Skip to content

use case

verified July 2026

TTS for appointment reminders and notifications.

Reminders are the honest edge case: short calls, bursty schedule, modest minutes. Run the numbers before you buy anything — including ours.

01

The cost shape, honestly

A clinic sending 2,000 reminder-minutes a month pays $60 to $200 on published meters — below the $150 line, the cheap end of the meter wins and you should take it. The line starts winning when reminder traffic shares infrastructure with anything else: the same line that speaks reminders at 9 AM can answer the desk at 2 PM, and the marginal cost of adding the reminder workload to an existing line is zero.

Table 1 — Reminder-only volume, one month

Minutes / moOn a meterGandr flat
1,000$30 – $100$150
2,000$60 – $200$150
5,000$150 – $500$150
10,000$300 – $1,000$150

02

What a reminder sounds like

Both clips below are dated production output of this API — the same one-shot surface (POST /v1/tts/bytes) a reminder job would call, no socket, fire and forget.

Audio — Reminder-shaped output, rendered on the production API

generated 2026-07-16

English

“You're all set for Thursday at ten with Doctor Okafor. I've texted the address and the two intake forms — reply here anytime and I'll move the appointment if something comes up.”

Jenny · 10.3 s · healthcare · appointment line

English

“Your technician is booked for Tuesday between nine and eleven. I'll send a text when they're about thirty minutes out, so you're not stuck waiting around all morning.”

Leo · 7.7 s · field service · scheduling

03

The burst problem

Reminder jobs fire in windows — 9 AM, lunchtime, end of day — so the real constraint is concurrency at the top of the hour, not minutes across the month. Burst lines price exactly that: traffic past your committed lines spills over at $10 a line-day, only on the days the window actually spikes, with a cap you set in the dashboard. A consistent cloned voice and per-key accounting (one key for the reminder job, readable at GET /v1/usage) keep the job auditable on its own.

See also

Related sheets.

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

Bring this use case to the call