Calque vs Codia AI

Calque is a free, MIT-licensed tool that turns a PNG or JPEG website screenshot into HTML and CSS by measuring pixels. It can produce a self-contained HTML file or JSON measurements, including colors, type scale, weights, spacing, container width, gutters, and corner radii. It also identifies sections, columns, cards, buttons, alignment, and reading order, and can reconstruct vertical gradients. With the assets option, it crops photographs from the screenshot for use in the output. Its check command renders the result in an installed Chrome-family browser and compares it pixel by pixel with the screenshot. Calque is packaged as a Claude skill that provides measurements for Claude to use when writing project code. The documented workflow uses Tesseract for OCR; Docker is optional. The maker says it makes no model call or API request and works offline after OCR data is cached. It handles one screenshot, not a whole site, and cannot identify an exact typeface. Icons become placeholders, and photo crops retain screenshot resolution and any overlaid text.

Codia AI converts screenshots, PDFs, slides, images, and design files into editable designs and other creative formats. Its Screenshot to Figma workflow detects text and layout to rebuild screenshots as editable layers. It also converts Photoshop files and content from Canva, Notion, or Office into Figma designs. For development, it can turn screenshots, PDFs, or Figma files into code for React, Vue, SwiftUI, Flutter, Android, or plain HTML. NoteSlide converts NotebookLM exports, regular PDFs, and image-based slides into editable PowerPoint or Keynote presentations. Visual Struct API turns interface screenshots and mockups into structured JSON, SVG, and Figma-compatible files. The product family includes Codia Studio and Figma and Canva plugins, with listed workflows for Figma, Canva, Photoshop, Sketch, Cursor, Claude Desktop, and ChatGPT. Codia offers web, API, and extension access, and lists a free plan at free. It says private customer files, prompts, and outputs are not used to train models unless the customer opts in or a separate written agreement provides otherwise. Converted output may need manual review, and OCR depends on source quality.