Extract text from images without uploading them

OCR here is done by a vision-language model reading the image directly rather than by a classical character-recognition engine, which handles screenshots, handwriting, tables and receipts noticeably better than a naive threshold-and-segment pipeline. Because it runs on your GPU there is no page quota and no upload, which matters when the documents are invoices, IDs, medical records or anything else you cannot hand to a free online converter.

free ocr onlineocr no uploadimage to text converterscreenshot to textprivate ocr toolbrowser ocr webgpuhandwriting ocr freereceipt ocr online

Frequently asked questions

Which languages are supported?

It depends on the model you pick; the default handles Latin-script languages well. Check the model card linked on the page for the exact coverage before relying on it for another script.

Does it preserve layout?

Reading order is usually preserved for simple documents. Multi-column layouts and complex tables are where any OCR pipeline, including this one, needs a human check.

Is my data uploaded to a server?

No. The model weights are downloaded from Hugging Face to your browser once, and every inference after that runs on your own GPU through WebGPU. Your text, images and audio are never sent anywhere — hjLabs.in has no inference server and no way to see your input.

Models available for this task

TrOCR Small (printed) — Xenova/trocr-small-printed, 70 MB, 62M params
TrOCR Small (handwritten) — Xenova/trocr-small-handwritten, 70 MB, 62M params
TrOCR Base (handwritten) — Xenova/trocr-base-handwritten, 341 MB, 334M params
TrOCR Base (printed) — Xenova/trocr-base-printed, 341 MB, 334M params
Nougat Small — Xenova/nougat-small, 258 MB, 250M params
Texify — Xenova/texify, 321 MB

Explore the rest of the playground

Vision models

Background removal — Remove a background without uploading the photo
Object detection — Detect objects in an image, on your own hardware
Zero-shot object detection — Detect anything you can describe, with no training
Image classification — Classify an image with ViT, locally
Zero-shot image classification — Classify images against labels you invent, using CLIP
Image segmentation — Segment an image into labelled regions, locally
Depth estimation — Generate a depth map from a single photo
Image to 3D (point cloud) — Turn a single photo into a 3D scene you can orbit
Image captioning — Generate a caption or alt text for any image

Guides & comparisons

Model catalog — The model catalog: what actually runs in a browser
WebGPU vs WASM — WebGPU vs WebAssembly for running models in a browser
Browser AI vs cloud API — Browser inference vs a hosted API: an honest comparison
Transformers.js vs WebLLM — Transformers.js vs WebLLM
Whisper model sizes — Choosing a Whisper size for browser transcription
fp32 vs q8 vs q4 — Picking a quantization level for browser inference
Why no image generation — Why this playground has no text-to-image generation
FAQ — Frequently asked questions about browser-based AI
About — About this project

This playground needs JavaScript and WebGPU. Models are downloaded to your browser and executed on your own GPU, so there is nothing to show without a script engine. Enable JavaScript, or read the FAQ for what the site does.