Data structures for Android SDK - Intelligent Media Services

This topic describes the data structures used by the Android software development kit (SDK).

Data structure overview

Note

Older versions of the SDK contain deprecated parameters and methods. We recommend that you upgrade to the latest version. For more information, see Android User Guide.

Structure type	Data type	Description
*Enum*	ARTCAICallAgentType	AI agent type
	ARTCAICallRobotState	The current state of the robot
	AICallErrorCode	An error occurred during the current AI call.
	VoicePrintStatusCode	The status code returned by automatic speech recognition (ASR).
	ARTCAICallSpeakingInterruptedReason	The reason why the agent's speech was interrupted.
	ARTCAICallAudioProfile	Audio encoding configuration
	ARTCAICallAudioScenario	Audio scenario configuration
	ARTCAICallVideoRenderMode	Video rendering mode
	ARTCAICallVideoRotationMode	Video rotation angle
	ARTCAICallVideoRenderMirrorMode	Video rendering image mode
	ARTCAICallTurnDetectionMode	The mode for determining whether the user has finished speaking.
*Class*	ARTCAICallConfig	Call configuration object
	ARTCAICallVideoConfig	Video configuration parameters
	ARTCAICallAudioConfig	Audio configuration parameters
	ARTCAICallAgentTemplateConfig (Deprecated)	Configurable parameters for a call
	ARTCAICallChatSyncConfig	Configuration for synchronizing agent chat records in a message-based conversation.
	ARTCAICallAgentInfo	Agent runtime information
	ARTCAICallSendTextToAgentRequest	Request object for sending text to an agent
	ARTCAICallVisionCustomCaptureRequest	Request object for custom frame capture for the visual large model.
	ARTCAICallVideoCanvas	Video rendering configuration object
	ARTCAICallAgentConfig	Configurable parameters for a call
	ARTCAICallAgentAsrConfig	Speech recognition configuration
	ARTCAICallAgentTtsConfig	Speech synthesis configuration
	ARTCAICallAgentLlmConfig	Large language model configuration
	ARTCAICallAgentAvatarConfig	Digital human configuration
	ARTCAICallAgentInterruptConfig	Interruption configuration
	ARTCAICallAgentVoiceprintConfig	Voiceprint-based noise reduction configuration
	ARTCAICallAgentTurnDetectionConfig	Turn detection configuration
	ARTCAICallAgentVcrResult	VCR detection result
	FrameMotionResult	Video frame detection result from VCR
	PeopleCountResult	People count detection result from VCR
	EquipmentResult	Electronic device detection result from VCR
	HeadMotionResult	Head motion detection result from VCR
	ARTCAICallAgentVcrConfig	VCR configuration
	ARTCAICallAgentVcrBaseConfig	Basic VCR detection configuration
	ARTCAICallAgentVcrFrameMotionConfig	VCR video frame detection configuration
	ARTCAICallExperimentalConfig	Experimental parameters used to control specific logic policies.

Data structure details

Enum

ARTCAICallAgentType

The type of AI agent.

Enumeration name	Description
VoiceAgent	Voice-only call
AvatarAgent	Digital human call
VisionAgent	Visual understanding call
VideoAgent	Video call
ChatBot	Message-based conversation

ARTCAICallRobotState

The current state of the robot.

Enumeration name	Description
Listening	Listening
Thinking	Thinking
Speaking	Speaking

AICallErrorCode

An error code for the current AI call.

Enumeration name	Description
None	None
InvalidAction	Invalid API call
InvalidParams	The parameters passed to the API are invalid.
StartFailed	Failed to start the call.
AgentSubscriptionRequired	Failed to start the call. The daily free trial quota is exceeded.
AgentNotFund	The agent was not found.
TokenExpired	The call authentication token expired.
ConnectionFailed	The connection failed and the call was interrupted.
KickedByUserReplace	The call failed because different devices using the same user ID joined the same call.
KickedBySystem	The call failed because the user was removed by the system.
LocalDeviceException	The call failed due to an on-premises device issue.
AgentLeaveChannel	The agent left the channel and the call ended.
AgentConcurrentLimit	The concurrency limit for the digital human agent is reached.
AgentAudioSubscribeFailed	Failed to subscribe to the agent's audio.
AiAgentAsrUnavailable	Failed to start the third-party ASR service.
AvatarAgentUnavailable	The digital human service is unavailable.
ChatLogNotFound	The chat log was not found.
InternalError	An internal error occurred.

