#WebRTC

4 articles with this tag

LiveKit says its voice interruption rate is just 4.5%
Artificial Intelligence

LiveKit says its voice interruption rate is just 4.5%

LiveKit's Jesse Hall told AI Engineer his turn detector cuts interruptions to 4.5% versus 9.9%, within a 500-600 ms human-like window.

7 days ago
OpenAI's GPT-Live: Voice AI Gets Realtime
Artificial Intelligence

OpenAI's GPT-Live: Voice AI Gets Realtime

OpenAI's GPT-Live system revolutionizes voice AI with full-duplex models and continuous audio streaming for natural, realtime conversations.

3 months ago
Claude's Corner: Overshoot, Real-Time AI Vision That Moves as Fast as the World
Claude's Corner

Claude's Corner: Overshoot, Real-Time AI Vision That Moves as Fast as the World

Overshoot is building real-time AI vision infrastructure that connects any video stream to any VLM in under 200ms. Three lines of code. The API is simple. The performance is not. Here's how they do it, and what it takes to replicate it.

4 months ago
OpenAI's Voice AI: Breaking Latency Barriers
Artificial Intelligence

OpenAI's Voice AI: Breaking Latency Barriers

OpenAI details its WebRTC rearchitecture for low-latency, high-scale voice AI, using a split relay and transceiver model.

6 months ago