Agora launches conversational AI engine for real-time voice interactions

Agora, a real-time engagement platform, has launched its conversational Artificial Intelligence (AI) engine, a solution designed to enable developers to build interactive voice experiences using any AI model. The engine focuses on delivering low-latency responses and real-time voice processing. 

The conversational AI engine supports various AI models, including custom-built ones and those from leading large language model providers. It is compatible with multiple text-to-speech solutions, allowing businesses to create AI-powered voice interactions. The engine optimises conversation flow by enabling faster responses and handling interruptions in real time. 

It includes background noise suppression, AI-driven acoustic algorithms, and real-time speech-to-text conversion to ensure clear voice interactions. It operates on Agora’s Software-Defined Real-Time Network (SD-RTN), which manages packet loss and minimises latency across different devices and networks. The engine is built on the TEN framework, an Agora-supported community project for conversational AI development. 

The company plans to integrate the conversational AI engine with its app builder product, allowing users to create conversational AI experiences without extensive coding. The no-code approach simplifies the deployment of voice-driven AI applications. 

The company is also partnering with Oracle to enhance the engine’s performance, leveraging Oracle Cloud Infrastructure for improved scalability and security. The collaboration aims to address challenges in voice-based AI conversations, such as latency and network limitations. 

The Conversational AI Engine can be used in various applications, including customer support, Internet of Things (IoT) device control, virtual shopping assistants, live AI event hosting, mental health support, AI-powered gaming characters, employee onboarding, and live tutoring, the company said. 

Tony Zhao, CEO of Agora, said, “Our goal is to bridge the gap between AI and human interaction, making conversations more intuitive, expressive, and impactful. We are dedicated to democratising voice interactions between humans and AI models, making them a fundamental part of how people connect, communicate, and innovate."