Detect

Detect AI writing

Scores how likely a text is to be AI-generated, sentence by sentence, and returns the reasons: structural patterns, phrase habits and rhythm. Optionally calibrated against a known writer's own samples.

POST

Billing. Billed per input word at the Detect rate. Calibrated requests cost the same. Credits & pricing

curl -X POST https://api.intactvoice.com/v1/detect \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "text": "In today'\''s fast-paced world, side hustles are more than just extra cash. In this post, we'\''ll explore…",
  "granularity": "sentence",
  "explain": true
}'

Response

{
  "id": "dt_01JD4QB2M9",
  "object": "detection",
  "model": "detect-2026-10",
  "verdict": "likely_ai",
  "ai_likelihood": 0.94,
  "confidence": "medium",
  "sentences": [
    {
      "text": "In today's fast-paced world, side hustles are more than just extra cash.",
      "ai_likelihood": 0.97,
      "signals": [
        "stock_opener",
        "inflation_frame"
      ]
    }
  ],
  "structure": [
    {
      "feature": "announced_thesis",
      "present": true
    },
    {
      "feature": "restated_close",
      "present": false
    }
  ],
  "usage": {
    "words_billed": 19
  }
}

200 OK · 400 Bad Request

Body

application/json

textstringrequired

Text to analyse, 40–25,000 words. Short texts return confidence: low.

granularityenumdefault: sentence

sentence adds per-sentence scores.

Available options:documentsentence

explainbooleandefault: true

Return the signals behind the score.

calibrate_tostring

A voice_id. Scores are reported relative to that writer's own baseline.

Response

200 · application/json

verdictenum

likely_human | mixed | likely_ai

ai_likelihoodnumber

0–1. A signal, not proof of authorship.

confidenceenum

low | medium | high. Driven mostly by length.

sentencesarray

Per-sentence scores and signals.

structurearray

Document-level patterns, e.g. restated_close, announced_thesis.

Body

Response

Errors