In text, a two-second wait is nothing. On a phone call, it’s an awkward silence — and awkward silences are when people say “hello? are you there?” and hang up.
Where the time goes
- Hearing the prospect finish speaking (and not cutting them off).
- Understanding what they said.
- Deciding what to say next.
- Turning that reply into natural-sounding speech.
Each step is fast on its own. Chained together over a phone line, they add up. The work is in overlapping them so the reply starts before the whole pipeline finishes.
“Nobody remembers a clever answer that arrived late.”
Interruptions are a feature
Real people talk over each other. A voice agent has to stop speaking the moment the prospect starts, and pick the thread back up without repeating itself.