The iOS SDK provides engine interfaces, delegate callbacks, and factory methods for AI call management.
API overview
Deprecated parameters and methods exist in earlier SDK versions. We recommend that you upgrade the SDK to the latest version. For more information, see iOS user guide.
|
Class/Protocol |
API |
Description |
|
ARTCAICallEngineInterface Engine interface definition |
The user ID of the current call. |
|
|
Indicates whether a call is in progress. |
||
|
Information about the current agent. |
||
|
The state of the current agent. |
||
|
Sets and gets callback events. |
||
|
Starts a call. |
||
|
Starts a call using the call configuration. |
||
|
Hangs up a call. |
||
|
Hangs up the call and destroys the current call engine. |
||
|
Audio configuration, including encoding settings such as sample rate, the number of sound channels, and bitrate, and scenario settings such as default and music scenarios. |
||
|
Video configuration. |
||
|
Sets the rendering view and configuration for the local camera. |
||
|
Sets the rendering view configuration for the agent. This is required when the agent has image rendering. This is valid only for AvatarAgent and VideoAgent. |
||
|
Interrupts the agent's speech. |
||
|
Enables or disables smart interruption. |
||
|
Switches the voice. |
||
|
Enables or disables the speaker. |
||
|
Enables or disables the push-to-talk mode. |
||
|
Starts speaking in push-to-talk mode. |
||
|
Stops speaking in push-to-talk mode. |
||
|
Cancels the current speech in push-to-talk mode. |
||
|
Mutes or unmutes the microphone. |
||
|
Stops or resumes the playback of the agent's audio stream. |
||
|
Parameter settings for visual understanding calls. |
||
|
Disables or enables the camera. |
||
|
Switches between the front and rear cameras. |
||
|
Parses the information of a shared agent. |
||
|
Starts a shared agent call. |
||
|
Obtain the RTC engine. |
||
|
Sends a text message to the agent. |
||
|
Sends a custom message to the server. Must be called after the call is connected. |
||
|
Updates the system prompt for the large language model (LLM). This operation must be called after the call is connected. |
||
|
Updates the parameters for Alibaba Cloud Model Studio. |
||
|
Updates the VCR configuration. |
||
|
For a visual understanding agent, starts custom frame capture. After this is started, you cannot talk to the agent by 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. |
||
|
Updates the threshold for voice activity detection. |
||
|
Updates the text-to-speech (TTS) playback speed. |
||
|
Creates an ARTC engine in advance. If not called, the engine is created when the call starts. |
||
|
Releases resources. |
||
|
ARTCAICallEngineDelegate Engine callback events |
An error occurred. |
|
|
The call agent has started. |
||
|
The call has started. |
||
|
The call has ended. |
||
|
Indicates whether the agent's video is available. |
||
|
Indicates whether the agent's audio is available. |
||
|
The RTC engine was created successfully. |
||
|
Indicates whether the push-to-talk mode is enabled for the current call. |
||
|
The current agent is about to leave (end the current call). |
||
|
A custom message is received from the current agent. |
||
|
The agent's state has changed. |
||
|
The network status has changed. |
||
|
The volume has changed. |
||
|
A notification that the user's question is recognized by the agent. |
||
|
A notification of the agent's response. |
||
|
The LLM has finished responding in the current call. |
||
|
The voice of the current call has changed. |
||
|
Indicates whether voice interruption is enabled for the current call. |
||
|
The agent's current speech is interrupted. Only callbacks for interruptions by specific words are supported. |
||
|
Indicates whether custom frame capture mode is enabled for the current visual understanding call. |
||
|
The first frame of the agent's digital human is rendered. |
||
|
A human is about to take over the current agent. |
||
|
The human takeover is connected. |
||
|
A notification of the agent's emotion. |
||
|
A callback for the availability of the agent's message channel. |
||
|
A VCR result is received from the current agent. |
||
|
The connection status changes during the call. |
||
|
Audio loopback latency. |
||
|
If you play background music through the ARTC instance during the current call, this playback callback is triggered. |
||
|
ARTCAICallEngineFactory Engine creation factory |
Creates a default engine instance. |