Attributed viewpoint

P95 under 1,000 ms target

A realistic production per-turn latency target is P95 under approximately 1,000 ms; beyond a couple of seconds, callers begin to disengage, and percentile-based SLOs—not averages—should be used and calibrated against user studies and real caller feedback.

Jose Nicholas Francisco·Published Aug 25, 2026

Behind the viewpoint

Translations are for reading; original excerpts remain the evidence.

Real-Time Voice AI Stack for Agents: Architecture Guide

Original excerpt

Target a P95 turn latency under about 1,000 ms, and treat anything beyond a couple of seconds as the point where callers start to disengage. Set percentile SLOs, not averages, and calibrate against user-study research like this IEEE study on perceived response delay in voice interfaces, then confirm the specific thresholds against your own caller feedback.

Open original · Paragraph 97 View source page