VoicePrintStatusCode

The status code returned by ASR.

Enumeration name	Description
Disable	Voiceprint-based noise reduction VAD is not enabled, and AIVad is disabled.
EnableWithoutRegister	Voiceprint-based noise reduction VAD is enabled, but voiceprint registration is not complete.
SpeakerRecognized	Voiceprint-based noise reduction VAD is enabled, and the main speaker is recognized.
SpeakerNotRecognized	Voiceprint-based noise reduction VAD is enabled, but the main speaker is not recognized.
DetectedSpeakerWithAIVad	AIVad is enabled, and the main speaker is recognized.
UndetectedSpeakerWithAIVad	AIVad is enabled, but the main speaker is not recognized.
Unknown	Unknown state

ARTCAICallSpeakingInterruptedReason

The reason why the agent's speech was interrupted.

Enumeration name	Description
UnKnown	Unknown reason
ByWorks	Interrupted because specific interruption words were recognized.
ByVoice	A speech interruption was detected.
ByInterruptSpeaking	Interrupted because the interruptSpeaking() API method was called.
BySpeechBroadCast	Interrupted by a proactive voice broadcast.
ByLlmQuery	Interrupted by a proactive large language model (LLM) query.

ARTCAICallAudioProfile

Audio encoding configuration.

Enumeration name	Description
ARTCAICallAudioLowQualityMode	Low-quality audio mode. Default audio sampling rate: 8000 Hz. Single sound channel. Maximum encoding bitrate: 12 kbps.
ARTCAICallAudioBasicQualityMode	Standard-quality audio mode. Default audio sampling rate: 16000 Hz. Single sound channel. Maximum encoding bitrate: 24 kbps.
ARTCAICallAudioHighQualityMode	(Default) High-quality audio mode. Default audio sampling rate: 48000 Hz. Single sound channel. Maximum encoding bitrate: 64 kbps.
ARTCAICallAudioStereoHighQualityMode	Stereo high-quality audio mode. Default audio sampling rate: 48000 Hz. Dual sound channels. Maximum encoding bitrate: 80 kbps.
ARTCAICallAudioSuperHighQualityMode	Super high-quality audio mode. Default audio sampling rate: 48000 Hz. Single sound channel. Maximum encoding bitrate: 96 kbps.
ARTCAICallAudioStereoSuperHighQualityMode	Stereo super high-quality audio mode. Default audio sampling rate: 48000 Hz. Dual sound channels. Maximum encoding bitrate: 128 kbps.

ARTCAICallAudioScenario

Audio scenario configuration.

Enumeration name	Description
ARTCAICallAudioSceneDefaultMode	Recommended for general Real-Time Communication scenarios.
ARTCAICallAudioSceneMusicMode	Audio scenario configuration. Recommended for scenarios that require high-fidelity music quality, such as musical instrument instruction.

ARTCAICallVideoRenderMode

Video rendering mode.

Enumeration name	Description
ARTCAICallVideoRenderModeAuto	Automatic mode
ARTCAICallVideoRenderModeStretch	Stretch tile mode. If the aspect ratio of the input video is different from the aspect ratio set for stream ingest, the input video is stretched to match the stream ingest ratio, which distorts the image.
ARTCAICallVideoRenderModeFill	Crop mode. If the aspect ratio of the input video is different from the aspect ratio set for stream ingest, the width or height of the input video is cropped, which causes a loss of image content.
ARTCAICallVideoRenderModeNoChange	No change

ARTCAICallVideoRotationMode

Video rotation angle.

Enumeration name	Description
ARTCAICallVideoRotationMode_0	0 degrees
ARTCAICallVideoRotationMode_90	90 degrees
ARTCAICallVideoRotationMode_180	180 degrees
ARTCAICallVideoRotationMode_270	270 degrees

ARTCAICallVideoRenderMirrorMode

The mirroring mode for video rendering.

Enumeration name	Description
ARTCAICallVideoRenderMirrorModeOnlyFront	Only the front camera preview is mirrored. Other views are not mirrored.
ARTCAICallVideoRenderMirrorModeAllEnabled	All views are mirrored.
ARTCAICallVideoRenderMirrorModeAllDisable	No views are mirrored.

