POST and done
Send a file or a URL. JSON in, JSON out. No SDK to install, just HTTP.
POST an audio clip, get a citable probability with model attribution in under half a second. The same model that runs the public detector, behind one endpoint.
The detector, as an endpoint. Same model, same methodology, same verdict you can cite.
Send a file or a URL. JSON in, JSON out. No SDK to install, just HTTP.
The API runs the exact model behind the public detector. 99% on clean audio.
When we recognize ElevenLabs, Resemble, PlayHT, OpenAI and others, we name the source.
Roughly half a second of compute on a typical clip. Built for newsroom and call-center speed.
Queue large batches and we post the results back when each job finishes.
Every response includes a permanent, APA-style citation URL and a one-way audio fingerprint.
The API returns the same probability the public detector does. The number a developer gets back is the number a court can cite.
{
"verdict": "likely_synthetic",
"probability": 0.973,
"confidence": "high",
"model": "ElevenLabs v2",
"methodology": "v3.2",
"duration_ms": 482,
"fingerprint": "sha256:9f8a2c…",
"citation_url": "https://aivoicedetector.com/v/ab12cd"
}
What comes back on a successful call. Nothing hidden, nothing rounded up.
| Field | Type | What it means |
|---|---|---|
| verdict | string | likely_synthetic, likely_authentic, or uncertain. |
| probability | number | 0 to 1, how likely the speech was machine-generated. We never round up. |
| confidence | string | high, medium, or low. Driven by audio quality and clip length. |
| model | string | The recognized generator (e.g. ElevenLabs v2), or "unknown synthesis". |
| methodology | string | The methodology version used, stamped on every verdict (e.g. v3.2). |
| duration_ms | number | Compute time for the verdict, in milliseconds. |
| fingerprint | string | A one-way hash of the audio. We never store the audio file itself. |
| citation_url | string | A permanent, APA-citable page for the verdict. Quote it, file it, subpoena it. |
A probability, not a promise.
The API tells you when it cannot tell. A probability near 50% means we genuinely do not know, usually because the clip is short or heavily compressed. We return the number and the confidence, and we never round up to look certain.
Short answers. Email the team for anything not here.