The rewrite and detection API.
Send a draft. Get it back in your writer's voice, fact-checked and scored, on a signed webhook.
Request · POST /v1/rewrite
curl -X POST https://api.intactvoice.com/v1/rewrite \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"text": "Many businesses struggle to create useful blog posts because the writer receives only a topic. Escalate any case older than 14 days.",
"voice_id": "voice_8f2k1x",
"platform": "blog",
"strength": "standard",
"fidelity": "strict",
"webhook_url": "https://example.com/hooks/intactvoice"
}'Result · GET /v1/jobs/{id} (excerpt)
{
"text": "Most blog posts go wrong before anyone writes a word: the writer gets a topic and nothing else. If a case is older than 14 days, escalate it.",
"summary": {
"ai_likelihood_before": 0.91,
"ai_likelihood_after": 0.14,
"verdict_after": "likely_human",
"fidelity_status": "pass",
"facts_kept": 1,
"facts_changed": 0,
"voice_match": 0.857,
"words_billed": 22
}
}Async by default.
Every rewrite returns 202 and a job. The result arrives on an HMAC-signed webhook, or poll the job. An Idempotency-Key stops a retry from billing twice.
Facts fail closed.
With strict fidelity, if a number, date, link or name would change, you get a 422 that names the fact. Nothing is billed.
Every score, in JSON.
Before and after AI-detector scores, each detector's score, flagged sentences with reasons, the fact checks and voice match. The same data as the web app.
API plans.
Billed yearly, two months free. Test keys return sample results and use no words.
Basic API$74.17 / month200,000 words a month60 requests / min
RecommendedPro API$157.50 / month600,000 words a month180 requests / min
Ultra API$324.17 / month1,000,000 words a month600 requests / min
EnterpriseCustomVolume pricing above 1M wordsCustom rate limits, invoice billing