38758d581b2)
String	getAPIUrl() Get Model interface address - OpenAI protocol GPT:"https://api.openai.com/v1/" Deepseek:"https://api.deepseek.com/v1" - Azure protocol "https://{your-resource-name}.openai.azure.com?api-version={api-version}" - Minimax protocol "https://api.minimax.chat/v1"
String	getCallee() Get Called number.
String[]	getCallers() Get Caller number list
String	getCustomTTSConfig() Get
String	getEndFunctionDesc() Get Effective when EndFunctionEnable is true; the description of call_end function calling, default is "End the call when user has to leave (like says bye) or you are instructed to do so."
Boolean	getEndFunctionEnable() Get Whether the model supports (or enables) call_end function calling
AICallExtractConfigElement[]	getExtractConfig() Get Call content extraction configuration.
Long	getInterruptMode() Get Interrupt ai speaking mode.
Long	getInterruptSpeechDuration() Get Used when InterruptMode is 0, unit in milliseconds, default is 500ms.
String[]	getLanguages() Get ASR Supported Languages, default is "zh" Chinese, Fill in the array with up to 4 languages, the first is the primary language for recognition, followed by optional languages, Note: When the primary language is a Chinese dialect, optional languages are invalid Currently, the supported languages are as follows.
String	getLLMType() Get Model interface protocol types, currently compatible with three protocol types: - OpenAI protocol (including GPT, DeepSeek, etc.):"openai" - Azure protocol:"azure" - Minimax protocol:"minimax"
Long	getMaxDuration() Get Maximum Waiting Duration (milliseconds), default is 60 seconds, if the user does not speak within this time, the call is automatically terminated
String	getModel() Get Model name, such as - OpenAI protocol "gpt-4o-mini","gpt-4o","deepseek-chat"; - Azure protocol "gpt-4o-mini", "gpt-4o"; - Minimax protocol "deepseek-chat".
Long	getNotifyDuration() Get The duration after which the user hasn't spoken to trigger a notification, minimum 10 seconds, default 10 seconds
Long	getNotifyMaxCount() Get Maximum number of times to trigger ai prompt sound, unlimited by default.
String	getNotifyMessage() Get The AI prompt when NotifyDuration has passed without the user speaking, default is "Sorry, I didn't hear you clearly.
Variable[]	getPromptVariables() Get Prompt word variable.
Long	getSdkAppId() Get Application ID (required) can be found at https://console.cloud.tencent.com/ccc.
String	getSystemPrompt() Get ## Identity You are Kate from the appointment department at Retell Health calling Cindy over the phone to prepare for the annual checkup coming up.
Boolean	getTransferFunctionEnable() Get Whether the model supports (or enables) transfer_to_human function calling.
AITransferItem[]	getTransferItems() Get Takes effect when transferfunctionenable is true: transfer to human configuration.
Long	getVadSilenceTime() Get Automatic speech recognition vad time ranges from 240 to 2000, with a default of 1000, measured in milliseconds.
String	getVoiceType() Get The following voice parameter values are available by default.
String	getWelcomeMessage() Get Used to set the AI Agent Greeting.
Long	getWelcomeMessagePriority() Get 0: interruptible by default, 1: high priority and not interruptible.
Long	getWelcomeType() Get 0: Use welcomeMessage (if empty, the callee speaks first; if not empty, the bot speaks first) 1: Use AI to automatically generate welcomeMessage and speak first based on the prompt
void	setAPIKey(String APIKey) Set Model API key, for authentication information, please refer to the respective model's official website - OpenAI protocol: [GPT](https://help.openai.com/en/articles/4936850-where-do-i-find-my-openai-api-key), [Hunyuan](https://intl.cloud.tencent.com/document/product/1729/111008?from_cn_redirect=1), [DeepSeek](https://api-docs.deepseek.com/zh-cn/); - Azure protocol: [Azure GPT](https://learn.microsoft.com/en-us/azure/ai-services/openai/chatgpt-quickstart?tabs=command-line%2Ctypescript%2Cpython-new&pivots=programming-language-studio#key-settings); - Minimax:[Minimax](https://platform.minimaxi.com/document/Fast%20access?key=66701cf51d57f38758d581b2)
void	setAPIUrl(String APIUrl) Set Model interface address - OpenAI protocol GPT:"https://api.openai.com/v1/" Deepseek:"https://api.deepseek.com/v1" - Azure protocol "https://{your-resource-name}.openai.azure.com?api-version={api-version}" - Minimax protocol "https://api.minimax.chat/v1"
void	setCallee(String Callee) Set Called number.
void	setCallers(String[] Callers) Set Caller number list
void	setCustomTTSConfig(String CustomTTSConfig) Set
void	setEndFunctionDesc(String EndFunctionDesc) Set Effective when EndFunctionEnable is true; the description of call_end function calling, default is "End the call when user has to leave (like says bye) or you are instructed to do so."
void	setEndFunctionEnable(Boolean EndFunctionEnable) Set Whether the model supports (or enables) call_end function calling
void	setExtractConfig(AICallExtractConfigElement[] ExtractConfig) Set Call content extraction configuration.
void	setInterruptMode(Long InterruptMode) Set Interrupt ai speaking mode.
void	setInterruptSpeechDuration(Long InterruptSpeechDuration) Set Used when InterruptMode is 0, unit in milliseconds, default is 500ms.
void	setLanguages(String[] Languages) Set ASR Supported Languages, default is "zh" Chinese, Fill in the array with up to 4 languages, the first is the primary language for recognition, followed by optional languages, Note: When the primary language is a Chinese dialect, optional languages are invalid Currently, the supported languages are as follows.
void	setLLMType(String LLMType) Set Model interface protocol types, currently compatible with three protocol types: - OpenAI protocol (including GPT, DeepSeek, etc.):"openai" - Azure protocol:"azure" - Minimax protocol:"minimax"
void	setMaxDuration(Long MaxDuration) Set Maximum Waiting Duration (milliseconds), default is 60 seconds, if the user does not speak within this time, the call is automatically terminated
void	setModel(String Model) Set Model name, such as - OpenAI protocol "gpt-4o-mini","gpt-4o","deepseek-chat"; - Azure protocol "gpt-4o-mini", "gpt-4o"; - Minimax protocol "deepseek-chat".
void	setNotifyDuration(Long NotifyDuration) Set The duration after which the user hasn't spoken to trigger a notification, minimum 10 seconds, default 10 seconds
void	setNotifyMaxCount(Long NotifyMaxCount) Set Maximum number of times to trigger ai prompt sound, unlimited by default.
void	setNotifyMessage(String NotifyMessage) Set The AI prompt when NotifyDuration has passed without the user speaking, default is "Sorry, I didn't hear you clearly.
void	setPromptVariables(Variable[] PromptVariables) Set Prompt word variable.
void	setSdkAppId(Long SdkAppId) Set Application ID (required) can be found at https://console.cloud.tencent.com/ccc.
void	setSystemPrompt(String SystemPrompt) Set ## Identity You are Kate from the appointment department at Retell Health calling Cindy over the phone to prepare for the annual checkup coming up.
void	setTransferFunctionEnable(Boolean TransferFunctionEnable) Set Whether the model supports (or enables) transfer_to_human function calling.
void	setTransferItems(AITransferItem[] TransferItems) Set Takes effect when transferfunctionenable is true: transfer to human configuration.
void	setVadSilenceTime(Long VadSilenceTime) Set Automatic speech recognition vad time ranges from 240 to 2000, with a default of 1000, measured in milliseconds.
void	setVoiceType(String VoiceType) Set The following voice parameter values are available by default.
void	setWelcomeMessage(String WelcomeMessage) Set Used to set the AI Agent Greeting.
void	setWelcomeMessagePriority(Long WelcomeMessagePriority) Set 0: interruptible by default, 1: high priority and not interruptible.
void	setWelcomeType(Long WelcomeType) Set 0: Use welcomeMessage (if empty, the callee speaks first; if not empty, the bot speaks first) 1: Use AI to automatically generate welcomeMessage and speak first based on the prompt
void	toMap(HashMap<String,String> map, String prefix) Internal implementation, normal users should not use it.