ARTCAICallTurnDetectionMode

The mode for determining whether the user has finished speaking.

Enumeration name	Description
ARTCAICallTurnDetectionNormalMode	NAT mode. AI is not used to determine whether the user has finished speaking based on semantics. The ASR silence duration is used instead.
ARTCAICallTurnDetectionSemanticMode	Semantic mode. AI is used to determine whether the user has finished speaking based on contextual semantics.

Class

ARTCAICallConfig

The call configuration object.

Parameter	Type	Description
agentId	String	The agent ID.
agentType	ARTCAICallAgentType	The agent type. This must match the type of the specified agentId. Otherwise, an error occurs when the agent starts.
agentUserId	String	The user ID of the agent. If you leave this empty, the agent service assigns a user ID.
region	String	The region where the agent service is located. This must be the same region as the specified agentId. Otherwise, an error occurs when the agent starts.
userData	String	Custom user information. This information is passed to the agent.
enableAudioDelayInfo	boolean	Specifies whether to enable statistics on conversation latency. Default value: true.
agentConfig	ARTCAICallAgentConfig	The agentConfig parameter used to start the call.
audioConfig	ARTCAICallAudioConfig	Local audio configuration
videoConfig	ARTCAICallVideoConfig	Local video configuration. This parameter takes effect only when the agent type is VisionAgent or VideoAgent.
chatSyncConfig	ARTCAICallChatSyncConfig	The configuration of the associated chat agent. If you configure this parameter, call records are synchronized to the chat agent during the call.
mAiCallVideoConfig	ARTCAICallVideoConfig	Video-related configuration (deprecated in versions 2.5 and later).
mAliCallAudioConfig	ARTCAICallAudioConfig	Audio-related configuration (deprecated in versions 2.5 and later).
mAiCallAgentTemplateConfig	ARTCAICallAgentTemplateConfig (Deprecated)	Configurable parameters for creating an AI audio or video call (deprecated in versions 2.5 and later).
mAiCallChatSyncConfig	ARTCAICallChatSyncConfig	Chat synchronization configuration. It is used to integrate the chat content of call-based agents and message-based agents into a single session (deprecated in versions 2.5 and later).

ARTCAICallVideoConfig

Video configuration parameters.

Parameter	Type	Description
useHighQualityPreview	boolean	Specifies whether to use high-definition local preview.
useFrontCameraDefault	boolean	Specifies whether to start the front camera by default.
cameraCaptureFrameRate	int	The camera capture frame rate.
useSurfaceView	boolean	Specifies whether to use SurfaceView for rendering. If you set this to false, TextureView is used for rendering.
videoEncoderWidth	int	The video encoding width.
videoEncoderHeight	int	The video encoding height.
videoEncoderFrameRate	int	The video encoding frame rate.
videoEncoderBitRate	int	The video encoding bitrate.
videoEncoderKeyFrameInterval	int	The Group of Pictures (GOP) interval. Unit: milliseconds.
isCameraMute	boolean	Specifies whether to mute the local video. Default value: false.

ARTCAICallAudioConfig

Audio configuration parameters.

Parameter	Type	Description
audioProfile	ARTCAICallAudioProfile	The audio encoding configuration. The default value is ARTCAICallAudioHighQualityMode. You can set this parameter to specify the audio sample rate and the number of sound channels.
audioScenario	ARTCAICallAudioScenario	The audio scenario configuration. The default value is ARTCAICallAudioSceneMusicMode. To specify Bluetooth for audio capture, use ARTCAICallAudioSceneDefaultMode.
enableSpeaker	boolean	Specifies whether to use the speaker or the earpiece for playback. By default, the speaker is used. Set this to false to switch to the earpiece.
isMicrophoneOn	boolean	Specifies whether to enable the microphone. Default value: true.

ARTCAICallAgentTemplateConfig (Deprecated)

Configurable parameters for a call.

Important

This type is deprecated in versions 2.5 and later. Use ARTCAICallAgentConfig instead.

