Agora announced the launch of its Conversational AI Engine, an advanced solution enabling developers to create interactive voice experiences with any AI model. Built for seamless real-time engagement, the engine ensures ultra-low latency responses and superior voice processing, allowing for the effortless creation of immersive voice AI experiences.
Agora’s Conversational AI Engine provides developers with the flexibility to use any AI model, whether custom-built or from leading LLM providers, and any text-to-speech (TTS) voice solution for their AI agent. The Engine is designed to optimise real-time conversation flow. It enables faster, low-latency responses and intelligently pauses for interruptions in real time, enabling more natural dialogue with users.
“Most AI models don’t yet offer the ability to interact via voice, and those that do haven’t optimized the experience,” said Tony Zhao, CEO of Agora. “Agora’s solution will help drive the adoption of conversational AI by enabling seamless, natural voice interactions. With effortless integration and real-time, voice-driven experiences that have near-zero lag, we are removing barriers and unlocking new possibilities for businesses and end users alike.”
With built-in background noise suppression, AI-driven acoustic algorithms, and real-time speech-to-text (STT), Agora’s Conversational AI Engine ensures clear and accurate voice interactions in any environment. Powered by Agora’s global Software-Defined Real-Time Network™, the Engine dynamically handles packet loss and minimizes latency, delivering exceptional performance across devices and networks. The solution is built on top of the TEN frameworks, an Agora-supported community project for building conversational AI. The Engine allows businesses to deploy natural and engaging real-time voice agents with maximum scalability and minimal effort.
Agora also plans to extend the capabilities of the Conversational AI Engine to its App Builder product, enabling a no-code approach to creating conversational AI experiences. App Builder allows users to create a simple UI and seamlessly integrate Agora’s Conversational AI Engine without extensive coding, making it possible to deploy voice-driven AI experiences even more quickly.
Zhao continued, “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.”
To further enhance its Conversational AI Engine, Agora is partnering with Oracle as a key AI infrastructure provider, leveraging the scalable Oracle Cloud Infrastructure (OCI) solution to optimise performance, security, and efficiency.
“Agora’s Conversational AI Engine solves two of the biggest hurdles in human-to-AI voice conversation—latency and wireless last mile challenges,” said Hua Jiang, Alliance & Channel Director, Oracle APAC. “We are proud to collaborate with Agora to provide the infrastructure that enables more natural, responsive, and reliable voice-powered conversational AI.”
Agora’s Conversational AI Engine is designed for a wide range of applications, including:
- 24/7 Customer Support: Create AI-powered voice agents that provide instant responses, troubleshoot issues, and guide customers through processes.
- IoT Integration: Enable seamless voice control for smart devices, wearables, robots, and connected applications.
- Virtual Shopping Assistants: Help customers find products, compare options, and make purchasing decisions in real time.
- Live AI Hosts: Leverage AI agents to host live events, equipped with automated content moderation and the ability to respond to viewers in real time.
- Mental Health Support: Offer mental health support agents that can listen, provide advice, and connect users with professional help if needed.
- Live Tutoring: Offer AI tutoring that can speak with students to offer real-time feedback and guidance when learning specific languages or subjects.
- AI-Powered NPCs in Gaming: Build more immersive virtual worlds with AI-controlled characters that can interact naturally with players via voice.
- Employee Onboarding: Guide new hires through training and provide instant access to a 24/7 resource to answer questions.