Methods inherited from class com.tencentcloudapi.common.AbstractModel

any, fromJsonString, getBinaryParams, GetHeader, getMultipartRequestParams, getSkipSign, set, SetHeader, setParamArrayObj, setParamArraySimple, setParamObj, setParamSimple, setSkipSign, toJsonString

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

CreateAICallRequest

public CreateAICallRequest()

CreateAICallRequest

public CreateAICallRequest(CreateAICallRequest source)

NOTE: Any ambiguous key set via .set("AnyKey", "value") will be a shallow copy, and any explicit key, i.e Foo, set via .setFoo("value") will be a deep copy.

Method Detail

getSdkAppId

public Long getSdkAppId()

Get Application ID (required) can be found at https://console.cloud.tencent.com/ccc.

Returns:

SdkAppId Application ID (required) can be found at https://console.cloud.tencent.com/ccc.

setSdkAppId

public void setSdkAppId(Long SdkAppId)

Set Application ID (required) can be found at https://console.cloud.tencent.com/ccc.

Parameters:

SdkAppId - Application ID (required) can be found at https://console.cloud.tencent.com/ccc.

getCallee

public String getCallee()

Get Called number.

Returns:

Callee Called number.

setCallee

public void setCallee(String Callee)

Set Called number.

Parameters:

Callee - Called number.

getSystemPrompt

public String getSystemPrompt()

Get ## Identity You are Kate from the appointment department at Retell Health calling Cindy over the phone to prepare for the annual checkup coming up. You are a pleasant and friendly receptionist caring deeply for the user. You don't provide medical advice but would use the medical knowledge to understand user responses. ## Style Guardrails Be Concise: Respond succinctly, addressing one topic at most. Embrace Variety: Use diverse language and rephrasing to enhance clarity without repeating content. Be Conversational: Use everyday language, making the chat feel like talking to a friend. Be Proactive: Lead the conversation, often wrapping up with a question or next-step suggestion. Avoid multiple questions in a single response. Get clarity: If the user only partially answers a question, or if the answer is unclear, keep asking to get clarity. Use a colloquial way of referring to the date (like Friday, January 14th, or Tuesday, January 12th, 2024 at 8am). ## Response Guideline Adapt and Guess: Try to understand transcripts that may contain transcription errors. Avoid mentioning "transcription error" in the response. Stay in Character: Keep conversations within your role's scope, guiding them back creatively without repeating. Ensure Fluid Dialogue: Respond in a role-appropriate, direct manner to maintain a smooth conversation flow. ## Task You will follow the steps below, do not skip steps, and only ask up to one question in response. If at any time the user showed anger or wanted a human agent, call transfer_call to transfer to a human representative. 1. Begin with a self-introduction and verify if callee is Cindy. - if callee is not Cindy, call end_call to hang up, say sorry for the confusion when hanging up. - if Cindy is not available, call end_call politely to hang up, say you will call back later when hanging up. 2. Inform Cindy she has an annual body check coming up on April 4th, 2024 at 10am PDT. Check if Cindy is available. - If not, tell Cindy to reschedule online and jump to step 5. 3. Ask Cindy if there's anything that the doctor should know before the annual checkup. - Ask followup questions as needed to assess the severity of the issue, and understand how it has progressed. 4. Tell Cindy to not eat or drink that day before the checkup. Also tell Cindy to give you a callback if there's any changes in health condition. 5. Ask Cindy if she has any questions, and if so, answer them until there are no questions. - If user asks something you do not know, let them know you don't have the answer. Ask them if they have any other questions. - If user do not have any questions, call function end_call to hang up.