Parameter	Type	Description
aiAgentId	String	The agent ID. Set this parameter when you call the call method of AICallKit to initiate an agent call. Note The agent ID is required and cannot be empty.
aiAgentRegion	String	The region where the agent service is located. Default value: cn-shanghai. Note Specify a region based on your agent.
aiAgentUserId	String	The user ID corresponding to the agent. If you do not set this, the AI Server generates a random user ID for the agent.
userExtendData	String	Business extension information in a JSON string. This information is passed to the LLM.
aiAgentGreeting	String	The agent's welcome message. The AI agent speaks this message after the user joins the call.
aiAgentUserOnlineTimeout	int	The timeout period for the agent to shut down the task if the user does not join the call. Unit: seconds. Default value: 60.
aiAgentUserOfflineTimeout	int	The timeout period for the agent to shut down the task after the user leaves the call. Unit: seconds. Default value: 5.
aiAgentWorkflowOverrideParams	String	Workflow override parameters. Default value: none.
aiAgentBailianAppParams	String	The parameters of the application center of Alibaba Cloud Model Studio. For more information, see Pass user information through to Alibaba Cloud Model Studio.
aiAgentAsrMaxSilence	int	The maximum duration of silence for speech recognition. Unit: milliseconds. Valid values: 200 to 1200. Default value: 400.
aiAgentVolume	int	The agent's speaking volume. Valid values: -1 to 100. Default value: -1. If you do not set this parameter, the recommended automatic volume mode is used.
enableVoiceInterrupt	boolean	Specifies whether to support voice interruption. Default value: true.
enableIntelligentSegment	boolean	Specifies whether to enable intelligent sentence segmentation. Default value: true.
enableVoicePrint	boolean	Specifies whether to use voiceprint recognition. Default value: false. To enable voiceprint recognition, set enableVoicePrint to true and specify voiceprintId.
voiceprintId	String	The voiceprint ID. If you set enableVoicePrint to true and specify a non-empty voiceprintId, voiceprint-based noise reduction is enabled for the current call. If this is empty, voiceprint-based noise reduction is not enabled.
aiAgentVoiceId	String	The voice ID for the agent's speech.
aiAgentMaxIdleTime	int	The maximum idle time for the agent. Unit: seconds. If the time is exceeded, the agent automatically goes offline. Set this to -1 to prevent the agent from exiting when idle. Default value: 600.
llmHistoryLimit	int	The maximum number of conversation rounds to retain in the LLM/MLLM history. If the value is less than 0, the server's default value of 10 is used.
aiAgentGracefulShutdown	boolean	Specifies whether to enable graceful shutdown. Default value: false. Note Graceful shutdown means that when the agent is stopped, for example, when the call is hung up, it finishes speaking the current sentence before stopping. This process can last for a maximum of 10 seconds.
enablePushToTalk	boolean	Specifies whether to enable push-to-talk mode. Default value: false.
aiAgentAvatarId	String	The digital human model ID. You can specify this when the agent type is AvatarAgent.
asrLanguageId	String	The ASR language ID. If you leave this empty, the agent's default configuration is used. Valid values: zh_mandarin: Chinese en: English zh_en: Chinese-English mixed es: Spanish jp: Japanese
wakeUpQuery	String	A wake-up query. This is an instruction from the user before the call starts, which the agent responds to immediately after the call begins. Example: "What's the weather like today?".
llmSystemPrompt	String	The system prompt for the LLM. Example: "You are a friendly and helpful assistant focused on providing users with accurate information and advice." Note This is not supported if the LLM node is a Model Studio workflow type.
interruptWords	List<String>	Trigger words for interrupting the conversation. Examples: "Let me interrupt" and "I see."
aiAgentLlmHistoryLimit	int	The maximum number of conversation rounds to retain in the LLM/MLLM history. Default value: 10.
aiAgentVadLevel	int	The sensitivity parameter for AIVad. This parameter helps resist human voice interference. Valid values: 0 to 11. AIVad is enabled on the client by default, and the value is 11. 0: Disables the VAD feature. 1 to 10: A higher value makes interruption more difficult. 11: Significantly different from other values. It causes less damage to the pre-processed conversation audio and provides stronger interference resistance.

ARTCAICallChatSyncConfig

Configuration for synchronizing agent chat records in a message-based chat.

Parameter	Type	Description
sessionId	String	A unique identifier for a conversation between a user and an agent. Default value: empty.
chatBotAgentId	String	The ID of the agent associated with the message-based conversation.
receiverId	String	The receiver ID for the message-based agent. This is the user's user ID.

