---
title: "Voice AI is governed by a sub-second human-conversational latency budget that multi-hop cloud architectures struggle to meet"
type: "claim"
status: "seedling"
audit_status: "flagged — every figure sourced to a Tier-3 vendor page, [unverified-quant]; the ~200ms turn-taking figure is well-established in conversation-analysis literature but is NOT cited to a primary source here; promoted at seedling pending primary sourcing (see [[question-verify-conversational-turn-taking-latency-thresholds]])"
flags: ["[unverified-quant — needs primary] All latency figures (200ms human response, 1200ms abandonment threshold, 250ms multi-vendor hop cost, 800ms-1.5s total, <1s Telnyx) come from a single Tier-3 vendor page; sources.md requires Tier 1-2 for quantitative claims. The vendor's own <1s figure is a self-report."]
source_url: "https://telnyx.com/resources/how-telnyx-fixed-voice-ai-latency-with-co-located-infrastructure"
source_title: "Voice AI Latency: Why colocation is mission critical"
source_author: "Telnyx editorial"
source_date: "2026 (exact date not available)"
source_quote: "Humans respond within 200 milliseconds in conversation"
source_tier: 3
provenance: "Promotion from 10-inbox/raw/2026-07-09-hop-telnyx-gpu-colocation-voice-latency.md, 2026-07-09"
origin: "batch"
derived_from: "10-inbox/raw/2026-07-09-hop-telnyx-gpu-colocation-voice-latency.md"
date_created: "2026-07-09T00:00:00.000Z"
tags: ["AI","voice-AI","latency","human-factors","conversation","inference","Telnyx"]
related_notes: ["claim-telnyx-colocates-gpus-at-telephony-pops-for-voice-latency","claim-llm-inference-prefill-decode"]
audits: ["2026-07-09 claude-opus-4-8"]
drafted_in: ["from-a-standing-start"]
---


A recurring argument in voice-AI engineering is that the design target is set not by the technology but by human perception of conversational timing. As framed by Telnyx (2026): "Humans respond within 200 milliseconds in conversation," and responses "above 1200ms" cause users to "hang up." Between those bounds lies the entire budget a spoken-dialogue system has to receive audio, transcribe it, run [[large language model|LLM]] [[inference]], synthesize speech, and return audio.

The claim's force is that this budget is *hard* — a perceptual floor, not a preference — and that conventional architectures spend too much of it on network overhead. A typical multi-vendor stack, chaining separately-hosted speech-to-text, LLM, and text-to-speech services, is said to add "250ms minimum in network hops alone," landing at "800ms - 1.5 seconds total." Against this, Telnyx claims a "response time of less than one second" from running the pipeline on colocated hardware — see [[claim-telnyx-colocates-gpus-at-telephony-pops-for-voice-latency]].

This connects to the internal latency structure of LLM inference itself: the perceived delay before a spoken system responds is dominated by Time to First Token, the prefill-phase metric described in [[claim-llm-inference-prefill-decode]]. Where a text chat can stream tokens into a visibly-typing UI, a voice turn must clear enough of the pipeline to begin *speaking* within the conversational window, making the latency budget less forgiving than in text interfaces.

Every number above is sourced to a single vendor page (Tier 3), and the specific figures are `[unverified-quant]`. The ~200ms turn-taking threshold does have a genuine primary home in conversation-analysis research (e.g. work on the timing of turn-taking), and the abandonment and hop-cost figures should be checkable against independent measurement — verification is routed to [[question-verify-conversational-turn-taking-latency-thresholds]].

## Update 2026-07-30 — the ~200ms figure now has a Tier-1 primary source

A dedicated verification capture (10-inbox/raw/2026-07-29-what-are-the-primary-sourced-thresholds-for-human.md) resolved part of this note's `[unverified-quant]` flag. The ~200ms turn-taking figure is now sourced to [[claim-stivers-2009-cross-linguistic-turn-taking-gap-208ms-mean]] (Stivers et al. 2009, *PNAS*, Tier 1: modal peak 0-200ms, cross-linguistic mean +208ms), and the related network-delay ceiling is sourced to [[claim-itu-t-g114-150ms-transparent-400ms-outer-limit-thresholds]] (ITU-T G.114, Tier 1: 150ms transparent / 400ms outer limit). This note's own text and `source_quote` are left as originally written — they still describe the Tier-3 Telnyx page this note was drafted from — but a future rewrite should re-point the turn-taking half of the argument at the new Tier-1 notes instead.

The other two figures are **not** resolved: no primary source was found confirming the vendor-specific claim that voice-AI response delays above ~1200ms cause abandonment (the closest primary, [[claim-brown-2005-call-center-abandonment-hazard-rate-two-peaks]], measures hold-queue abandonment — a caller waiting for a human agent — not AI-response abandonment, and the two mechanisms should not be assumed to transfer). The ~250ms multi-vendor hop-cost figure remains unaddressed. This note should stay `status: seedling` with its `[unverified-quant]` flag intact for those two figures; see the updated progress log at [[question-verify-conversational-turn-taking-latency-thresholds]].

> [!note] Seek's commentary:
> The underlying idea — that human turn-taking timing imposes a fixed budget voice AI must fit inside — is sound and predates any vendor. What is not established here is the vendor's specific numbers, especially the self-reported sub-second figure. The concept is worth keeping; the digits are not yet load-bearing. — Seek