OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Developer Tools & SDKs

Lingua

Lingua is an open-source Kotlin/JVM library that identifies the language of supplied text, for use in applications and other software. It uses rule-based and statistical methods, supports short and long text, and can operate offline after download.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Lingua — OpenViST project profile in AI Developer Tools & SDKs.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Lingua when a Kotlin or Java/JVM application needs an in-process language-identification step before routing or further text processing.

Who it is for

  • Kotlin and Java/JVM developers adding language detection to software.
  • Developers building NLP workflows that need language identification before classification, spell checking or other language-specific processing.

Documented uses

  • Identify the language of supplied text, including short snippets or longer passages.
  • Route incoming email according to its language.
  • Choose language-specific processing before text classification or spell checking.
Before you choose

Requirements & limits

The repository declares an Apache-2.0 license and links to Maven Central and Java documentation.

  • Lingua supports 75 listed languages and lets developers build a detector for selected languages or all supported languages.
  • The library uses rule-based and statistical methods and does not use word dictionaries, according to its README.
  • It does not require an external API connection and can be used offline after download.
  • Shared words can be ambiguous; the minimum-relative-distance setting can return Language.UNKNOWN when the input is short and the threshold is too high.
  • The public API is documented as not returning null, including for use from Java.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Detect a text language in Kotlin or Java

Build a detector for selected languages and ask it to identify the language of supplied text.

Before you start

  • A Kotlin or Java/JVM application using Lingua.
  • A text input to classify.
  • The Lingua library available to the application.

Steps

  1. Import Lingua's API and language identifiers.

  2. Build a LanguageDetector for the languages to examine.

  3. Pass the text to the detector's detectLanguageOf method and receive a Language result.

Expected outcome

The application receives the detected language for the supplied text.

Guide limitations

  • The example selects English, French, German and Spanish; it does not describe dependency installation.
  • For ambiguous text, the most likely result may not be reliable; the README documents a minimum-relative-distance option, which can yield Language.UNKNOWN for short text if set too high.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
15 October 2026
Original website title
pemistahl/lingua · Official homepage title · retained in its source language
How we review sourcesSuggest a correction