Image to text (OCR)
Upload an image or a scanned PDF and FileTinker reads the text with on-device OCR. Pick your language, then copy or download the result. The recognition engine downloads once and runs in your browser — your file is never uploaded.
The OCR engine downloads on first use (a few MB) and is then cached.
Extract text by file type
Jump straight to your file type — each opens its own page ready to go:
OCR by language
Open the tool with a specific language preselected — each has its own page:
How to extract text from an image
- Choose your language, then upload an image or scanned PDF.
- Wait while the OCR engine reads the text (the first run downloads the model).
- Copy the recognized text or download it as a .txt file.
About OCR (optical character recognition)
OCR turns pictures of text — photos, screenshots, scanned documents — into editable, searchable text. FileTinker uses Tesseract compiled to WebAssembly, so recognition happens on your own device rather than a server. It works best on clear, well-lit, high-contrast text; stylised fonts and handwriting are harder.
Because everything runs in your browser, your documents stay private — useful for receipts, IDs, contracts and notes you'd rather not upload. The engine and language data are fetched once from a CDN and cached, so later runs start faster.
Frequently asked questions
How does the OCR work?
FileTinker runs Tesseract, an open-source OCR engine, as WebAssembly in your browser. The engine and language model download from a CDN the first time and are then cached; your image or PDF is recognised locally and never uploaded.
Which languages are supported?
English, Traditional Chinese and Simplified Chinese, plus a combined English + Chinese mode. Choose the language that matches your document before uploading for the best accuracy.
Can it read scanned PDFs?
Yes. Each page of a PDF is rendered to an image and recognised in turn, then the text is combined. Clear, high-resolution scans give the best results.
Is my file uploaded?
No. Only the OCR engine and language model are downloaded; your image or PDF is processed entirely in your browser and never leaves your device.