ParseJet

Image to Word — Turn a Photo into an Editable Document

Upload a photo, screenshot or scanned page and download a Word document with its text — editable, searchable, ready for Word or Google Docs. ParseJet reads the image with OCR on our own servers (English, Chinese, Japanese, Spanish and 20+ languages), keeps the lines and paragraphs in reading order, and writes a clean .docx. Free, no signup; API for batches.

Drop a file here or browse

Accepts JPG,JPEG,PNG,WEBP,TIFF,TIF,BMP,GIF files

Free — 3 requests/day, no signup. for 300 credits/month free.

Files are converted on ParseJet's servers and deleted right after the response.

How it works

1

Upload the image

A phone photo of a page, a scan, a screenshot — JPG, PNG, WebP, TIFF, BMP or GIF up to 20 MB.

2

OCR reads the text

Lines are detected and recognized on ParseJet’s servers, then reassembled into paragraphs.

3

Download the .docx

Open it in Word, Google Docs or LibreOffice and edit away.

Key features

What makes this image to word stand out.

Editable text, not a picture

The Word file contains real text you can search, correct and reformat — not the image pasted into a page.

20+ languages

Latin-script languages, Chinese and Japanese are read automatically; Korean, Cyrillic, Arabic, Hindi, Thai and Greek with a language hint (set for you on the localized pages).

Reading order kept

Lines are grouped into paragraphs the way they appear on the page.

Phone photos welcome

Upside-down images are corrected; even lighting and a straight-on shot give the best results.

Private by design

OCR runs on servers ParseJet operates with open-source models; images are discarded after the response.

Batch via API

Send images to /v1/convert/document with output_format=docx and store the documents.

Use cases

Common scenarios where this tool saves you time.

Retype nothing

A photographed letter, form or printout becomes a document you can edit in minutes.

Students and researchers

Turn photos of book pages and handouts into notes you can quote and annotate.

Office paperwork

Bring paper contracts and memos back into Word for revision.

Scanned PDFs too

For multi-page scans saved as PDF, use PDF to Word — the same OCR, page by page.

Automate with the API

Use the same tool programmatically. Works with any language — just HTTP.

cURL
# Image → Word (OCR); add ?language=ko|ru|ar|hi|th|el for non-Latin scripts
curl -X POST "https://api.parsejet.com/v1/convert/document?language=en" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "[email protected]" -F "output_format=docx" -o scan.docx
Python
import httpx

resp = httpx.post(
    "https://api.parsejet.com/v1/convert/document",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    files={"files": open("scan.jpg", "rb")},
    data={"output_format": "docx"},
    timeout=120,
)
resp.raise_for_status()
open("scan.docx", "wb").write(resp.content)
JavaScript
const formData = new FormData();
formData.append("files", imageFile);
formData.append("output_format", "docx");

const res = await fetch("https://api.parsejet.com/v1/convert/document", {
  method: "POST",
  headers: { Authorization: "Bearer YOUR_API_KEY" },
  body: formData,
});
const docx = await res.blob();

Want to automate this?

ParseJet API gives you the same parsing power via a single HTTP endpoint. No ffmpeg, no poppler, no tesseract — just one API call.

curl -X POST https://api.parsejet.com/v1/parse/auto/url \ -H "Content-Type: application/json" \ -d '{"url":"https://example.com"}'
Read API Docs

Frequently asked questions

How do I convert a JPG to a Word document?

Upload the image above and click Convert; download the .docx that comes back and open it in Word. Three conversions a day are free without an account.

Does it keep the layout of the page?

It keeps the text in reading order with paragraph breaks. Columns, fonts and exact positioning are not reproduced — you get clean editable text, which is what most people want to work with.

Can it read handwriting?

Printed and typed text is where OCR is reliable. Neat block letters often work; cursive and messy notes usually do not.

Which languages are supported?

English and all Latin-script languages, Simplified and Traditional Chinese and Japanese without settings; Korean, Russian and other Cyrillic languages, Arabic, Hindi, Thai and Greek with a language hint (the localized versions of this page set it automatically).

Is my image sent to a third party?

No. OCR runs on ParseJet’s own servers with open-source models, and the image is discarded once the document has been returned.

Is it free?

Yes. Three free conversions a day with no signup; a conversion costs 2 credits and the free account includes 300 credits per month. Paid plans start at $19/month.

Start extracting text for free

No signup required. Parse your first file in seconds.

View Pricing