What makes spoken turns feel fast enough to keep using?
Voice
Latency budgets, barge-in, turn-taking and the parts of a voice pipeline that are somebody else's server rather than your code.
6 posts
Start here
Designing an agent conversation people can actually use
The seven decisions that make or break a conversational feature: discoverability, endpointing, barge-in, errors, confirmation, latency and the visual answer.
- Conversational interfaces and older users: the real tensionWhy asking for a task costs older users less than navigating to it, and why the same people are least likely to have tried an AI product.Voice8 min
- Voice is an alternative input path, not a speed featureThe case for a spoken path into your app, argued from the curb-cut effect, WCAG 2.2 and what screen reader users actually report.Voice7 min
- How fast does a voice agent have to be? A latency playbookWhere a spoken turn's milliseconds go, what the turn-taking research actually measured, and which tactics shorten which segment of the budget.Voice9 min
- What barge-in really costs, and how we pay for itServer-side turn detection decides when an agent should stop talking. The client decides whether it actually does, and that is where it breaks.Voice11 min
- An in-app agent is an accessibility feature, narrowlyAn agent that completes a task is an alternative input path, and one WCAG 2.2 criterion turns the biometric confirm into an accessibility win rather than a tax.Voice10 min