use case
verified July 2026
TTS for pharmacy refill and adherence calls.
A refill reminder is a thirty-second call that moves a health outcome. It has to say the drug name right, land in the patient’s language, and go out every day without the program’s budget depending on how many patients picked up.
01
What the call must get right
- Drug names pronounced correctly — transcript controls pin the hard ones once, for every call after.
- The patient’s language, from one cloned pharmacy voice across all 23.
- Callbacks answered: the same line that reminds also takes the "refill it" reply.
02
The program, priced
Small programs may sit below the meter crossover — the pricing page holds that arithmetic in the open. Chain-scale adherence programs are the line’s natural shape: high volume, identical calls, fixed budget.
Table 1 — A reminder program’s month, both models
| Program | Minutes / mo | On a $30–$100 meter | On Gandr lines |
|---|---|---|---|
| Single pharmacy, 1 line | 2,000 | $60 – $200 | $150 |
| Chain program, 5 lines | 25,000 | $750 – $2,500 | $750 |
03
The trust posture
Health calls carry the strictest identity bar: every sample is watermarked at generation, reference audio never enters a training set, and the provenance sheet publishes both claims with the mechanism stated.
See also
Related sheets.
use case
zero
TTS for healthcare scheduling calls
One line answers the front desk and speaks the recall list. TTS for clinic scheduling: a consistent cloned voice, 23 languages, and traffic accounted per key.
use case
2,000 min
TTS for appointment reminders and notifications
Reminder traffic is bursty and short-form. Where a meter genuinely wins, this page says so — and where burst lines beat both, it shows the arithmetic.
capability
never
Provenance and privacy, applied at generation
The policy surface of the engine: an inaudible watermark on every sample, reference audio that never trains, and per-key audit trails at GET /v1/usage.
Thirty minutes, your production script, the live latency readout — measured in front of you.
Bring this use case to the call