75+ languages
Detects major and many minor languages, returning standard ISO 639-1 codes.
CatalogLatency Typically 0.1–0.5 seconds Async false Rate Limit Per API key Max Input No hard limit; very short strings (under 10 characters) may reduce accuracy
cn8/text-language
Send a `texts` array and get one detection per text in `data.results`. Each detection
Learn more about Language Detection Text NLPsyncInstant previewtextanalysisnlp
Try it
Texts to detectOne text per line — any language.
Result
Results show up here
The sample input is ready — just hit Run.
Overview
Send a texts array and get one detection per text in data.results. Each detection includes an ISO 639-1 code (en, tr, es, …), a full language_name, and a confidence score. Responses are synchronous and fast. Ideal for routing content, measuring language distribution, and pre-processing before language-specific services.
Key capabilities
Confidence per detection
Every detection includes a confidence score from 0 to 1.
Language name included
Each result returns both the code and the full language name.
Fast
Lightweight detection, typically sub-second.
When to use it
Content routing
Send text to the right translator, locale or language-specific pipeline.
Analytics
Measure the language mix in user-generated content.
Pre-processing
Detect language before feeding text into language-specific services like sentiment or NER.
Input & output
input
A texts array of strings — one detection is produced per text.
JSON body
output
results[] with a language code, language_name and confidence per text.
JSON
Guides & tips
How it works
- Each text in the
textsarray is matched to its most likely language. - You get back the ISO 639-1 code, the full language name, and a confidence score, one entry per text in
data.results. - For mixed-language text, the dominant language is returned.
Tips
- Use the field name
texts(an array); you can include several texts in one request, and the price is per request. - The top match is returned per text — there's no separate list of alternative candidates.
- For reliable results, send at least a full sentence; very short strings (under 10 characters) score lower.
Specs
Schema
Request body
textsrequiredarray<string>Array of texts. Each text produces one results[] entry.
Response
results[].languagestringISO 639-1 code (e.g. en, tr, es, fr).
results[].language_namestringFull language name (e.g. Turkish, English, French).
results[].confidencenumberConfidence score, from 0 to 1.
Pricing
Billed per request.
| Service | Unit | Price |
|---|---|---|
| Language Detection | item | $0.001/request |