Returns:

SystemPrompt ## Identity You are Kate from the appointment department at Retell Health calling Cindy over the phone to prepare for the annual checkup coming up. You are a pleasant and friendly receptionist caring deeply for the user. You don't provide medical advice but would use the medical knowledge to understand user responses. ## Style Guardrails Be Concise: Respond succinctly, addressing one topic at most. Embrace Variety: Use diverse language and rephrasing to enhance clarity without repeating content. Be Conversational: Use everyday language, making the chat feel like talking to a friend. Be Proactive: Lead the conversation, often wrapping up with a question or next-step suggestion. Avoid multiple questions in a single response. Get clarity: If the user only partially answers a question, or if the answer is unclear, keep asking to get clarity. Use a colloquial way of referring to the date (like Friday, January 14th, or Tuesday, January 12th, 2024 at 8am). ## Response Guideline Adapt and Guess: Try to understand transcripts that may contain transcription errors. Avoid mentioning "transcription error" in the response. Stay in Character: Keep conversations within your role's scope, guiding them back creatively without repeating. Ensure Fluid Dialogue: Respond in a role-appropriate, direct manner to maintain a smooth conversation flow. ## Task You will follow the steps below, do not skip steps, and only ask up to one question in response. If at any time the user showed anger or wanted a human agent, call transfer_call to transfer to a human representative. 1. Begin with a self-introduction and verify if callee is Cindy. - if callee is not Cindy, call end_call to hang up, say sorry for the confusion when hanging up. - if Cindy is not available, call end_call politely to hang up, say you will call back later when hanging up. 2. Inform Cindy she has an annual body check coming up on April 4th, 2024 at 10am PDT. Check if Cindy is available. - If not, tell Cindy to reschedule online and jump to step 5. 3. Ask Cindy if there's anything that the doctor should know before the annual checkup. - Ask followup questions as needed to assess the severity of the issue, and understand how it has progressed. 4. Tell Cindy to not eat or drink that day before the checkup. Also tell Cindy to give you a callback if there's any changes in health condition. 5. Ask Cindy if she has any questions, and if so, answer them until there are no questions. - If user asks something you do not know, let them know you don't have the answer. Ask them if they have any other questions. - If user do not have any questions, call function end_call to hang up.

setSystemPrompt

public void setSystemPrompt(String SystemPrompt)

Set ## Identity You are Kate from the appointment department at Retell Health calling Cindy over the phone to prepare for the annual checkup coming up. You are a pleasant and friendly receptionist caring deeply for the user. You don't provide medical advice but would use the medical knowledge to understand user responses. ## Style Guardrails Be Concise: Respond succinctly, addressing one topic at most. Embrace Variety: Use diverse language and rephrasing to enhance clarity without repeating content. Be Conversational: Use everyday language, making the chat feel like talking to a friend. Be Proactive: Lead the conversation, often wrapping up with a question or next-step suggestion. Avoid multiple questions in a single response. Get clarity: If the user only partially answers a question, or if the answer is unclear, keep asking to get clarity. Use a colloquial way of referring to the date (like Friday, January 14th, or Tuesday, January 12th, 2024 at 8am). ## Response Guideline Adapt and Guess: Try to understand transcripts that may contain transcription errors. Avoid mentioning "transcription error" in the response. Stay in Character: Keep conversations within your role's scope, guiding them back creatively without repeating. Ensure Fluid Dialogue: Respond in a role-appropriate, direct manner to maintain a smooth conversation flow. ## Task You will follow the steps below, do not skip steps, and only ask up to one question in response. If at any time the user showed anger or wanted a human agent, call transfer_call to transfer to a human representative. 1. Begin with a self-introduction and verify if callee is Cindy. - if callee is not Cindy, call end_call to hang up, say sorry for the confusion when hanging up. - if Cindy is not available, call end_call politely to hang up, say you will call back later when hanging up. 2. Inform Cindy she has an annual body check coming up on April 4th, 2024 at 10am PDT. Check if Cindy is available. - If not, tell Cindy to reschedule online and jump to step 5. 3. Ask Cindy if there's anything that the doctor should know before the annual checkup. - Ask followup questions as needed to assess the severity of the issue, and understand how it has progressed. 4. Tell Cindy to not eat or drink that day before the checkup. Also tell Cindy to give you a callback if there's any changes in health condition. 5. Ask Cindy if she has any questions, and if so, answer them until there are no questions. - If user asks something you do not know, let them know you don't have the answer. Ask them if they have any other questions. - If user do not have any questions, call function end_call to hang up.

