MLAIEL is in test & preview — some profiles and content are demonstrations. Learn more
Detects the language of a text offline and translates it with OpenAI, DeepL or LibreTranslate.
Agent = does one task.
Staff ran it and it worked. You still need your own provider accounts where listed.
You get an in-app notification when a new version is published. Nothing is installed or updated on your computer automatically.
Guesses which language a text is written in, offline: by alphabet for non-Latin scripts (Arabic, Cyrillic, Chinese, Japanese, Korean, Thai, Hindi and more) and by common words for 13 Latin-script languages. It translates through a service you connect yourself: OpenAI, DeepL or a LibreTranslate server. In auto mode it tries the configured services in order and falls back if one is down. Without any service it says so instead of inventing a translation.
Runs on MLAIEL's own OpenAI key for signed-in members with a verified email. Inputs and results are moderated, nothing you upload is stored, and you get 8 tries per day across all tools.
Sign in with a verified email to try this tool. Sign in
This repository is linked. Activity appears after the next daily check.
Public data from GitHub, checked once a day.
Developers who need a quick language guess and a small, dependable translation wrapper.
Optional: your own OpenAI account
Put your key in a setting named OPENAI_API_KEY on your own computer. Never share it. Where to get a key
Optional: your own DeepL account
Put your key in a setting named DEEPL_API_KEY on your own computer. Never share it. Where to get a key
Optional: your own LibreTranslate account
Put your key in a setting named LIBRETRANSLATE_URL on your own computer. Never share it. Where to get a key
MLAIEL does not run these tools for you and never asks for your provider keys. You run them on your own computer or server, with your own accounts.
Downloads come straight from the source repository. MLAIEL does not host files.
Follow these steps in order. If you get stuck, ask in the improvement project.
Use as a library
import { detectLanguage, translateText } from "./language-detection-translation/src/index.ts";
console.log(detectLanguage("Ich weiß nicht, warum der Zug so spät ist."));
console.log(await translateText("Good morning", { target: "ja" }));Command line
node --env-file=.env examples/cli.ts translate es "Hello world"
Node.js 22.18+ (runs TypeScript directly, no build step) · Windows, macOS, Linux (tested on Windows 11) · No runtime npm dependencies
License: MIT
MIT, declared by the owner: Fahed Mlaiel, who holds all rights to Mlaiel/iacherie, chose the MIT License for this clean TypeScript rewrite on 2026-10-01. The package ships the LICENSE file. This is not legal advice.
This is not legal advice. Check the license yourself before you use or share this tool.
Run test · Passed
Windows 11, Node.js 22.18, package 1.0.0 run from source with a real OpenAI key, 2026-10-01 · Oct 1, 2026
Detected the language of samples offline and translated them with a real OpenAI key.
Run test · Passed
Windows 11 · CPython 3.12.7 · fresh virtual environment with httpx only · all provider keys removed · Oct 1, 2026
Offline detection ran correctly for Arabic, Chinese and Russian. Translation was not tested with a real service: without keys it returned provider NONE, as expected.
0.1.0 → 1.0.0
Oct 1, 2026 · source revision mlaiel packages/marketplace/language-detection-translation@1.0.0
1.0.0 is a clean TypeScript rewrite. Latin-script languages are now told apart (0.1.0 reported them all as English), more scripts are detected, and OpenAI translation with provider fallback is new. 23 offline tests; OpenAI translation validated with the real API.
0.1.0 · first release
Oct 1, 2026 · source revision 54911be
First listing of the iacherie language module, pinned to the analyzed revision. No code changes compared to the source repository.
Updates are never applied silently. You decide if and when to download a new version.
Source files: language_support.py