glossary
verified July 2026
Concurrent lines
A line is the capacity to hold one conversation right now. Minutes measure how much your agents talked last month; lines measure how many callers can be talking this second — and the second number is the one that pages you.
01
The quiet cap in metered plans
Most per-character plans also carry a concurrency ceiling — pay for characters, and separately be capped on simultaneous requests by plan tier. The meter is the visible price; the cap is the one you discover at your busiest hour. Here the relationship is inverted: concurrency is the only thing you buy, and usage on each line is unmetered.
02
The three mechanics
Fig. — Capacity, priced three ways
1 line
one concurrent conversation — $150 a month annual, unmetered
$10
a burst line-day, when traffic spills past your committed lines
$20 / mo
a standby line idling beside another vendor, for failover
Past absolute capacity the API refuses fast with a retryable busy signal — a full lane never quietly slows the others.
03
Sizing a fleet
- Count busy-hour simultaneous conversations, not monthly minutes — that peak is your line count.
- Let bursts spill instead of sizing for them: the spike days cost $10 a line-day, capped in the dashboard, and the quiet days cost nothing extra.
- The pilot exists to find the real number: 20 lines against 30 days of actual traffic.
See also
Related sheets.
glossary
$30–$100
TTS pricing: per character vs flat rate
The two ways speech synthesis is priced, what each one does to a voice product, and which side of the break-even your workload sits on.
capability
$10
Burst lines: capacity priced by the day
Traffic past your committed lines spills to burst lines at $10 a line-day, capped in your dashboard — capacity for spike days without paying for them all year.
use case
43,200 min
TTS for AI receptionists
A 24/7 receptionist line speaks up to 43,200 minutes a month: $1,296 to $4,320 on a character meter, $150 flat. The arithmetic for always-on voice.
Every term on this page is measurable on a live call — watch the readout while your own script synthesizes.
See the measured figures live