Parameters:

SystemPrompt - ## Identity You are Kate from the appointment department at Retell Health calling Cindy over the phone to prepare for the annual checkup coming up. You are a pleasant and friendly receptionist caring deeply for the user. You don't provide medical advice but would use the medical knowledge to understand user responses. ## Style Guardrails Be Concise: Respond succinctly, addressing one topic at most. Embrace Variety: Use diverse language and rephrasing to enhance clarity without repeating content. Be Conversational: Use everyday language, making the chat feel like talking to a friend. Be Proactive: Lead the conversation, often wrapping up with a question or next-step suggestion. Avoid multiple questions in a single response. Get clarity: If the user only partially answers a question, or if the answer is unclear, keep asking to get clarity. Use a colloquial way of referring to the date (like Friday, January 14th, or Tuesday, January 12th, 2024 at 8am). ## Response Guideline Adapt and Guess: Try to understand transcripts that may contain transcription errors. Avoid mentioning "transcription error" in the response. Stay in Character: Keep conversations within your role's scope, guiding them back creatively without repeating. Ensure Fluid Dialogue: Respond in a role-appropriate, direct manner to maintain a smooth conversation flow. ## Task You will follow the steps below, do not skip steps, and only ask up to one question in response. If at any time the user showed anger or wanted a human agent, call transfer_call to transfer to a human representative. 1. Begin with a self-introduction and verify if callee is Cindy. - if callee is not Cindy, call end_call to hang up, say sorry for the confusion when hanging up. - if Cindy is not available, call end_call politely to hang up, say you will call back later when hanging up. 2. Inform Cindy she has an annual body check coming up on April 4th, 2024 at 10am PDT. Check if Cindy is available. - If not, tell Cindy to reschedule online and jump to step 5. 3. Ask Cindy if there's anything that the doctor should know before the annual checkup. - Ask followup questions as needed to assess the severity of the issue, and understand how it has progressed. 4. Tell Cindy to not eat or drink that day before the checkup. Also tell Cindy to give you a callback if there's any changes in health condition. 5. Ask Cindy if she has any questions, and if so, answer them until there are no questions. - If user asks something you do not know, let them know you don't have the answer. Ask them if they have any other questions. - If user do not have any questions, call function end_call to hang up.

getLLMType

public String getLLMType()

Get Model interface protocol types, currently compatible with three protocol types: - OpenAI protocol (including GPT, DeepSeek, etc.):"openai" - Azure protocol:"azure" - Minimax protocol:"minimax"

Returns:

LLMType Model interface protocol types, currently compatible with three protocol types: - OpenAI protocol (including GPT, DeepSeek, etc.):"openai" - Azure protocol:"azure" - Minimax protocol:"minimax"

setLLMType

public void setLLMType(String LLMType)

Set Model interface protocol types, currently compatible with three protocol types: - OpenAI protocol (including GPT, DeepSeek, etc.):"openai" - Azure protocol:"azure" - Minimax protocol:"minimax"

Parameters:

LLMType - Model interface protocol types, currently compatible with three protocol types: - OpenAI protocol (including GPT, DeepSeek, etc.):"openai" - Azure protocol:"azure" - Minimax protocol:"minimax"

getModel

public String getModel()

Get Model name, such as - OpenAI protocol "gpt-4o-mini","gpt-4o","deepseek-chat"; - Azure protocol "gpt-4o-mini", "gpt-4o"; - Minimax protocol "deepseek-chat".

Returns:

Model Model name, such as - OpenAI protocol "gpt-4o-mini","gpt-4o","deepseek-chat"; - Azure protocol "gpt-4o-mini", "gpt-4o"; - Minimax protocol "deepseek-chat".

setModel

public void setModel(String Model)

Set Model name, such as - OpenAI protocol "gpt-4o-mini","gpt-4o","deepseek-chat"; - Azure protocol "gpt-4o-mini", "gpt-4o"; - Minimax protocol "deepseek-chat".

Parameters:

Model - Model name, such as - OpenAI protocol "gpt-4o-mini","gpt-4o","deepseek-chat"; - Azure protocol "gpt-4o-mini", "gpt-4o"; - Minimax protocol "deepseek-chat".

getAPIKey

public String getAPIKey()

Get Model API key, for authentication information, please refer to the respective model's official website - OpenAI protocol: [GPT](https://help.openai.com/en/articles/4936850-where-do-i-find-my-openai-api-key), [Hunyuan](https://intl.cloud.tencent.com/document/product/1729/111008?from_cn_redirect=1), [DeepSeek](https://api-docs.deepseek.com/zh-cn/); - Azure protocol: [Azure GPT](https://learn.microsoft.com/en-us/azure/ai-services/openai/chatgpt-quickstart?tabs=command-line%2Ctypescript%2Cpython-new&pivots=programming-language-studio#key-settings); - Minimax:[Minimax](https://platform.minimaxi.com/document/Fast%20access?key=66701cf51d57f38758d581b2)

Returns:

APIKey Model API key, for authentication information, please refer to the respective model's official website - OpenAI protocol: [GPT](https://help.openai.com/en/articles/4936850-where-do-i-find-my-openai-api-key), [Hunyuan](https://intl.cloud.tencent.com/document/product/1729/111008?from_cn_redirect=1), [DeepSeek](https://api-docs.deepseek.com/zh-cn/); - Azure protocol: [Azure GPT](https://learn.microsoft.com/en-us/azure/ai-services/openai/chatgpt-quickstart?tabs=command-line%2Ctypescript%2Cpython-new&pivots=programming-language-studio#key-settings); - Minimax:[Minimax](https://platform.minimaxi.com/document/Fast%20access?key=66701cf51d57f38758d581b2)

setAPIKey

public void setAPIKey(String APIKey)

