Text Processing

Fast, easy-to-use AI text embeddings, optimized for serverless functions.

Markdown parser and lexer. A fork of marked.js maintained for Assemble.

Core engine to convert extended MDAST to DOCX. Supports plugins for footnotes, images, lists, tables, and more. Designed for seamless Markdown-to-DOCX conversion.

Convert Markdown Abstract Syntax Tree (MDAST) to DOCX seamlessly. Supports footnotes, images, links, and customizable document properties.

N8N node for generating text embeddings using Transformer.js with direct text input

A powerful AI-powered CLI tool

A tool for semantic chunking of text

Semantically create chunks from large texts. Useful for workflows involving large language models (LLMs).

Extend MDAST by parsing embedded HTML in Markdown. Converts HTML into structured MDAST nodes compatible with @m2d/core for DOCX generation.

Post-processing tools for Fountain screenplays

Extend MDAST by parsing embedded HTML in Markdown. Converts HTML into structured MDAST nodes compatible with @m2d/core for DOCX generation.

Functions for manipulating strings.

Naive Bayes Text Classifier

🧠 powerful JavaScript library that leverages advanced AI embeddings to perform zero-shot text classification. Whether you're dealing with unlabelled data or seeking to classify text against dynamic and user-defined labels, this library provides a seamles

a javascript package for node and browsers that supports general processing of the Sutton SignWriting script

Core engine to convert extended MDAST to DOCX. Supports plugins for footnotes, images, lists, tables, and more. Designed for seamless Markdown-to-DOCX conversion.

A library that extracts City, State and Zip information from text and provides a structured response.

Lightweight JavaScript SDK for running Clara agent flows with comprehensive node support including AI, data processing, API operations, file handling, and audio transcription

An accurate natural language detection library, suitable for long and short text alike

Add a custom document scanner to your web apps by using and customizing our proven imaging technology. The Document Scanner SDK is the same software that we use at the core of Genius Scan: it's tried and trusted every day by millions of people on iOS and

Count syllables in text using the CMU Pronouncing Dictionary

A C++ based data analytics platform for processing large-scale real-time streams containing structured and unstructured data

Read Vietnamese number like a Vietnamese

一个基于 Cheerio 的 HTML 解析和数据提取工具库

A pure JavaScript implementation of a BPE tokenizer (Encoder/Decoder) for GPT-2 / GPT-3 / GPT-4 / Claude Instant / Claude 2

A fork of xml-js with some improvements. A convertor between XML text and Javascript object / JSON text.

JavaScript library that provides advanced string casing capabilities with intelligent capitalization handling. It offers a comprehensive set of features to convert strings to various casing styles, including title case, sentence case, camel case, snake ca

MDAST to DOCX plugin for resolving and embedding images. Supports base64, URLs, and custom resolvers for seamless DOCX image integration.

A Node.js wrapper for the Python EasyOCR library

A Model Context Protocol (MCP) server implementation for Sarvam's text processing capabilities, providing language identification, text analytics, translation, and transliteration services for Indian languages.

MDAST to DOCX plugin for resolving and embedding images. Supports base64, URLs, and custom resolvers for seamless DOCX image integration.

Extended MDAST types and custom node data for mdast2docx with support for DOCX formatting.

A Gatsby plugin that automatically adds configurable watermarks to all images during the build process. Supports both text and image watermarks.

Extended MDAST types and custom node data for mdast2docx with support for DOCX formatting.

SDK for creating videos programmatically using JSON2Video API

Tokenizer for Vietnamese in Nodejs and Javascript

Babel Street Analytics API Node.js client SDK

ChatGPT Client using official OpenAI API

Vietnamese string processing library.

React Native plugin of the Docutain Document Scanner SDK for Android and iOS. High quality document scanning, data extraction, text recognition and PDF creation for your apps. Easily scan documents in your app.

A convertor between XML text and Javascript object / JSON text.

A powerful text analytics library that provides easy integration with AWS Comprehend and Azure Text Analytics for language detection, sentiment analysis, entity recognition, and key phrase extraction.

Convert Markdown Abstract Syntax Tree (MDAST) to DOCX seamlessly. Supports footnotes, images, links, and customizable document properties.

MCP server for terminal operations and file editing

Text processing implementation, supports commonly used rich text formats, such as font size, color, bold, italics, etc.

A convertor between XML text and Javascript object / JSON text.

A reverse engineered API for Google Bard chatbot

An easy-to-use prompt builder for creating structured prompts

verse.db isn't just a database, it's your universal data bridge. Designed for unmatched flexibility, security, and performance, verse.db empowers you to manage your data with ease.

Capacitor plugin of the Docutain Document Scanner SDK for Android and iOS. High quality document scanning, data extraction, text recognition and PDF creation for your apps. Easily scan documents in your app.