Queue multiple files
Add screenshots, scans, or exported images and run them as one OCR batch.
Feature
Extract text from many images without the busywork.
The batch extractor queues multiple files, runs local OCR on each, and merges the results when one combined output fits the job.
Private by defaultBatch OCR uses local engines unless you configure cloud OCR.
Built for repetitive OCR jobs.
Batch work stays in a focused queue instead of tab after tab.
Merge when useful
Combine results into a single document when the job calls for one combined output.
Local engines
Native OCR, PaddleOCR, Tesseract, and ocrs all run on your machine.
Same metadata path
Results land in history like single extractions, ready to reopen anytime.
Workflow
Batch OCR in three moves.
Add your files
Select the images for the job and let the batch extractor take over.
Run the queue
Extract runs locally, with per-file results collected as they finish.
Use or merge output
Copy individual results, merge them, or convert to Markdown, HTML, Word, or PDF.
Try batch extraction on your next stack of images.
pixtotext runs full OCR locally on Windows, macOS, and Linux, and it is free to try.