Set Model API key, for authentication information, please refer to the respective model's official website - OpenAI protocol: [GPT](https://help.openai.com/en/articles/4936850-where-do-i-find-my-openai-api-key), [Hunyuan](https://intl.cloud.tencent.com/document/product/1729/111008?from_cn_redirect=1), [DeepSeek](https://api-docs.deepseek.com/zh-cn/); - Azure protocol: [Azure GPT](https://learn.microsoft.com/en-us/azure/ai-services/openai/chatgpt-quickstart?tabs=command-line%2Ctypescript%2Cpython-new&pivots=programming-language-studio#key-settings); - Minimax:[Minimax](https://platform.minimaxi.com/document/Fast%20access?key=66701cf51d57f38758d581b2)

Parameters:

APIKey - Model API key, for authentication information, please refer to the respective model's official website - OpenAI protocol: [GPT](https://help.openai.com/en/articles/4936850-where-do-i-find-my-openai-api-key), [Hunyuan](https://intl.cloud.tencent.com/document/product/1729/111008?from_cn_redirect=1), [DeepSeek](https://api-docs.deepseek.com/zh-cn/); - Azure protocol: [Azure GPT](https://learn.microsoft.com/en-us/azure/ai-services/openai/chatgpt-quickstart?tabs=command-line%2Ctypescript%2Cpython-new&pivots=programming-language-studio#key-settings); - Minimax:[Minimax](https://platform.minimaxi.com/document/Fast%20access?key=66701cf51d57f38758d581b2)

getAPIUrl

public String getAPIUrl()

Get Model interface address - OpenAI protocol GPT:"https://api.openai.com/v1/" Deepseek:"https://api.deepseek.com/v1" - Azure protocol "https://{your-resource-name}.openai.azure.com?api-version={api-version}" - Minimax protocol "https://api.minimax.chat/v1"

Returns:

APIUrl Model interface address - OpenAI protocol GPT:"https://api.openai.com/v1/" Deepseek:"https://api.deepseek.com/v1" - Azure protocol "https://{your-resource-name}.openai.azure.com?api-version={api-version}" - Minimax protocol "https://api.minimax.chat/v1"

setAPIUrl

public void setAPIUrl(String APIUrl)

Set Model interface address - OpenAI protocol GPT:"https://api.openai.com/v1/" Deepseek:"https://api.deepseek.com/v1" - Azure protocol "https://{your-resource-name}.openai.azure.com?api-version={api-version}" - Minimax protocol "https://api.minimax.chat/v1"

Parameters:

APIUrl - Model interface address - OpenAI protocol GPT:"https://api.openai.com/v1/" Deepseek:"https://api.deepseek.com/v1" - Azure protocol "https://{your-resource-name}.openai.azure.com?api-version={api-version}" - Minimax protocol "https://api.minimax.chat/v1"

getVoiceType

public String getVoiceType()

Get The following voice parameter values are available by default. If you wish to customize the voice type, please leave VoiceType blank and configure it in the CustomTTSConfig parameter. Chinese: ZhiMei: Zhimei, customer service female voice ZhiXi: Zhixi, general female voice ZhiQi: Zhiqi, customer service female voice ZhiTian: Zhitian, female child voice AiXiaoJing: Ai Xiaojing, dialogue female voice English: WeRose:English Female Voice Monika:English Female Voice Japanese: Nanami Korean: SunHi Indonesian (Indonesia): Gadis Malay (Malaysia): Yasmin Tamil (Malaysia): Kani Thai (Thailand): Achara Vietnamese (Vietnam): HoaiMy

Returns:

VoiceType The following voice parameter values are available by default. If you wish to customize the voice type, please leave VoiceType blank and configure it in the CustomTTSConfig parameter. Chinese: ZhiMei: Zhimei, customer service female voice ZhiXi: Zhixi, general female voice ZhiQi: Zhiqi, customer service female voice ZhiTian: Zhitian, female child voice AiXiaoJing: Ai Xiaojing, dialogue female voice English: WeRose:English Female Voice Monika:English Female Voice Japanese: Nanami Korean: SunHi Indonesian (Indonesia): Gadis Malay (Malaysia): Yasmin Tamil (Malaysia): Kani Thai (Thailand): Achara Vietnamese (Vietnam): HoaiMy

setVoiceType

public void setVoiceType(String VoiceType)

Set The following voice parameter values are available by default. If you wish to customize the voice type, please leave VoiceType blank and configure it in the CustomTTSConfig parameter. Chinese: ZhiMei: Zhimei, customer service female voice ZhiXi: Zhixi, general female voice ZhiQi: Zhiqi, customer service female voice ZhiTian: Zhitian, female child voice AiXiaoJing: Ai Xiaojing, dialogue female voice English: WeRose:English Female Voice Monika:English Female Voice Japanese: Nanami Korean: SunHi Indonesian (Indonesia): Gadis Malay (Malaysia): Yasmin Tamil (Malaysia): Kani Thai (Thailand): Achara Vietnamese (Vietnam): HoaiMy

Parameters:

VoiceType - The following voice parameter values are available by default. If you wish to customize the voice type, please leave VoiceType blank and configure it in the CustomTTSConfig parameter. Chinese: ZhiMei: Zhimei, customer service female voice ZhiXi: Zhixi, general female voice ZhiQi: Zhiqi, customer service female voice ZhiTian: Zhitian, female child voice AiXiaoJing: Ai Xiaojing, dialogue female voice English: WeRose:English Female Voice Monika:English Female Voice Japanese: Nanami Korean: SunHi Indonesian (Indonesia): Gadis Malay (Malaysia): Yasmin Tamil (Malaysia): Kani Thai (Thailand): Achara Vietnamese (Vietnam): HoaiMy

getCallers

public String[] getCallers()

Get Caller number list

Returns:

Callers Caller number list

setCallers

public void setCallers(String[] Callers)

Set Caller number list

Parameters:

Callers - Caller number list

getWelcomeMessage

public String getWelcomeMessage()

Get Used to set the AI Agent Greeting.

