Language Detector

Overview

Detects the likely language of text using offline statistical analysis. Returns ISO 639-1 code, confidence score, alternatives, and reliability indicator. Accepts file input via file_ref — no need to extract file content first.

LLMs can guess languages but waste tokens and may hallucinate ISO codes. We return a confidence-scored, offline answer with zero reasoning overhead.

When to use it

Scope

Non-goals

• Does not translate text
• Does not detect byte or character encoding
• Does not identify writing script (Latin, Cyrillic, CJK)
• Does not distinguish regional dialects (e.g. Brazilian vs European Portuguese)

Properties

Capabilities

Cost & billing

Flat rate per invocation

File handling

File limits

Constraints this skill applies to your input and generated files. The “Limited by” column shows the static source of each cap; none of these can be raised by upgrading your plan.

How we handle your data

Input schema

Output schema

API contract

curl -sS -X POST "$BASE/v1/execute" -H "Authorization: Bearer $KEY" -H 'Content-Type: application/json' -d '{"skillKey":"text.detect_language","input":{"text":"The quick brown fox jumps over the lazy dog near the riverbank."}}'

import { Squillify } from "@squillify/sdk";

const sq = new Squillify({ apiKey: process.env.SQUILLIFY_API_KEY });

const { output } = await sq.execute("text.detect_language", {"text":"The quick brown fox jumps over the lazy dog near the riverbank."});

Errors

Other limits

Limitations

• Does not translate text
• Does not detect byte or character encoding
• Does not identify writing script (Latin, Cyrillic, CJK)
• Does not distinguish regional dialects (e.g. Brazilian vs European Portuguese)
• Translating text between languages
• Detecting file or byte-stream encoding
• Classifying very short text (1–3 words) where statistical signal is weak
• Script identification without language classification

How to call

POST /v1/execute (requires authentication)

{
  "skillKey": "text.detect_language",
  "input": {
    "text": "The quick brown fox jumps over the lazy dog near the riverbank."
  }
}

Examples

{
  "text": "The quick brown fox jumps over the lazy dog near the riverbank."
}

{
  "language": "en",
  "_meta": {
    "originalLength": 63,
    "truncated": false,
    "sampleLength": 63
  },
  "confidence": 1,
  "reliable": true,
  "alternatives": [
    {
      "confidence": 1,
      "language": "en"
    },
    {
      "confidence": 0.8071,
      "language": "da"
    },
    {
      "confidence": 0.8045,
      "language": "tl"
    },
    {
      "confidence": 0.7994,
      "language": "cy"
    },
    {
      "confidence": 0.7947,
      "language": "yo"
    }
  ]
}

{
  "candidateLanguages": [
    "fr",
    "es",
    "it"
  ],
  "text": "Bonjour le monde"
}

{
  "language": "fr",
  "_meta": {
    "originalLength": 16,
    "truncated": false,
    "sampleLength": 16
  },
  "confidence": 1,
  "reliable": true,
  "alternatives": [
    {
      "confidence": 1,
      "language": "fr"
    },
    {
      "confidence": 0.7004,
      "language": "it"
    },
    {
      "confidence": 0.6811,
      "language": "es"
    }
  ]
}

Recommended use cases

• Route text to the correct language-specific pipeline
• Select locale-aware formatting or segmentation rules
• Validate declared language metadata against actual content

Avoid for

• Translating text between languages
• Detecting file or byte-stream encoding
• Classifying very short text (1–3 words) where statistical signal is weak
• Script identification without language classification

Related skills

Composable with

Safety & privacy

• Runs without calling any external service.
• Your payloads are never stored permanently.
• Telemetry captures metadata only — never your payload contents.
• We never train models on your payloads.
• No human reviews your payloads.

Tags