blog

notes from the router.

Field notes on the parts of voice AI that usually fail in production: latency budgets, endpointing, provider selection, benchmark methodology, and the engineering decisions behind reliable spoken agents.

engineering methodology 6 notes

latest note

engineering · 2026-04-23 · 6 min

Cutting voice agent latency to sub-500ms — a practical playbook

A latency budget for cascaded voice pipelines, why endpointing is the silent killer, and where the architecture itself has to change when you cannot push lower.

read dispatch