Skip to content

Adir-html/captio

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

✦ Captio

Turn any image into clean, structured text in seconds.

Captio analyzes uploaded images and generates:

  • Title
  • Key points
  • Description
  • Context-aware summary

Supports:

  • Product photos
  • Screenshots / UI
  • Documents
  • Posters
  • Portraits / people
  • Service / business visuals

🚀 Live Demo

👉 https://captio.vercel.app


⚡ How it works

  1. Upload an image
  2. Click generate
  3. Get structured, usable text instantly

✨ Features

  • Works with multiple image types
  • Multi-language support
  • Clean, structured output
  • Copy / export ready
  • No signup required
  • Fast (~10 seconds)

🛠 Tech Stack

Frontend

  • HTML, CSS, JavaScript (no framework)

Backend

  • FastAPI (Python)
  • OpenRouter (GPT-4o Vision)

Deployment

  • Vercel (frontend + serverless backend)

📸 Examples

Try uploading:

  • a product image → get product description
  • a screenshot → get explanation
  • a document → get summary
  • a portrait → get natural description

⚠️ Notes

  • Free plan: limited generations per day
  • Backend rate limiting is best-effort (serverless environment)
  • Images are not stored

💡 Why I built this

Writing text from images (products, screenshots, docs) is annoying.

Captio makes it instant.


📬 Feedback

Would love feedback, ideas, or suggestions.

About

AI tool that turns images (products, screenshots, documents, portraits) into structured text using GPT-4 Vision.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors