French profanity filter API that reads verlan

It reads verlan, accents dropped or swapped and texting shorthand, and lets habite and salopette through.

Live on the real engine Verlan, flipped back

te pu

« pute » whore

**** block · strong

Name your users' country too: gosses and tabernacle are read as Canada reads them (every word read by country).Each answer is the rules alone, the fast mode, checking a comment with language: "fr". In balanced mode, the default, the model reads what the rules leave open.

Accents dropped or swapped

Five spellings of one insult, each read back to the same word.

enculé
encule
éncule
enculè
ENCULÉ

Each one reads as

encule

fucker

blockall 5

Every other French disguise, read back

Each spelling as typed, what the rules read in it, the tricks they named and their answer.

Digits for letters
3ncul3
reads asencule
leetspeakblock · strong
Dotted
e.n.c.u.l.e
reads asencule
separatorblock · strong
A Cyrillic с
сonnard
reads asconnard
homoglyphmixed_scriptblock · strong
Letters repeated
saloooope
reads assalope
repeated_charsblock · strong
A zero and a four
c0nn4rd
reads asconnard
leetspeakblock · strong
A Cyrillic е
putе
reads aspute
homoglyphmixed_scriptblock · strong

Texting shorthand, read in full

The letters French users type in place of the words.

Short forTypedWhat it saysThe rules

fils de putefdpson of a whoreblock · strong

nique ta mèrentmfuck your motherblock · strong

ferme ta gueuleftgshut the fuck upblock · moderate

va te faire foutrevtffgo fuck yourselfblock · strong

ta gueuletgshut upblock · mild

putainptnfuck, said to no onereview · strong

French words a list would block

A list matching inside words finds a rude string in each; the rules read the whole word.

habiteLives, as in j’habite
salopetteDungarees
fichierA computer file
MâconA town in Burgundy
pissenlitA dandelion
PuteauxA town beside Paris
députéA member of parliament
BitcheA town in Lorraine

A list matching inside words8 of 8blocked

Unprofane, rules alone8 of 8allow

Measured in French

The same French texts given to every system, and the open benchmark’s French items.

95.2%

Unprofane

Flagged 4.2% of clean French texts

65.3%

Perspective API

Flagged 2.1% of clean French texts

58.1%

OpenAI moderation

Flagged 6.3% of clean French texts

The share of 167 toxic French texts each caught; the same set holds 240 clean ones. The judged development set, read on 2026-09-28, engine 2026-09-29, each system at Unprofane’s overall false-alarm rate. Unprofane was tuned on this set, so its figures here flatter it.How it was measured

1.000F1 on the Scunthorpe Test’s 35 French items, rules aloneThe public split, run of 2026-10-20, engine 2026-10-18. Every language’s score

Other APIs and French

AWS ComprehendIts toxicity detection supports only English.Amazon Web Services, read 2026-10-20
WebPurifyIt does not detect the language: a text is checked as English unless the call names another.WebPurify (WebFurther, LLC), read 2026-10-20

Name French in the call

Send language "fr" and a bare word reads as French writes it. Every language is still read.

Get your API key

100 checks a day, no card

curl -X POST https://api.unprofane.com/v1/check \
  -H "Authorization: Bearer up_test_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"text":"Va te faire foutre, connard","context":"comment","language":"fr"}'

const res = await fetch('https://api.unprofane.com/v1/check', {
  method: 'POST',
  headers: { Authorization: 'Bearer up_test_YOUR_KEY', 'Content-Type': 'application/json' },
  body: JSON.stringify({
    "text": "Va te faire foutre, connard",
    "context": "comment",
    "language": "fr"
  }),
});
const result = await res.json();

import httpx

r = httpx.request(
    "POST",
    "https://api.unprofane.com/v1/check",
    headers={"Authorization": "Bearer up_test_YOUR_KEY"},
    json={
        "text": "Va te faire foutre, connard",
        "context": "comment",
        "language": "fr",
    },
    timeout=5.0,
)
result = r.json()

req, _ := http.NewRequest("POST", "https://api.unprofane.com/v1/check",
	strings.NewReader(`{"text":"Va te faire foutre, connard","context":"comment","language":"fr"}`))
req.Header.Set("Authorization", "Bearer up_test_YOUR_KEY")
req.Header.Set("Content-Type", "application/json")
res, err := http.DefaultClient.Do(req)

$res = file_get_contents('https://api.unprofane.com/v1/check', false, stream_context_create(['http' => [
  'method' => 'POST',
  'header' => "Authorization: Bearer up_test_YOUR_KEY\r\nContent-Type: application/json\r\n",
  'content' => '{"text":"Va te faire foutre, connard","context":"comment","language":"fr"}',
]]));
$result = json_decode($res, true);

require 'net/http'; require 'json'
uri = URI('https://api.unprofane.com/v1/check')
req = Net::HTTP::Post.new(uri, 'Authorization' => 'Bearer up_test_YOUR_KEY', 'Content-Type' => 'application/json')
req.body = '{"text":"Va te faire foutre, connard","context":"comment","language":"fr"}'
res = Net::HTTP.start(uri.host, uri.port, use_ssl: true) { |http| http.request(req) }
result = JSON.parse(res.body)

using var http = new HttpClient();
http.DefaultRequestHeaders.Authorization = new AuthenticationHeaderValue("Bearer", "up_test_YOUR_KEY");
var req = new HttpRequestMessage(HttpMethod.Post, "https://api.unprofane.com/v1/check");
req.Content = new StringContent("{\"text\":\"Va te faire foutre, connard\",\"context\":\"comment\",\"language\":\"fr\"}", Encoding.UTF8, "application/json");
var res = await http.SendAsync(req);
var result = await res.Content.ReadFromJsonAsync<JsonElement>();

var http := HTTPRequest.new()
add_child(http)
http.request_completed.connect(func(_r, _code, _h, body):
	var result = JSON.parse_string(body.get_string_from_utf8())
	print(result))
http.request("https://api.unprofane.com/v1/check",
	PackedStringArray(["Authorization: Bearer up_test_YOUR_KEY", "Content-Type: application/json"]),
	HTTPClient.METHOD_POST, "{\"text\":\"Va te faire foutre, connard\",\"context\":\"comment\",\"language\":\"fr\"}")

Response200

{
  "allowed": false,
  "action": "block",
  "severity": "strong",
  "matches": [
    {
      "text": "Va te faire foutre",
      "normalized": "va te faire foutre",
      "category": "insult",
      "severity": "strong"
    },
    {
      "text": "connard",
      "normalized": "connard",
      "category": "insult",
      "severity": "strong"
    }
  ],
  "censored": "******************, *******",
  "language": {
    "detected": "fr",
    "confidence": 0.75
  }
}

Other languages

Filter French before anyone reads it

Every language Unprofane covers is read on every call, French with its disguises included.

Get your API key