Median human turn-taking pause is -120ms, so voice AI's 500ms brag still misses how people talk
alexisgallagher · x · 2026-11-04
Voice AI builders often brag about 500ms response latency after a human finishes speaking, but empirical studies show the median pause between people is around -120ms — a negative number, meaning humans start talking before the other person finishes.
The takeaway: voice AI is better than ever, but still far from natural conversation; handling overlapping talk matters as much as raw latency.
More from Models
- Overthinking Bench: Claude burns 1,069 thinking tokens on 'is the globe round?' — intellectronica · 2026-11-04
- Andrew Ng: asking if LLMs beat specialists at their own game is now meaningless — andrewgwils · 2026-11-04
- Model Vendors Post-Train for Tool Search, Squeezing Out MCP-Layer Workarounds — pvncher · 2026-11-04
- Claude Opus 5.5 blocks viewing Qwen's reasoning, safeguard error says sorry not allowed — andpoul · 2026-11-04
- Gemini API deprecations: 2.5 Pro auto-redirects to 3.8 Flash on Dec 1 — patloeber · 2026-11-04
- Tencent's Hy4 coming to LMArena after preview hit #2 among open models in Agent Arena — arena · 2026-11-04