Integration solution without UI

Overview

AICallKit SDK is a development kit for managing intelligent agents. The SDK provides a series of API operations that can be used by developers to implement conversations between intelligent agents and users in apps. After AICallKit SDK is integrated, developers can directly use most features related to intelligent agents, without the need to develop features on their own. This significantly shortens the development cycle, improves the quality of apps, and provides users with a richer and smoother speech interaction experience. For more information about integration on different devices, see the following topics:

• Integrate AUI Kits for AI real-time interaction into Android apps

• Integrate AUI Kits for AI real-time interaction into iOS apps

• Integrate AUI Kits for AI real-time interaction into web apps

For more information about server-side development, see Integrate AUI Kits AppServer for AI real-time interaction and API description.

Flowchart

After an intelligent agent is started in an app, the app can call the call() method to start a call. During the call, the app can call the API operations of AICallKit SDK to implement interactive features such as live subtitles and interruption. AICallKit SDK relies on the capabilities of ApsaraVideo Real-time Communication (ARTC), and thus provides the features of AliVCSDK_ARTC SDK. If you need to use the capabilities of ApsaraVideo Live and ApsaraVideo VOD in your business scenarios, you can use ApsaraVideo MediaBox SDK. For example, you can use AliVCSDK_Standard or AliVCSDK_InteractiveLive. For more information, see Select and download SDKs.

Benefits

• After AICallKit SDK is integrated, a series of operations can be performed on intelligent agents.

• Developers can develop their own AppServers based on business requirements.

• AICallKit SDK can be integrated into Android, iOS, and web apps.

Features

• Calls with intelligent agents: You can start and end calls with voice agents, digital human agents, or visual understanding agents.

• Intelligent agent status: You can obtain the real-time status of intelligent agents.

• Live subtitles: The conversations between intelligent agents and users are converted into text in real time and displayed on clients.

• Interruption: Intelligent agents can recognize the conversation interruption intention of users.

• Advanced configurations of intelligent agents: You can customize the voice of intelligent agents and enable intelligent interruption.

• Local device management: You can disable the speaker and mute the microphone during a call.