eniompw/GeminiOCR
Gemini API for OCR
This tool helps you quickly extract text from images, like scanned documents, photos of signs, or screenshots. You provide an image, and it returns the text found within it, saving you from manually typing. It's designed for anyone who needs to convert visual information into editable text.
Use this if you frequently need to get text out of images or scanned documents without retyping it manually.
Not ideal if you need highly accurate text extraction from complex layouts, handwritten notes, or documents in many different languages, as this is a simple demo.
Stars
15
Forks
3
Language
HTML
License
MIT
Category
Last pushed
Nov 17, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/eniompw/GeminiOCR"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
HanaokaYuzu/Gemini-API
✨ Reverse-engineered Python API for Google Gemini web app
faetalize/zodiac
A ⚡lightweight⚡ frontend for Google's Gemini Pro.
hihumanzone/Gemini-Discord-Bot
A Discord bot leveraging Google Gemini. Has image/video/audio recognition, conversation...
Amm1rr/WebAI-to-API
Gemini to API (Don't need API KEY) (ChatGPT, Claude, DeeepSeek, Grok and more)
GewoonJaap/gemini-cli-openai
Expose Gemini CLI endpoints as OpenAI API with Cloudflare Workers