Returns:

WelcomeMessage Used to set the AI Agent Greeting.

setWelcomeMessage

public void setWelcomeMessage(String WelcomeMessage)

Set Used to set the AI Agent Greeting.

Parameters:

WelcomeMessage - Used to set the AI Agent Greeting.

getWelcomeType

public Long getWelcomeType()

Get 0: Use welcomeMessage (if empty, the callee speaks first; if not empty, the bot speaks first) 1: Use AI to automatically generate welcomeMessage and speak first based on the prompt

Returns:

WelcomeType 0: Use welcomeMessage (if empty, the callee speaks first; if not empty, the bot speaks first) 1: Use AI to automatically generate welcomeMessage and speak first based on the prompt

setWelcomeType

public void setWelcomeType(Long WelcomeType)

Set 0: Use welcomeMessage (if empty, the callee speaks first; if not empty, the bot speaks first) 1: Use AI to automatically generate welcomeMessage and speak first based on the prompt

Parameters:

WelcomeType - 0: Use welcomeMessage (if empty, the callee speaks first; if not empty, the bot speaks first) 1: Use AI to automatically generate welcomeMessage and speak first based on the prompt

getWelcomeMessagePriority

public Long getWelcomeMessagePriority()

Get 0: interruptible by default, 1: high priority and not interruptible.

Returns:

WelcomeMessagePriority 0: interruptible by default, 1: high priority and not interruptible.

setWelcomeMessagePriority

public void setWelcomeMessagePriority(Long WelcomeMessagePriority)

Set 0: interruptible by default, 1: high priority and not interruptible.

Parameters:

WelcomeMessagePriority - 0: interruptible by default, 1: high priority and not interruptible.

getMaxDuration

public Long getMaxDuration()

Get Maximum Waiting Duration (milliseconds), default is 60 seconds, if the user does not speak within this time, the call is automatically terminated

Returns:

MaxDuration Maximum Waiting Duration (milliseconds), default is 60 seconds, if the user does not speak within this time, the call is automatically terminated

setMaxDuration

public void setMaxDuration(Long MaxDuration)

Set Maximum Waiting Duration (milliseconds), default is 60 seconds, if the user does not speak within this time, the call is automatically terminated

Parameters:

MaxDuration - Maximum Waiting Duration (milliseconds), default is 60 seconds, if the user does not speak within this time, the call is automatically terminated

getLanguages

public String[] getLanguages()

Get ASR Supported Languages, default is "zh" Chinese, Fill in the array with up to 4 languages, the first is the primary language for recognition, followed by optional languages, Note: When the primary language is a Chinese dialect, optional languages are invalid Currently, the supported languages are as follows. The English name of the language is on the left side of the equals sign, and the value to be filled in the Language field is on the right side, following ISO639: 1. Chinese = "zh" # Chinese 2. Chinese_TW = "zh-TW" # Taiwan (China) 3. Chinese_DIALECT = "zh-dialect" # Chinese Dialect 4. English = "en" # English 5. Vietnamese = "vi" # Vietnamese 6. Japanese = "ja" # Japanese 7. Korean = "ko" # Korean 8. Indonesia = "id" # Indonesian 9. Thai = "th" # Thai 10. Portuguese = "pt" # Portuguese 11. Turkish = "tr" # Turkish 12. Arabic = "ar" # Arabic 13. Spanish = "es" # Spanish 14. Hindi = "hi" # Hindi 15. French = "fr" # French 16. Malay = "ms" # Malay 17. Filipino = "fil" # Filipino 18. German = "de" # German 19. Italian = "it" # Italian 20. Russian = "ru" # Russian

Returns:

Languages ASR Supported Languages, default is "zh" Chinese, Fill in the array with up to 4 languages, the first is the primary language for recognition, followed by optional languages, Note: When the primary language is a Chinese dialect, optional languages are invalid Currently, the supported languages are as follows. The English name of the language is on the left side of the equals sign, and the value to be filled in the Language field is on the right side, following ISO639: 1. Chinese = "zh" # Chinese 2. Chinese_TW = "zh-TW" # Taiwan (China) 3. Chinese_DIALECT = "zh-dialect" # Chinese Dialect 4. English = "en" # English 5. Vietnamese = "vi" # Vietnamese 6. Japanese = "ja" # Japanese 7. Korean = "ko" # Korean 8. Indonesia = "id" # Indonesian 9. Thai = "th" # Thai 10. Portuguese = "pt" # Portuguese 11. Turkish = "tr" # Turkish 12. Arabic = "ar" # Arabic 13. Spanish = "es" # Spanish 14. Hindi = "hi" # Hindi 15. French = "fr" # French 16. Malay = "ms" # Malay 17. Filipino = "fil" # Filipino 18. German = "de" # German 19. Italian = "it" # Italian 20. Russian = "ru" # Russian

setLanguages

public void setLanguages(String[] Languages)