ARTCAICallAgentInfo

Agent runtime information.

Parameter	Type	Description
agentId	String	The current agent ID.
agentType	ARTCAICallAgentType	The agent type.
agentUserId	String	The user ID of the agent in the RTC channel.
channelId	String	The RTC channel ID where the agent is located.
instanceId	String	The instance ID of the currently running agent. When an agent starts, the system assigns a unique instance ID to identify and track its entire lifecycle and running state.
requestId	String	The request ID of the currently running agent.

ARTCAICallSendTextToAgentRequest

A request object for sending text to an agent.

Parameter	Type	Description
text	String	The text message to send to the agent. Example: "What is this?".

ARTCAICallVisionCustomCaptureRequest

A request object for custom frame capture for the large vision model.

Parameter	Type	Description
text	String	The text parameter for requesting the multi-modal large model.
enableASR	boolean	Specifies whether to use the ASR result of the human voice as input for the large model. If true, the ASR result and the captured frame are sent to the large model. Otherwise, the text field and the captured frame are sent to the large model. Note This takes effect only during continuous frame capture.
isSingle	boolean	If true, it indicates a single frame capture. The custom frame capture state is exited immediately after the frame is captured. If false, it indicates continuous frame capture. The custom frame capture state is automatically exited after the specified duration.
eachDuration	int	The frame capture interval. Unit: seconds.
num	int	The number of images to capture each time.
duration	int	The duration of continuous frame capture. Unit: seconds. If isSingle is true, this is ignored. Otherwise, the custom frame capture state ends when this duration is reached.
userData	String	A JSON string for custom business information. It is passed to the large model along with the text and image frames for business processing.

ARTCAICallVideoCanvas

Video rendering configuration object.

Parameter	Type	Description
renderMode	ARTCAICallVideoRenderMode	The rendering mode. Default value: ARTCAICallVideoRenderModeAuto.
mirrorMode	ARTCAICallVideoRenderMirrorMode	The image mode. Default value: ARTCAICallVideoRenderMirrorModeOnlyFront.
rotationMode	ARTCAICallVideoRotationMode	The rotation angle. Default value: ARTCAICallVideoRotationMode_0.
zOrderOnTop	boolean	Specifies whether the SurfaceView should be placed on a display layer on top of all other windows. Default value: true.
zOrderMediaOverlay	boolean	Specifies whether the SurfaceView should be placed on a display layer on top of windows such as MediaPlayer and Camera. Default value: true.

ARTCAICallAgentConfig

Configurable parameters for a call.

Parameter	Type	Description
agentGreeting	String	The agent's welcome message. If you leave this empty, the agent's configured value is used. Maximum length: 100 characters.
wakeUpQuery	String	An instruction from the user before the call starts, which the agent responds to immediately after the call begins.
agentMaxIdleTime	int	The maximum idle time for the agent. Unit: seconds. If the time is exceeded, the agent automatically goes offline. Default value: 600.
userOnlineTimeout	int	The timeout period for the agent to shut down the task if the user does not join the call. Default value: 60.
userOfflineTimeout	int	The timeout period for the agent to shut down the task after the user leaves the call. Default value: 5.
enablePushToTalk	boolean	Specifies whether to enable push-to-talk mode.
agentGracefulShutdown	boolean	Specifies whether to enable graceful shutdown. This allows the agent to finish speaking the current sentence before stopping.
volume	int	The agent's speaking volume. Valid values: 0 to 400. Default value: 100.
workflowOverrideParams	String	Workflow override parameters
enableIntelligentSegment	boolean	Specifies whether to enable intelligent sentence segmentation.
asrConfig	ARTCAICallAgentAsrConfig	Speech recognition configuration
ttsConfig	ARTCAICallAgentTtsConfig	Speech synthesis configuration
llmConfig	ARTCAICallAgentLlmConfig	Large language model configuration
avatarConfig	ARTCAICallAgentAvatarConfig	Digital human configuration
interruptConfig	ARTCAICallAgentInterruptConfig	Interruption configuration
voiceprintConfig	ARTCAICallAgentVoiceprintConfig	Voiceprint-based noise reduction configuration
turnDetectionConfig	ARTCAICallAgentTurnDetectionConfig	Turn detection configuration
experimentalConfig	ARTCAICallExperimentalConfig	Customized, non-productized configuration
ARTCAICallAgentVcrConfig	ARTCAICallAgentVcrConfig	VCR configuration

ARTCAICallAgentAsrConfig

Speech recognition configuration.

