AI article
Five hundred milliseconds of silence: how a voice agent decides you have finished
Community description: Voice agents end your turn on a timer. Here are the actual defaults across OpenAI, Pipecat, LiveKit and Silero, what human turn-taking research says about the time they have, and why the new turn-detection models have a hole in them where children should be.
Dev.to | Sep 16, 2026 | Max
Automated excerpt
Between those two failures lies a gap of a few hundred milliseconds, and almost the whole industry closes it the same way, with a timer. The cross-linguistic median is plus one hundred milliseconds and the mean across the whole set is plus two hundred and eight; Japanese is fastest with a mean of seven milliseconds, Danish slowest at four hundred and sixty-nine. The trouble is that silence inside a turn and silence after a turn are physically identical.
Selected automatically from source text; not independently written or fact-checked. Read the original for full context.