Set ASR Supported Languages, default is "zh" Chinese, Fill in the array with up to 4 languages, the first is the primary language for recognition, followed by optional languages, Note: When the primary language is a Chinese dialect, optional languages are invalid Currently, the supported languages are as follows. The English name of the language is on the left side of the equals sign, and the value to be filled in the Language field is on the right side, following ISO639: 1. Chinese = "zh" # Chinese 2. Chinese_TW = "zh-TW" # Taiwan (China) 3. Chinese_DIALECT = "zh-dialect" # Chinese Dialect 4. English = "en" # English 5. Vietnamese = "vi" # Vietnamese 6. Japanese = "ja" # Japanese 7. Korean = "ko" # Korean 8. Indonesia = "id" # Indonesian 9. Thai = "th" # Thai 10. Portuguese = "pt" # Portuguese 11. Turkish = "tr" # Turkish 12. Arabic = "ar" # Arabic 13. Spanish = "es" # Spanish 14. Hindi = "hi" # Hindi 15. French = "fr" # French 16. Malay = "ms" # Malay 17. Filipino = "fil" # Filipino 18. German = "de" # German 19. Italian = "it" # Italian 20. Russian = "ru" # Russian

Parameters:

Languages - ASR Supported Languages, default is "zh" Chinese, Fill in the array with up to 4 languages, the first is the primary language for recognition, followed by optional languages, Note: When the primary language is a Chinese dialect, optional languages are invalid Currently, the supported languages are as follows. The English name of the language is on the left side of the equals sign, and the value to be filled in the Language field is on the right side, following ISO639: 1. Chinese = "zh" # Chinese 2. Chinese_TW = "zh-TW" # Taiwan (China) 3. Chinese_DIALECT = "zh-dialect" # Chinese Dialect 4. English = "en" # English 5. Vietnamese = "vi" # Vietnamese 6. Japanese = "ja" # Japanese 7. Korean = "ko" # Korean 8. Indonesia = "id" # Indonesian 9. Thai = "th" # Thai 10. Portuguese = "pt" # Portuguese 11. Turkish = "tr" # Turkish 12. Arabic = "ar" # Arabic 13. Spanish = "es" # Spanish 14. Hindi = "hi" # Hindi 15. French = "fr" # French 16. Malay = "ms" # Malay 17. Filipino = "fil" # Filipino 18. German = "de" # German 19. Italian = "it" # Italian 20. Russian = "ru" # Russian

getInterruptMode

public Long getInterruptMode()

Get Interrupt ai speaking mode. default is 0. 0 indicates automatic interruption and 1 indicates no interruption.

Returns:

InterruptMode Interrupt ai speaking mode. default is 0. 0 indicates automatic interruption and 1 indicates no interruption.

setInterruptMode

public void setInterruptMode(Long InterruptMode)

Set Interrupt ai speaking mode. default is 0. 0 indicates automatic interruption and 1 indicates no interruption.

Parameters:

InterruptMode - Interrupt ai speaking mode. default is 0. 0 indicates automatic interruption and 1 indicates no interruption.

getInterruptSpeechDuration

public Long getInterruptSpeechDuration()

Get Used when InterruptMode is 0, unit in milliseconds, default is 500ms. It means that the server-side detects ongoing vocal input for the InterruptSpeechDuration milliseconds and then interrupts.

Returns:

InterruptSpeechDuration Used when InterruptMode is 0, unit in milliseconds, default is 500ms. It means that the server-side detects ongoing vocal input for the InterruptSpeechDuration milliseconds and then interrupts.

setInterruptSpeechDuration

public void setInterruptSpeechDuration(Long InterruptSpeechDuration)

Set Used when InterruptMode is 0, unit in milliseconds, default is 500ms. It means that the server-side detects ongoing vocal input for the InterruptSpeechDuration milliseconds and then interrupts.

Parameters:

InterruptSpeechDuration - Used when InterruptMode is 0, unit in milliseconds, default is 500ms. It means that the server-side detects ongoing vocal input for the InterruptSpeechDuration milliseconds and then interrupts.

getEndFunctionEnable

public Boolean getEndFunctionEnable()

Get Whether the model supports (or enables) call_end function calling

Returns:

EndFunctionEnable Whether the model supports (or enables) call_end function calling

setEndFunctionEnable

public void setEndFunctionEnable(Boolean EndFunctionEnable)

Set Whether the model supports (or enables) call_end function calling

Parameters:

EndFunctionEnable - Whether the model supports (or enables) call_end function calling

getEndFunctionDesc

public String getEndFunctionDesc()

Get Effective when EndFunctionEnable is true; the description of call_end function calling, default is "End the call when user has to leave (like says bye) or you are instructed to do so."

Returns:

EndFunctionDesc Effective when EndFunctionEnable is true; the description of call_end function calling, default is "End the call when user has to leave (like says bye) or you are instructed to do so."

setEndFunctionDesc

public void setEndFunctionDesc(String EndFunctionDesc)

Set Effective when EndFunctionEnable is true; the description of call_end function calling, default is "End the call when user has to leave (like says bye) or you are instructed to do so."

Parameters:

EndFunctionDesc - Effective when EndFunctionEnable is true; the description of call_end function calling, default is "End the call when user has to leave (like says bye) or you are instructed to do so."

getTransferFunctionEnable

public Boolean getTransferFunctionEnable()

Get Whether the model supports (or enables) transfer_to_human function calling.

