TTS for travel booking and disruption lines.

Travel support has two modes: the steady trickle of bookings, and the hour after a cancelled flight when four hundred people call at once, in eleven languages, already upset. The agent that answers has to be instant, calm, and multilingual — and the month that contains that hour should not cost extra.

1 hr

a cancelled flight’s call volume — compressed into the hour after the gate closes

The disruption hour

Standing lines carry bookings; burst lines absorb the cancellation spike at $10 a line-day.
The caller’s language is the first thing detected — one voice answers in all 23.
Itineraries, airport codes, and times read precisely via transcript controls; the tone stays level via expression controls.

The month, priced

The meter bills the storm; the line prices it as burst days. Either way the traveler on the phone hears the same 107 ms first audio.

Table 1 — An online agency’s support month

Operation	Minutes / mo	On a $30–$100 meter	On Gandr lines
Steady bookings, 2 lines	8,000	$240 – $800	$300
Disruption week included	20,000	$600 – $2,000	$300 + burst days

Why the calm voice matters

A stressed traveler talked back from the edge is the difference between a rebooking and a refund. The expression controls are documented per request — the same script can be read urgent for the gate change and warm for the apology.

Related sheets.

use case

TTS for live voice translation

Spex-TTS grew out of a production live-translation product. One cloned identity across 23 languages, 107 ms first audio, measured on the production API.

use case

8,000 min

TTS for AI customer-support agents

The latency budget and cost arithmetic for a voice support desk: why first audio decides whether callers interrupt, and what 8,000 minutes a month costs.

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.

Thirty minutes, your production script, the live latency readout — measured in front of you.

Bring this use case to the call