This topic introduces integration solutions for Real-time Conversational AI, describing the benefits and scenarios of each solution.
Integration solutions
Real-time Conversational AI provides two integration solutions based on the AICallKit SDK for audio and video call and messaging scenarios.
Integration solution with UI: This low-code solution includes UI components for audio and video applications. You can run a demo with simple configurations and integrate the UI components into your project.
Integration solution without UI: With this solution, you can customize the user interfaces and do not need to manage the underlying implementation of Real-time Conversational AI.
When Real-time Conversational AI is integrated based on AICallKit SDK, you can still access APIs provided by ARTC SDK. AICallKit SDK is a reliable, specialized interface that encapsulates certain functionalities of ARTC SDK for specific scenarios. This solution simplifies the integration process and provides flexibility.
Server-side features
Agent configurations: Customize the welcome message and voice, and enable intelligent interruption.
Call records: The built-in speech recognition technology automatically transcribes call content. You can review the content and use records for model training.
Intelligent agent callbacks: Configure callbacks for an AI agent to trigger automated actions or responses when specific events occur.
Hotword recognition: Upload hotwords to ensure accurate recognition of specific terms or phrases.
Avatar integration: After an avatar is integrated, audio responses in the workflow can be represented through the avatar, offering a richer and more intuitive interactive experience.