A Recipe for Real Time Voice AI: WebRTC, SLMs and Open Source Software

AI-powered voice agents are transforming enterprise communications, telecom, healthcare, and more, but achieving low-latency realistic real-time AI responses remains a challenge.

This talk explores how Small Language Models (SLMs) and open-source tools enable affordable, fast AI-driven WebRTC interactions. Based on real-world experience building AI analytics and real-time voice agents, we’ll cover:

- How SLMs reduce cost and improve response times for voice AI.

- Some standard AI architectures that connect models to external data and tools.

- Benchmarking some voice AI pipelines to compare real-time performance.

- Live demo of an AI-powered WebRTC assistant.

‍