Dispatch
Console →
Dispatch
Console →
Dispatch is transmitted, heard, and gone. Everything else in emergency care leaves a record that someone can go back to. We turn the radio into one, with the original audio sitting behind every line of it.
No recorder replacement, no API dependency. We watch the folder your recorder already writes to.
Trunk-recorder, rtl_airband and SDRTrunk do not expose an API. They write one file per transmission to a directory. We read that directory. It is the most durable integration available, because it does not break when your recorder updates.
Speech to text runs on dedicated GPU hardware, not a public API. Operational radio is sensitive material and it should not leave the building to be understood.
A poorly captured transmission cannot produce a confidently asserted finding. Confidence is capped by the quality of the audio it came from, so a bad capture never masquerades as a clean one.
Recordings are served only through an authenticated endpoint that writes an audit record. Every listen leaves a trace, because in review the question is always who heard what, and when.
Accredited emergency medical dispatch programmes must pull recorded calls at random and score them for protocol compliance. Today that work is manual, slow, and the first thing to slip when a centre is short staffed.
One answering point cannot see how it compares to the others, and a state programme cannot correct variation it never measures. Quality assurance done centre by centre, by hand, on a random sample, produces exactly that blind spot.
The same observable measures applied identically across every participating answering point: determinant assigned, pre-arrival instruction given, address and callback confirmed, time to dispatch. Comparable because they are computed the same way, not because someone agreed to a form.
A state average hides the centre that is struggling. We report the spread between centres and the count of calls falling below threshold, because that is where a programme actually intervenes.
Deployment per answering point is a recorder output directory and a channel definition. There is no per-seat client to install and no change to how call-takers work, which is what makes a small rural centre as easy to onboard as a large one.
Centre-level access to its own calls and scores, with the statewide comparison available to the programme. Audio access is authenticated and logged at every level.
The engine is running today in a security and incident-monitoring deployment, transcribing operational radio and turning it into structured incidents with the audio retained behind each one. What is described above is that engine, aimed at emergency medical dispatch quality assurance.
We have no deployed United States public-safety customer today. We are not an emergency medical dispatch protocol vendor and do not sell call-taking software.
Recording and review of voice traffic is governed by state law, and consent rules differ across states. Any deployment is designed around the rules of the state it runs in, decided before the first recording is processed rather than after.
If you are procuring an EMD system and want a quality assurance layer behind it, or you are a prime looking for that component, that is the conversation we are useful in.