Parameter	Type	Description
asrLanguageId	String	The ASR language ID. If you leave this empty, the agent's configured value is used.
asrMaxSilence	int	The threshold for detecting sentence breaks in speech. A silence duration exceeding this threshold is considered a sentence break. Default value: 400 ms. Valid values: 200 to 1200 ms.
asrHotWords	List<String>	A list of ASR hot words. Limit: 500 words or fewer. Each word can have a maximum of 10 characters.
vadLevel	int	The sensitivity parameter for AIVad. Default value: 11. Valid values: 0 to 11. 0: Disables the VAD feature. 1 to 10: A higher value makes interruption more difficult. 11: Significantly different from other values. It causes less damage to the pre-processed conversation audio and provides stronger interference resistance.
customParams	String	When using self-managed ASR, pass runtime parameters in URL parameter format. Example: "mode=fast&sample=16000&format=wav".
vadDuration	int	The minimum duration threshold for voice activity detection, used to control interruption sensitivity. The default value of 0 disables this feature. Valid range: 200 to 2000 milliseconds. A common range is 200 to 500, corresponding to 1 to 4 characters.

ARTCAICallAgentTtsConfig

Speech synthesis configuration.

Parameter	Type	Description
agentVoiceId	String	The voice ID for the agent's speech. If you leave this empty, the agent's configured value is used.
pronunciationRules	List	An array of pronunciation rules. A maximum of 20 rules are supported. If the array is nil or empty, no rules are used. Example: `[ { "Word": "overlap", // Target word "Pronunciation": "chongdie", // Replacement pronunciation "Type": "replacement" // Polyphone rule }, { "Word": "action", "Pronunciation": "hangdong", "Type": "replacement" } ]`
speechRate	double	The speech rate for text-to-speech (TTS) playback. This is supported for all TTS types. Valid values: 0.5 to 2.0. Default value: 1.0. If the value is less than 0, it is not sent to the server, and the configuration in the console is used.
languageId	String	The language code for TTS playback. This is valid when the TTS type is MiniMax.
emotion	String	The emotion type for TTS playback. This is valid when the TTS type is MiniMax.
modelId	String	The TTS model ID. Currently, only MiniMax is supported. Valid values: speech-01-turbo, speech-02-turbo.

ARTCAICallAgentLlmConfig

Large language model configuration.

Parameter	Type	Description
llmHistoryLimit	int	The maximum number of conversation rounds to retain in the history. Default value: 10.
llmSystemPrompt	String	The system prompt for the LLM.
bailianAppParams	String	Parameters for Model Studio Application Center.
llmCompleteReply	boolean	Specifies whether to send the complete LLM result. Note If enabled, the complete LLM result is returned through the onLLMReplyCompleted event callback after the result is generated.
openAIExtraQuery	String	Additional query parameters for the OpenAI protocol-based LLM. Note Parameters must be in the key=value format. Use the ampersand (&) to separate multiple parameters. All values must be strings.

ARTCAICallAgentAvatarConfig

Digital human configuration.

Parameter	Type	Description
agentAvatarId	String	The digital human model ID. If you leave this empty, the agent's configured value is used.

ARTCAICallAgentInterruptConfig

Interruption configuration.

Parameter	Type	Description
enableVoiceInterrupt	boolean	Specifies whether to enable intelligent interruption.
interruptWords	List<String>	Specific words or phrases that trigger a conversation interruption.

ARTCAICallAgentVoiceprintConfig

Voiceprint-based noise reduction configuration.

Parameter	Type	Description
useVoiceprint	boolean	Specifies whether to use voiceprint-based noise reduction for the current sentence break.
voiceprintId	String	The voiceprint ID. If this is not empty, voiceprint-based noise reduction is enabled for the current call.

ARTCAICallAgentTurnDetectionConfig

Turn detection configuration.

