Agora Expands Integration with OpenAI Realtime API to Advance Multimodal AI Agent Interactions

Agora, a global leader in real-time engagement and conversational AI, announced expanded support for OpenAI’s Realtime API, which is now generally available. The integration brings advanced capabilities-such as automated greetings, mixed-modality interactions, and selective attention locking-designed to make communication with AI agents more seamless and human-like.

This milestone strengthens Agora’s collaboration with OpenAI, marking the first multimodal large language model (MLLM) built into the Agora platform. By combining OpenAI’s Realtime API with Agora’s Conversational AI Engine, developers can more easily create intelligent, responsive, and natural AI agents, while reducing development complexity and accelerating time to market.

“Real-time multimodal interaction is the missing piece for AI agents to feel truly human,” said Tony Zhao, CEO of Agora. “By integrating OpenAI’s Realtime API into our Conversational AI Engine, we’re giving developers the tools to build experiences that are faster, smarter, and more natural than ever before.”

Also Read: Accenture Acquires MomentumABM to Strengthen B2B Marketing and Account-Based Growth Strategies

Key features now available through Agora’s Conversational AI Engine include:

• Automated Greetings: Delivers instant session awareness and smooth onboarding.
• Mixed-Modality Interaction: Supports seamless switching between voice and text in a single session.
• Flexible Turn-Detection: Provides developers with precise control over conversational flow.
• Selective Attention Locking: Filters out background noise and distractions to ensure uninterrupted engagement.

By pairing Agora’s global real-time network infrastructure (SDRTN®) with OpenAI’s real-time language models, developers gain access to a scalable, purpose-built toolkit for deploying multimodal AI agents. This enables use cases ranging from customer service and virtual assistants to robotics and field operations.

One early adopter, Carbon Origins, is already utilizing the integrated technology to drive efficiency in robotics.

“The combination of OpenAI’s Realtime API and Agora’s conversational AI technology enable hands-free control of our autonomous robot fleet,” said Amogha Krishna Srirangarajan, CEO and Founder of Carbon Origins. “The technology powers the automation of complex checklists and system operations in our Constellation AI solution, allowing operators to focus on strategic tasks and orchestration instead of manual execution.”

With this integration, Agora continues to position itself as a leading enabler of real-time conversational AI, equipping developers and enterprises with the tools needed to transform user engagement and unlock new opportunities in multimodal interaction.