Render documents whose layout you already know, so labels come for free
Emerged finds new products worth a look, daily — what’s new today
Pull clean text from images and screenshots with a pip install and no GPU
It turns screenshots and scans into text on an ordinary laptop in about a second a page, so nothing has to go to a cloud OCR service.
Textsnap is a one-command OCR tool that runs on the CPU through ONNX Runtime. It uses a small PP-OCRv6 model first and, when confidence drops, falls back to the larger PaddleOCR-VL vision-language model for difficult pages. It reads from files, the clipboard or a webpage, handles batches, and with --structured returns Markdown instead of plain text. After the first model download it works offline. It installs with pip on macOS, Linux and Windows, and there is a portable mode for a standalone folder.
Render documents whose layout you already know, so labels come for free
A Mac capture inbox for selections, dictation and screenshots, kept as files
A desktop workspace that runs open-weight models on your own machine
A PDF scanner and editor for iPhone that works in English and Arabic
Paste screenshots into remote coding agents with Ctrl+V
Meeting notes that stay on your computer, with no bot joining the call