This topic describes the details of the Android software development kit (SDK) API operations.
API overview
Older SDK versions contain deprecated parameters and methods. Upgrade the SDK to the latest version. For more information, see Android usage guide.
Class/Protocol | API | Description |
ARTCAICallEngine Defines the audio and video call engine API. | Initialization | |
Sets the agent type. | ||
Creates and starts a call. | ||
Initiates an agent call through the client-side call API. | ||
Hangs up the call. | ||
Switches the microphone status. | ||
Interrupt the robot. | ||
Enables or disables smart interruption. | ||
Switches between the speaker and earpiece. | ||
Stops or resumes the playback of the agent's audio stream. | ||
Enables or disables the push-to-talk mode. | ||
Checks whether the push-to-talk mode is enabled. | ||
Push-to-talk mode: Starts speaking. | ||
Push-to-talk mode: Finishes speaking. | ||
Push-to-talk mode: Cancels the current speech. | ||
Switches the voice. | ||
Gets the current voice. | ||
Registers a callback. | ||
Checks whether the microphone is muted. | ||
Checks whether the speaker is used for playback. | ||
Checks whether smart interruption is enabled. | ||
Sets the view container for the digital human and specifies the rendering mode. | ||
Sets the local view container for visual understanding and specifies the rendering mode. | ||
Enable or disable the camera | ||
Is the camera turned off? | ||
Switches between the front and rear cameras. | ||
You can obtain the RTC engine instance. | ||
Gets the official protocol implementation. | ||
Sends a custom message to the large language model (LLM). | ||
Sends a custom message to the business server. This operation must be called after the call is connected. | ||
Updates the system prompt for the LLM. This operation must be called after the call is connected. | ||
Updates the parameters for the Alibaba Cloud Model Studio application center. | ||
Updates the VCR configuration. | ||
For a visual understanding agent, starts custom frame capture. After this is started, you cannot talk to the agent through voice. This operation must be called after the call is connected. | ||
For a visual understanding agent, stops custom frame capture. This operation must be called after the call is connected. | ||
Sets the video view container for the agent. | ||
Sets the video view container for the agent and specifies the rendering mode. | ||
Sets the local preview view control. | ||
Sets the local preview view control and specifies the rendering mode. | ||
Gets the runtime information of the current agent. | ||
IARTCAICallEngineCallback Engine callback events | An error occurred. | |
The agent started successfully. | ||
The call started. | ||
The call ended. | ||
The underlying AliRtcEngine engine is created. | ||
Robot state sync | ||
Callback for when the user is speaking. | ||
Synchronizes the text recognized by Automatic Speech Recognition (ASR) from the user's speech. | ||
Synchronous agent responses | ||
The LLM has finished answering in the current call. | ||
Callback for network status changes. | ||
The volume changed. | ||
The voice for the current call changed. | ||
The voice interruption setting for the current call changed. | ||
Is the agent video active (stream ingest)? | ||
The agent's audio stream is available. | ||
Audio loopback latency. | ||
The first video frame of the digital human is rendered. | ||
Callback for when a user comes online. | ||
The agent's current speech is interrupted. | ||
Custom frame capture mode is enabled for the current visual understanding call. | ||
The current agent is about to leave the call. | ||
A human agent is about to take over from the current agent. | ||
The human agent takeover is connected. | ||
A custom message from the agent is received. | ||
Notification of the agent's emotion analysis result. | ||
Callback for the availability of the agent's message channel. | ||
A VCR result is received from the current agent. |