Turn latency: 3362ms (transcriber: 642ms, endpointing: 2231ms, kb: N/A, model: 227ms, voice: 262ms)
Endpointing is insane! any idea how to fix this.
AWhat is your smart endpointing set to?
VTo fix the high endpointing latency, try adjusting your
This configuration helps reduce perceived latency by optimizing how Vapi determines when a user has completed their turn.
Source:
startSpeakingPlan configuration:This configuration helps reduce perceived latency by optimizing how Vapi determines when a user has completed their turn.
Source:
⤵️ Mention @Vapi Support Bot for follow-ups 🐥
EHigh endpointing latency like 2231ms is usually caused by default silence timeouts (up to 1.5s) and added wait buffers, you can reduce it by lowering waitSeconds, enabling smart endpointing, and tweaking silence thresholds for faster turn-taking.
