ocrs

On the record

Automatic model download

On first run, the CLI downloads required models automatically and stores them in `~/.cache/ocrs`.github.com · read 5 Oct 2026

C interface

The project provides a C ABI with functions to recognize text and retrieve lines with bounding boxes.github.com · read 9 Oct 2026

CLI

The CLI can extract text from image files and write text, JSON layout data, or annotated PNG output.github.com · read 9 Oct 2026

Clipboard

The CLI supports reading an image from the system clipboard when installed with its clipboard feature.github.com · read 9 Oct 2026

Clipboard input

An optional `clipboard` feature enables OCR on images from the system clipboard.github.com · read 5 Oct 2026

Image types

The project aims to handle scanned documents, photos containing text, and screenshots with little or no preprocessing.github.com · read 9 Oct 2026

Implementation

Its neural network models are trained in PyTorch, exported to ONNX, and run using the RTen engine.github.com · read 5 Oct 2026

Installation

The CLI can be installed with Cargo using `cargo install ocrs-cli --locked`; installing it requires Rust and Cargo.github.com · read 5 Oct 2026

JavaScript

An alpha WebAssembly build is available for Node, browsers, and other WebAssembly runtimes.github.com · read 9 Oct 2026

Language support

It currently recognizes the Latin alphabet only, with support for more languages planned.github.com · read 9 Oct 2026

Library API

The project provides an OCR engine as a Rust library for use in Rust applications.github.com · read 5 Oct 2026

License

The repository lists Apache-2.0 and MIT licenses.github.com · read 9 Oct 2026

Maturity

The project describes itself as an early preview and says it may make more errors than commercial OCR engines.github.com · read 9 Oct 2026

Model customization

The C API can load custom models in ONNX format when built with the onnx feature.github.com · read 9 Oct 2026

Model data

The project says it uses open and liberally licensed datasets, and links to a separate repository with model, dataset, and custom training details.github.com · read 5 Oct 2026

OCR engine

Its neural network models are trained in PyTorch, exported to ONNX, and run using the RTen engine.github.com · read 9 Oct 2026

Output options

The CLI can save extracted text, return text and layout information as JSON, or create an annotated image showing detected words and lines.github.com · read 5 Oct 2026

Platform support

The project says it is intended to compile and run across platforms, including WebAssembly.github.com · read 5 Oct 2026

Alternatives to ocrs

OS OCR.spaceAndroidiPhone & iPad+7 VI Veryfi Invoices OCR APIAndroidiPhone & iPad+4 AT Amazon Textract AnalyzeExpenseWebAPI+1 TO Tesseract OCRAndroidiPhone & iPad+5 DL Dynamsoft Label RecognizerAndroidiPhone & iPad+5 MB Microblink BlinkIDAndroidiPhone & iPad+6 SD Scanbot Data Capture SDKAndroidiPhone & iPad+3 AO Asprise OCR SDKWindowsMac+2

Every alternative, ranked