use case
verified July 2026
TTS for utility outage lines.
An outage line has the hardest traffic shape in telephony: near-zero for months, then the entire service area calling inside twenty minutes. Sizing that on a meter means paying for the storm every month; sizing it on lines means paying for the calm and bursting for the storm.
01
The storm, served
- Standing lines carry the daily trickle of billing and service calls.
- When the storm hits, burst lines absorb the surge at $10 a line-day — the spike is a line-item, not a negotiation.
- Estimated-restoration scripts update per neighborhood; unmetered characters mean re-recording the whole area costs nothing.
- The caller’s language is detected from the first turn — one voice, 23 languages, no menu tree.
02
Past absolute capacity
If a regional storm outruns even burst capacity, the API refuses fast with a retryable 503 — callers hear one more ring, not a stack of half-dead streams. Live calls already connected never degrade. That behavior is published on the load sheet, with the three-tier posture behind it.
03
The calm month, priced
The meter charges you most in the month your customers are angriest. Lines hold the budget flat and price the storm as burst days you can count.
Table 1 — A regional utility, ordinary month vs storm month
| Month | Minutes | On a $30–$100 meter | On Gandr lines |
|---|---|---|---|
| Ordinary, 2 lines | 6,000 | $180 – $600 | $300 |
| Storm, 2 lines + burst | 40,000 | $1,200 – $4,000 | $300 + burst days |
See also
Related sheets.
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.
capability
3 tiers
Serving that degrades before it fails
Three serving tiers behind one endpoint — primary GPU fleet, warm spill, independent fallback — and a fast retryable 503 past absolute capacity.
use case
12,000 min
TTS for order-status calls
An order-status call is one fact delivered fast. The latency and seasonal cost shape of where-is-my-order traffic, with burst lines for the peak weeks.
Thirty minutes, your production script, the live latency readout — measured in front of you.
Bring this use case to the call