ocr-local

Extract Chinese or English text from images locally using Tesseract.js.

Updated Mar 11, 2026
One-click install
npx skills add https://github.com/ISAQQSAI/SkillAttack --skill ocr-local-isaqqsai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ocr-local
Source: https://github.com/ISAQQSAI/SkillAttack/tree/main/data/hot100skills/074_shaw555_ocr-local
Command: npx skills add https://github.com/ISAQQSAI/SkillAttack --skill ocr-local-isaqqsai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires tesseract.js, and includes scripts (resource) components.

What problem does it solve?

Manually extracting text from images is slow and error-prone; this Skill automates OCR locally without needing online services.

Core Features & Use Cases

  • Local OCR execution with no API keys required.
  • Supports Chinese (simplified/traditional) and English with optional mixed-language recognition.
  • Use cases include scanning documents, screenshots, and photos to extract text for indexing or archival.

Quick Start

Run the OCR script on an image to extract text locally without sending data to external services.

Frequently Asked Questions about ocr-local

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract text from images locally using Node.js without an API key?

You can extract text from images locally by running a Node.js script with the tesseract.js library. This offline OCR approach requires no API keys and processes documents or screenshots directly on your machine, returning plain text or JSON.

Does offline OCR with tesseract.js support mixed Chinese and English text recognition?

Yes, offline OCR with tesseract.js supports mixed Chinese and English text recognition. You can specify language codes like chi_sim, chi_tra, and eng to extract text from photos or documents containing mixed-language content.

What is the best way to perform image-to-text conversion without sending data to external services?

The best way to perform image-to-text conversion privately is using a local OCR script. By leveraging tesseract.js, the extraction executes entirely offline without external calls, ensuring your document and screenshot data remains secure.

What are the limitations of using tesseract.js for offline document scanning?

Limitations of using tesseract.js for offline document scanning include requiring a local Node.js environment and relying on the accuracy of the Tesseract OCR engine. It supports specific language codes and may require clear image inputs for accurate text extraction.

Can I get JSON output from extracting text in screenshots locally?

Yes, you can get JSON output when extracting text from screenshots locally. The OCR script processes images using tesseract.js and can format the recognized Chinese or English text into structured JSON or plain text outputs.