Detect AI-generated speech

POST/v1/deepfake/detect

#Authentication

#Headers

#Request body

Send the request as multipart/form-data. Upload the audio file in the file field (up to 100 MB) and send the other fields as form fields. See Audio and limits.

• filefilerequired

  The audio file: WAV, MP3, FLAC, OGG/Opus, WebM, M4A/AAC or AIFF, at most 100 MB.

#Response

200 The check completed.

• request_idstringrequired
• operation_idstringrequired
• objectstringrequired

  always "deepfake.detection"

• resultobjectrequired
  8 fields in result

  • verdictstringrequired

    The decision: real, fake (AI-generated), or not_sure (try a longer or cleaner recording).

    One of: real, fake, not_sure

  • labelstringrequired

    The same decision in the older wording: synthetic (fake), genuine (real), uncertain (not sure).

    One of: synthetic, genuine, uncertain

  • is_syntheticbooleanrequired

    true only when the verdict is fake.

  • scorenumberrequired

    How likely the recording is AI-generated, from 0 to 1.

    0 to 1

  • thresholdnumberrequired

    The main model's threshold (0.62). Informational: decide with verdict.

  • score_semanticsstringrequired

    A short reminder of what score means.

  • duration_secondsnumberrequired

    Length of the checked audio, in seconds.

  • segmentsarray of objectrequired

    Scores for consecutive, overlapping parts of the recording.

    3 fields in segments

    • startnumberrequired

      Start of this part of the recording, in seconds.

    • endnumberrequired

      End of this part of the recording, in seconds.

    • scorenumberrequired

      How likely this part is synthetic (0 to 1).

      0 to 1

• modelobjectrequired
  2 fields in model

  • namestringrequired

    Model family: aletheia (deepfake detection) or eidos (speaker verification).

  • versionstringrequired

    Opaque model version; it changes whenever the model is updated.

• creditsobjectrequired
  4 fields in credits

  • chargedintegerrequired

    Credits used by this request. A repeated request with the same Idempotency-Key uses none: it reports 0 here and what the original request used in original_charge.

  • balanceinteger or nullrequired

    Your available credits after this request; null on the unlimited plan.

  • original_chargeinteger or null

    Only on repeated requests (charged is then 0): the credits the original request used.

  • unlimitedboolean or null

    Present (true) only for accounts on the unlimited plan, where checks use no credits.

• latency_msnumberrequired
• idempotent_replaybooleanrequired

#Example response

{
  "request_id": "req_8f14e45fceea167a5a36dedd",
  "operation_id": "op_6f1ed002ab5595859014ebf0951522d9",
  "object": "deepfake.detection",
  "idempotent_replay": false,
  "result": {
    "threshold": 0.62,
    "score_semantics": "Higher means more likely AI-generated. Decide with the verdict, not the score alone.",
    "verdict": "real",
    "label": "genuine",
    "is_synthetic": false,
    "score": 0.0731,
    "duration_seconds": 6.4,
    "segments": [
      {
        "start": 0,
        "end": 4,
        "score": 0.061
      },
      {
        "start": 2,
        "end": 6.4,
        "score": 0.085
      }
    ]
  }
}

#Errors

Error bodies share one shape with a stable error.code; see Errors for every code and how to fix it.

#Code samples

curl "https://platform.detectif.ai/v1/deepfake/detect" \
  -H "Authorization: Bearer $DETECTIF_API_KEY" \
  -H "Idempotency-Key: $(uuidgen)" \
  -F "file=@clip.wav"

import os
import uuid

import requests

with open("clip.wav", "rb") as f:
    resp = requests.post(
        "https://platform.detectif.ai/v1/deepfake/detect",
        headers={"Authorization": f"Bearer {os.environ['DETECTIF_API_KEY']}", "Idempotency-Key": str(uuid.uuid4())},
        files={"file": f},
        timeout=300,
    )
print(resp.status_code, resp.json())

import { readFile } from "node:fs/promises";
import { randomUUID } from "node:crypto";

const form = new FormData();
form.append("file", new Blob([await readFile("clip.wav")]), "clip.wav");

const res = await fetch("https://platform.detectif.ai/v1/deepfake/detect", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.DETECTIF_API_KEY}`,
    "Idempotency-Key": randomUUID(),
  },
  body: form,
});
console.log(res.status, await res.json());