Returns:

TransferFunctionEnable Whether the model supports (or enables) transfer_to_human function calling.

setTransferFunctionEnable

public void setTransferFunctionEnable(Boolean TransferFunctionEnable)

Set Whether the model supports (or enables) transfer_to_human function calling.

Parameters:

TransferFunctionEnable - Whether the model supports (or enables) transfer_to_human function calling.

getTransferItems

public AITransferItem[] getTransferItems()

Get Takes effect when transferfunctionenable is true: transfer to human configuration.

Returns:

TransferItems Takes effect when transferfunctionenable is true: transfer to human configuration.

setTransferItems

public void setTransferItems(AITransferItem[] TransferItems)

Set Takes effect when transferfunctionenable is true: transfer to human configuration.

Parameters:

TransferItems - Takes effect when transferfunctionenable is true: transfer to human configuration.

getNotifyDuration

public Long getNotifyDuration()

Get The duration after which the user hasn't spoken to trigger a notification, minimum 10 seconds, default 10 seconds

Returns:

NotifyDuration The duration after which the user hasn't spoken to trigger a notification, minimum 10 seconds, default 10 seconds

setNotifyDuration

public void setNotifyDuration(Long NotifyDuration)

Set The duration after which the user hasn't spoken to trigger a notification, minimum 10 seconds, default 10 seconds

Parameters:

NotifyDuration - The duration after which the user hasn't spoken to trigger a notification, minimum 10 seconds, default 10 seconds

getNotifyMessage

public String getNotifyMessage()

Get The AI prompt when NotifyDuration has passed without the user speaking, default is "Sorry, I didn't hear you clearly. Can you repeat that?"

Returns:

NotifyMessage The AI prompt when NotifyDuration has passed without the user speaking, default is "Sorry, I didn't hear you clearly. Can you repeat that?"

setNotifyMessage

public void setNotifyMessage(String NotifyMessage)

Set The AI prompt when NotifyDuration has passed without the user speaking, default is "Sorry, I didn't hear you clearly. Can you repeat that?"

Parameters:

NotifyMessage - The AI prompt when NotifyDuration has passed without the user speaking, default is "Sorry, I didn't hear you clearly. Can you repeat that?"

getNotifyMaxCount

public Long getNotifyMaxCount()

Get Maximum number of times to trigger ai prompt sound, unlimited by default.

Returns:

NotifyMaxCount Maximum number of times to trigger ai prompt sound, unlimited by default.

setNotifyMaxCount

public void setNotifyMaxCount(Long NotifyMaxCount)

Set Maximum number of times to trigger ai prompt sound, unlimited by default.

Parameters:

NotifyMaxCount - Maximum number of times to trigger ai prompt sound, unlimited by default.

getCustomTTSConfig

public String getCustomTTSConfig()

Get

And VoiceType field needs to select one, here is to use your own custom TTS, VoiceType is some built-in sound qualities

• Tencent TTS
  For configuration, please refer to Tencent Cloud TTS documentation link

{
    "TTSType": "tencent", // String TTS type, currently supports "tencent" and "minixmax", other vendors support in progress
    "AppId": "Your application ID", // String required
    "SecretId": "Your Secret ID", // String Required
    "SecretKey":  "Your Secret Key", // String Required
    "VoiceType": 101001, // Integer Required, Sound quality ID, includes standard and premium sound quality. Premium sound quality is more realistic and differently priced than standard sound quality. See TTS billing overview for details. For the full list of sound quality IDs, see the TTS sound quality list.
    "Speed": 1.25, // Integer Optional, speech speed, range: [-2,6], corresponding to different speeds: -2: represents 0.6x -1: represents 0.8x 0: represents 1.0x (default) 1: represents 1.2x 2: represents 1.5x 6: represents 2.5x For more precise speed control, you can retain two decimal places, such as 0.5/1.25/2.81, etc. For parameter value to actual speed conversion, refer to Speed Conversion
    "Volume": 5, // Integer Optional, Volume level, range: [0,10], corresponding to 11 levels of volume, default is 0, which represents normal volume.
    "PrimaryLanguage": 1, // Integer Optional, Primary language 1- Chinese (default) 2- English 3- Japanese
    "FastVoiceType": "xxxx"   // Optional parameter, Fast VRS parameter
  }

• Azure TTS
  For configuration, refer to theAzure TTS documentation

{
    "TTSType": "azure", // Required: String TTS type
    "SubscriptionKey": "xxxxxxxx", // Required: String subscription key
    "Region": "chinanorth3",  // Required: String subscription region
    "VoiceName": "zh-CN-XiaoxiaoNeural", // Required: String Timbre Name required
    "Language": "zh-CN", // Required: String Language for synthesis
    "Rate": 1 // Optional: float Playback Speed 0.5-2 default is 1
}

• Custom

TTS
Please refer to the specific protocol standards in the Tencent documentation

{
  "TTSType": "custom", // Required String
  "APIKey": "ApiKey", // Required String for Authentication
  "APIUrl": "http://0.0.0.0:8080/stream-audio" // Required String, TTS API URL
  "AudioFormat": "wav", // String, optional, expected audio format, such as mp3, ogg_opus, pcm, wav, default is wav, currently only pcm and wav are supported,
  "SampleRate": 16000,  // Integer, optional, audio sample rate, default is 16000 (16k), recommended value is 16000
  "AudioChannel": 1,    // Integer, optional, number of audio channels, values: 1 or 2, default is 1
}