Work out what language text is in

The language, with a confidence figure, from as little as a sentence.

Drop a file here, or choose one, or type below.

.txt · .md · .html · .csv · up to 4 MB · processed in memory and never stored · or paste with Ctrl+V

Or type it in

3 credits

What it does

Also called: work out what language text is in · detect the language of a paragraph · identify a foreign language snippet.

Use it from your own code

The same endpoint this page calls — no daily cap, 3 credits a call either way.

POST /v1/nlp/language-detect

curl -X POST "$DOATHING_API/v1/nlp/language-detect" \
  -H "x-api-key: $DOATHING_KEY" \
  -H "content-type: application/json" \
  -d '{"text": "Le chat est assis sur le tapis et regarde la pluie."}'

The language, with a confidence figure, from as little as a sentence.

Detect the language of a text with per-candidate confidence scores.

Input

Send either a text string or a file object. A file is decoded as UTF-8 and must be one of text/plain, text/markdown, text/html, text/csv.

Response

The result carries your remaining balance alongside it, so you can track spend without a second call.

{
  "language": "fr",
  "language_name": "French",
  "confidence": 0.9999,
  "candidates": [
    {
      "language": "fr",
      "language_name": "French",
      "confidence": 0.9999
    }
  ],
  "request_id": "37f01edb-0163-42a1-ac51-0acaef979800",
  "credits_remaining": 96
}

Cost

3 credits per call, whether it is run from the site or from the API — the credential differs, the price does not. A new account starts with 20 credits.

A rejected request still costs a credit: the authorizer decrements before the tool validates. A call rejected for a missing or invalid key is free.