Voice and Vision

The field is contested because the two halves are moving at different speeds. Vision on structured imagery — meter photos, shelf gaps, claim forms — is at production accuracy on frontier models and on a distilled small model, and the retail sector owner is already using it. Voice is not. Our latency run for an AU telco measured a p95 turn latency of 2.6 seconds via US-hosted realtime endpoints, well past the point at which callers talk over the agent; a Sydney-region endpoint launched in July halves that but does not fix barge-in, which failed on 18% of interruptions, or hallucinated confirmations, which occurred in 4 of 50 test calls. Vendors claim 70% containment; the analyst line says 40% of AU volume by 2027. Both may be true for tier-1 queues and neither is true for anything transactional. The recommendation is 'not yet' above triage, and the graveyard holds the IVR-replacement thesis.

Telco and insurance clients are being pitched voice agents by every contact-centre vendor, and the pitch numbers are containment rates measured on US English in US data centres. Quantium's edge is a measured AU floor: the latency, the accent error rate and the confirmation-hallucination rate on real queues. That number is the difference between a triage deployment that works and a payments deployment that generates complaints to the TIO. Vision is the opposite story — a quiet production capability in field ops and retail that nobody is asking the lab about because it already works.

Realtime voice agents in Australian contact centres are gated by reliability, not capability: a round-trip floor from Sydney to US-hosted realtime models, accent-driven recognition errors, barge-in failures and hallucinated confirmations mean they hold for tier-1 triage and fail above it; vision in field operations and retail is further along because latency is not the product. That is the lab's one-line position on it, which is not the same as an explanation.

The shape the field is converging on, from the most authoritative source in it: Recognition error on Australian-accented English is roughly twice the US baseline on current realtime stacks.signal

This is the section a page most needs a person for, and the one composition is worst at. Nobody has written the plain-language version — what the idea is, in words that assume nothing — and it is the first thing a reader who has never met the term needs.

The lab opened this field on 2026-03-12 and it reached mainstream awareness on 2025-11-01. The gap between those two dates is the lead time the lab is measured on.

What shipped: Frontier lab launches Sydney-region realtime voice endpoint (OpenAI, 2026-07-15) and Contact-centre platform vendor claims 70% containment with voice agents (Vendor press release, 2026-05-06). Tooling arriving is what moves a field from argument to something a team could try.signalsignal

What changes, concretely: AU voice latency floor: p50 1.4 s and p95 2.6 s turn latency via US-hosted realtime endpoints; 0.78 s p50 via the Sydney-region endpoint launched in July (x-voice-latency).signalsignal

There is already a shipped default — voice.scope = tier1-triage · voice.endpoint = au-region · voice.readback = grounded-to-tool-output · handoff.on = transactional-intent · skill: cavendish/voice-guardrails — so a team adopting this is changing a setting rather than starting a project.

The binding constraint is reliability: it works and is not yet dependable enough to put near a customer. Everything upstream of that is solved and everything downstream of it is waiting.

Workforce readiness is low: Nobody in delivery has built a barge-in-safe voice loop; the vendor stacks hide it until it fails. Agent-estimated. A recommendation needing skills the firm does not hold is an aspiration rather than an action, and it routes to the enablement agenda instead of the delivery one.

Something here has already been killed: Realtime voice agents replace tier-1 IVR, on the telco partner withdrew the test trunk on day 24 of a planned 40-call measurement and the pair was reassigned; 11 calls were measured, which is not enough to answer the hypothesis either way. It is marked resurrectable on: A telco or contact-centre partner lending a SIP trunk for three uninterrupted weeks, or an AU-region realtime endpoint from a second vendor so the comparison can run without one..graveyard

The argued case against it is the red team's, further down this page, and it is deliberately one-sided — this section is what stands in the way mechanically, not what somebody thinks of it.