ocr

Extract text from image files using the Qwen VL OCR model.

94|7|Updated Feb 10, 2026

Search Tags:#ocr #text-recognition #image-text-extraction #qwen-vl #document-digitization #screenshot-transcription

Ready to run

npx skills add https://github.com/jin-bo/agentao --skill ocr-jin-bo

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: ocr
Source: https://github.com/jin-bo/agentao/tree/main/examples/skills/ocr
Command: npx skills add https://github.com/jin-bo/agentao --skill ocr-jin-bo

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires openai, python-dotenv, and includes scripts (resource) components.

What problem does it solve?

Manually transcribing text from images like screenshots, photos, or scanned documents is slow, tedious, and prone to human error. This skill automates the entire process to deliver accurate text extraction in seconds.

Core Features & Use Cases

AI-Powered OCR: Uses the Qwen VL OCR model to reliably extract text from images of varying quality and layout.
Multi-Format Support: Works with all common image formats including JPG, JPEG, PNG, GIF, and WebP.
Use Case: Quickly pull text from a screenshot of a meeting note, a photo of a printed invoice, or a scanned research paper without manual typing.

Quick Start

Use the ocr skill to extract all text from the image file 'team-meeting-screenshot.png'.

Frequently Asked Questions about ocr

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

FAQPage Schema

How do I extract text from a screenshot or scanned document?▼

Supported image formats for text extraction include JPG, JPEG, PNG, GIF, and WebP. This allows you to process various digital image files, whether they are photos of physical materials or scanned document digitization inputs.

Do I need API keys to use Qwen VL for image text recognition?▼

Yes, you need to configure QWEN_API_KEY and QWEN_BASE_URL credentials to access the Qwen VL OCR model. These environment variables are required for the skill to authenticate and perform accurate character recognition.

What is the best way to digitize printed invoices from photos?▼

The best way to digitize printed invoices from photos is using AI-powered OCR to extract text content directly from digital image files. This approach handles varying image quality and layout to deliver accurate transcription in seconds.

Can I use python-dotenv to manage OCR API credentials?▼

Yes, you can use python-dotenv to manage your QWEN_API_KEY and QWEN_BASE_URL credentials. Loading environment variables through python-dotenv ensures the Qwen VL OCR model can securely access required authentication details.