JPEG to Word DOCX converter

JPG to DOCX rebuilt a photographed receipt as editable Word content and created one Word table for the item rows.

Converted with AI Deep Read · input deleted within 24 h
Free: 5 conversions a day · 5 MB each
Higher limits →

From real runs

What you get — and what changes

Element	Result	What happens
Receipt header	Kept	The store name and register line were transcribed into editable Word paragraphs despite rotation and JPEG compression.
Item table	Changed	Our document engine generated one Word table from the OCR transcript, but column widths and receipt-like spacing needed cleanup.
Negative amounts	Kept	Discount and return amounts stayed in parentheses in DOCX because this document route does not normalize accounting negatives.
Blank quantity cells	Changed	Rows without quantities were present, but blank middle cells can be awkward to edit in the resulting Word table.
Payment lines	Kept	Card authorization and reimbursement-code text appeared below the table as normal Word paragraphs.
Paper appearance	Lost	The rotated paper edge, receipt background color, and camera framing were not preserved in the Word output.
Runtime	Kept	The receipt JPG returned an 11 KB DOCX in 4.3 seconds and consumed one Deep Read credit.

Receipt header Kept
The store name and register line were transcribed into editable Word paragraphs despite rotation and JPEG compression.
Item table Changed
Our document engine generated one Word table from the OCR transcript, but column widths and receipt-like spacing needed cleanup.
Negative amounts Kept
Discount and return amounts stayed in parentheses in DOCX because this document route does not normalize accounting negatives.
Blank quantity cells Changed
Rows without quantities were present, but blank middle cells can be awkward to edit in the resulting Word table.
Payment lines Kept
Card authorization and reimbursement-code text appeared below the table as normal Word paragraphs.
Paper appearance Lost
The rotated paper edge, receipt background color, and camera framing were not preserved in the Word output.
Runtime Kept
The receipt JPG returned an 11 KB DOCX in 4.3 seconds and consumed one Deep Read credit.

Sample conversions

Receipt photo

Input: Rotated JPG receipt with five item rows, quantities, amounts, two parenthesized negatives, total, card auth, and reimbursement note.
Output: DOCX included editable receipt text and a Word table. The two negative amounts stayed parenthesized, and the paper rotation was discarded.

Low-contrast field note

Input: Compressed JPG with grey inspection notes, psi values, a faint stamp, and a handwritten-style line.
Output: Word output is suitable for narrative cleanup, but the hand note should be reviewed because OCR certainty is lower than printed text.

A real JPEG → Word DOCX run

We converted our JPEG sample (97 KB) with AI Deep Read under AI Deep Read on 2026-09-11. It took 4.0 s and produced a 11 KB Word DOCX file, 89% smaller than the input. The engine raised 1 warning, listed below.

Input · sample.jpg · 97 KB

1240 × 1754 px, baseline

Width: 1,240
Height: 1,754
Encoding: baseline

Output · sample.docx · 11 KB

Word document: 23 paragraphs, 3 headings, 1 table, 0 embedded images; fonts Consolas

Paragraphs: 23
Headings: 3
Tables: 1
Images: 0
Archive parts: 16
Fonts: Consolas

AI Deep Read read 1 page; 1 credit per page

Is your file a scan?

JPG-to-DOCX starts from a photo or scan and spends 1 Deep Read credit per image. The OCR transcript becomes Word content after our document engine conversion, so shadows and paper skew vanish while ambiguous small print remains a review risk.

Options and when to change them

extractTablesAsGfm: Keep it enabled for receipts or photographed forms so table syntax can become a Word table.
preserveLayout: Use it when row and label placement in the photo matters more than a clean document flow.
languageHint: Set this for receipts or signs in a known language when item names are short or abbreviated.

Do it yourself

Tesseract + Pandoc

bash

tesseract receipt.jpg stdout --psm 6 > receipt.txt
pandoc receipt.txt -o receipt.docx

The command makes a DOCX, but the receipt table usually needs manual tabbing or a hand-built table afterward.

JPEG to Word DOCX by API or MCP

The HTTP API and the MCP server run the exact engine this page uses (AI Deep Read); the response carries the same warnings the web converter shows. Check support first with GET /api/v1/pairs?from=jpg&to=docx.

curl

curl -X POST https://filetypeconverters.com/api/v1/convert \
  -H "Authorization: Bearer $FTC_API_KEY" \
  -F "file=@input.jpg" -F "from=jpg" -F "to=docx" \
  -F "deepRead=true" \
  --output output.docx

API reference

When this is the wrong conversion

If the receipt values need formulas, use /convert/jpg-to-xlsx instead of editing a Word table.
If you only need the extracted words, /convert/jpg-to-txt avoids DOCX packaging and table cleanup.
If exact evidence is required for reimbursement, keep the original JPG attached to the Word summary.

JPEG to Word DOCX questions

Will receipt negatives become minus signs in DOCX?

No. The receipt DOCX kept '(4.20)' and '(3.00)' because document output preserves the printed notation. Use XLSX or CSV when normalized negative numbers matter.

Does JPG to DOCX correct photo rotation?

The text was read from a slightly rotated image, and the generated DOCX itself was upright. The rotated paper edge is not retained.

Are item rows editable as a Word table?

The tested receipt produced one Word table. Review blank cells and column widths before sending it as a polished document.