Parameter	Type	Description
turnEndWords	List<String>	Specific words that indicate the end of a sentence. Examples: "Over" and "I'm done talking."
mode	ARTCAICallTurnDetectionMode	The mode for determining whether the user has finished speaking. The default is semantic sentence segmentation mode, where AI determines if the user has finished speaking based on contextual semantics. Default value: ARTCAICallTurnDetectionSemanticMode.
semanticWaitDuration	int	The custom wait time for semantic sentence segmentation. Unit: milliseconds. Valid values: 0 to 10000. The default value of -1 indicates that the AI automatically determines the appropriate wait time. Note The semanticWaitDuration parameter is invalid in ARTCAICallTurnDetectionNormalMode mode.

ARTCAICallAgentVcrResult

VCR detection result.

Parameter	Type	Description
resultData	Object	All VCR detection results returned by the agent.
stillFrameMotionResult	FrameMotionResult	The still frame detection result from VCR.
invalidFrameMotionResult	FrameMotionResult	The invalid frame detection result from VCR.
peopleCountResult	PeopleCountResult	The real-time people count detection result from VCR.
equipmentResult	EquipmentResult	The electronic device detection result from VCR.
headMotionResult	HeadMotionResult	The head motion detection result from VCR.

FrameMotionResult

The VCR result for video frame detection.

Parameter	Type	Description
duration	int	How long ago it was sent. Unit: milliseconds.

PeopleCountResult

The VCR result for people count detection.

Parameter	Type	Description
count	int	The number of people detected by VCR.

EquipmentResult

The VCR result for electronic device detection.

Parameter	Type	Description
mobilePhoneCount	int	The total number of devices.
watchCount	int	The number of watches.
headPhoneCount	int	The number of headphones.

HeadMotionResult

The VCR result for head motion detection.

Parameter	Type	Description
nodDetected	boolean	Nodding detected
shakeDetected	boolean	Shaking head detected

ARTCAICallAgentVcrConfig

VCR configuration.

Parameter	Type	Description
data	JSONObject	When a user passes a JSON object, it is cached. This object is then used to generate a JSON string, allowing for custom extensions.
stillFrameMotion	ARTCAICallAgentVcrFrameMotionConfig	The still frame detection configuration for VCR.
invalidFrameMotion	ARTCAICallAgentVcrFrameMotionConfig	The invalid frame detection configuration for VCR.
peopleCount	ARTCAICallAgentVcrBaseConfig	The real-time people count detection configuration for VCR.
equipment	ARTCAICallAgentVcrBaseConfig	The electronic device detection configuration for VCR.
headMotion	ARTCAICallAgentVcrBaseConfig	The head motion detection configuration for VCR.

ARTCAICallAgentVcrBaseConfig

Basic VCR detection configuration.

Parameter	Type	Description
enable	boolean	Specifies whether to enable the feature.

ARTCAICallAgentVcrFrameMotionConfig

VCR video frame detection configuration.

Parameter	Type	Description
callbackDelay	int	The delay after which the callback is triggered. Unit: milliseconds.

ARTCAICallExperimentalConfig

Experimental parameters that control specific logic.

Parameter	Type	Description
rtcSdkParams	JSONObject	RTC SDK parameters
commonParams	JSONObject	Common parameters

IARTCAICallService details

generateAIAgentShareCall

Starts a shared agent call.

/**
 * Starts a shared agent call.
 * @param userId The ID of the currently logged-on user.
 * @param aiAgentId The agent ID.
 * @param aiAgentType The agent type.
 * @param artcaiCallConfig The agent configuration.
 * @param callback The request callback.
 */
void generateAIAgentShareCall(String userId, String aiAgentId, ARTCAICallEngine.ARTCAICallAgentType aiAgentType, ARTCAICallEngine.ARTCAICallConfig artcaiCallConfig, IARTCAICallServiceCallback callback);

ARTCAIAgentUtil details

parseAiAgentShareInfo

Parses the information of a shared agent.

/**
 * Parses the information of a shared agent.
 * @param shareInfoText
 * @return The structured configuration of the shared agent.
 */
public static ARTCAIAgentShareInfo parseAiAgentShareInfo(String shareInfoText);

parseAiAgentInfo

Parses the response information for starting an agent.

/**
 * Parses the response information for starting an agent.
 * @param jsonObject The response information for starting the agent.
 * @return The structured information in the response for starting the agent.
 */
public static ARTCAIAgentInfo parseAiAgentInfo(JSONObject jsonObject);