glossary
verified July 2026
Barge-in
Barge-in is the caller talking over the agent — and expecting it to stop, listen, and answer, the way a person would. Callers do it constantly, and an agent that keeps talking through it reads as a machine immediately.
01
What barge-in demands of TTS
- Instant stop: kill the audio stream mid-word the moment the caller speaks. A persistent socket per call makes this one message.
- Fast restart: the answer to the interruption is a fresh synthesis inside the same turn budget — first audio latency is paid again, which is why 107 ms and not 500 matters twice.
- No billing penalty: on a character meter, every barge-in bills characters nobody heard. Unmetered synthesis makes the interrupted sentence free.
02
The interrupted turn, to scale
Fig. — A normal turn vs an interrupted turn — same one-second budget
Normal turn — STT → LLM → TTS
550 ms and up
Interrupted turn — detect, stop, redo all three
the same stages, twice
▲ the restart begins here
the caller’s patience
Every fixed cost in the pipeline is paid twice per interruption — the stages you can buy down, synthesis first among them, decide whether interruptions feel handled or fumbled.
See also
Related sheets.
use case
20 ports
Replacing IVR menus with voice agents
Tearing out press-1 menus for a conversational agent changes the latency and concurrency math. What the synthesis layer must do, with measured figures.
glossary
107 / 108
Time to first audio (TTFA)
TTFA is the delay from sending text to the first playable audio byte. How it differs from model latency and TTFB, and how to measure it honestly.
capability
1 socket
The synthesis layer for voice agents
The TTS layer of a voice-agent stack: one socket per call, barge-in as one message, 107 ms measured first audio, and lines that price concurrency, not talk.
Every term on this page is measurable on a live call — watch the readout while your own script synthesizes.
See the measured figures live