Language detection library ported from Google's language-detection.
An accurate natural language detection library, suitable for short text and mixed-language text
pysbd (Python Sentence Boundary Disambiguation) is a rule-based sentence boundary detection that works out-of-the-box across many languages.
fasttext with wheels and no external dependency, but only the predict method (<1MB)
A flexible free and unlimited python tool to translate between different languages in a simple way using multiple translators
Quickly detect text language and segment language
Python bindings around Google Chromium's embedded compact language detection library (CLD2)
Fully customizable language detection for spaCy pipeline
Fork of the language identification tool langid.py, featuring a modernized codebase and faster execution times.
langid.py is a standalone Language Identification (LangID) tool.
Fast and zero-dependency lemmatization, tokenization and sentence splitting for 54 languages.
Multi-lingual Automatic Speech Recognition (ASR) based on Whisper models, with accurate word timestamps, access to language detection confidence, several options for Voice Activity Detection (VAD), and more.
Cross-language temporary email detection library. Stop users from signing up with temporary email addresses.
An auditing agent that enables automated monitoring and interaction with language models to detect potential alignment issues, reward hacking, and other concerning behaviors.
OCR, layout, reading order, and table recognition in 90+ languages.
LLM-Guard is a comprehensive tool designed to fortify the security of Large Language Models (LLMs). By offering sanitization, detection of harmful language, prevention of data leakage, and resistance against prompt injection attacks, LLM-Guard ensures that your interactions with LLMs remain safe and secure.
80x faster and 95% accurate language identification with fastText
Breame is a lightweight Python package with a number of tools to aid in the detection of words that have dual spellings and meanings in British and American English.
Translate, transliterate, get the language of texts in no time with the help of multiple APIs!
Common lingua, a language detection model.
fasttext with wheels and no external dependency, but only the predict method (<1MB)
HuSpaCy: industrial strength Hungarian natural language processing
Fully customizable language detection pipeline for spaCy
Date parsing for input whose format you do not control: format detection, ambiguity reported, 20 locales, natural language, column order, format strings.
sPrint, Superroute's printing SDK: find network, USB and Bluetooth printers, detect their language, print labels, PDF, HTML, images and raw bytes, and run a Superroute print node.
Unofficial slim build of lingua: accurate natural language detection with only the en, es, fr, de, it, pt, nl, ja models compiled in
Shared language-parsing substrate for static-analysis tools — tree-sitter dispatch and analysis primitives across 16 programming languages plus YAML, JSON, Markdown, CMake and Bash, from Rust.
Compact Language Detector v3 (CLD3) Python bindings — modernised fork with prebuilt wheels for Python 3.10–3.14.
Glin-Profanity is a lightweight and efficient Python package designed to detect and filter profane language in text inputs across multiple languages.
Fast drop-in replacement for langdetect: the same results, bit for bit, from a Rust core
Language detection using FastText and Spacy
Text preprocessing & PII anonymization pipeline for NLP/ML: ONNX NER ensemble, language detection, stopword removal, and configurable token replacement.
Text language detection basic on trigrams.
Unified language SDK — detection, transcription, romanization, translation, TTS routing
A high-accuracy, rule-based Sentence Boundary Detector (SBD) with a drop-in adapter for pysbd, delivering faster and more accurate segmentation.
Next-generation Punkt sentence and paragraph boundary detection with zero dependencies
MOMENT: A Family of Open Time Series Foundation Models
Text Language is a language detection API that detects the language of any input string, returning the full language name and its two-letter ISO 639-1 code. Send plain text passages or short snippets to identify incoming multilingual content.
Cross-language metadata standard: declare typed entities once, generate idiomatic drift-checked code across languages — Python port.
Language Detection API Client
pysbd (Python Sentence Boundary Disambiguation) is a rule-based sentence boundary detection that works out-of-the-box across many languages.
Detect language support for font binaries
AI code review tool that works with any language model provider. It detects issues in GitHub pull requests or local changes—instantly, reliably, and without vendor lock-in.
Kenya translation and language resources: Swahili/English civic glossary, Kikuyu and Luo guides, official document terminology, language detection
Turn detection for the speakers your detector was not trained on. Framework-agnostic core, thin adapters, contributable language packs.
UQLM (Uncertainty Quantification for Language Models) is a Python package for UQ-based LLM hallucination detection.
Nexatron MCP server — governed enterprise-data access for Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, and any MCP-compatible AI client. Exposes 12 tools (query, list_connections, get_schema, list_metrics, list_views, search_knowledge_base, detect_schema_drift, test_connection, list_conversations, get_report, get_credit_balance, whoami) and 1 resource (nexatron://platform/info) over the Nexatron REST API with per-tenant isolation and cryptographic audit.
This is a multilingual tokenization tool that currently supports for zh/ja/en/ko, and more languages.