Skip to content

JPEG to Markdown converter

JPG to Markdown read a compressed low-contrast inspection note into a short Markdown document and interpreted the drawn underline as a rule.

  • 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

  • Title Kept

    The field-note heading became a level-one Markdown heading despite low grey contrast.

  • Short note lines Changed

    Each printed note was separated into its own paragraph, which is readable but less compact than the source.

  • Measurements Kept

    The pressure target and observed values kept their numbers, semicolon, and psi units.

  • Handwritten-style text Changed

    The simulated hand note was promoted to normal Markdown text, so reviewers should compare real handwriting carefully.

  • Underline Changed

    The drawn line below the hand note became a row of underscores, adding a visual artifact not present as text.

  • JPEG noise Kept

    Compression did not create stray characters in this sample, even around faint stamp text.

  • Runtime Kept

    The 68-quality JPEG finished in 7.5 seconds and used one Deep Read credit for the image.

Sample conversions

Inspection note photo

Input
Low-contrast JPG with a title, four typed note lines, psi readings, a stamp, and one handwritten-style sentence.
Output
Markdown kept the heading and note text, read the stamp date, and added an underscore line from the drawn underline.

Receipt photo for notes

Input
Rotated receipt JPG with item names, quantities, amounts, negative discounts in parentheses, and payment lines.
Output
Markdown-style OCR is readable for notes, but a spreadsheet target is safer when quantities and totals need column checks.

A real JPEG → Markdown run

We converted our JPEG sample (97 KB) with AI Deep Read under AI Deep Read on 2026-09-11. It took 2.9 s and produced a 497 B Markdown file, 99% 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.md · 497 B

3 headings, 1 table, 3 list items, 0 code blocks, 0 image references

Headings
3
Tables
1
List items
3
Code blocks
0
Images
0
Lines
14
  • AI Deep Read read 1 page; 1 credit per page

First lines of the output

md
# Feedback Atlas — Q3 activity trail

Prepared for: Board of Directors · 12 Sep 2026

## Headline numbers

| Metric | Q2 | Q3 |
|---|---:|---:|
| ARR | $4.1M | $4.9M |
| Net revenue retention | 108% | 113% |
| Support CSAT | 93% | 94% |
| Refunds | (12,400) | (9,850) |

## What went well

- Enterprise pipeline doubled after the SOC 2 report shipped.
- Support CSAT held at 94% while ticket volume rose 31%.
- Two renewals slipped into October. Owner: VP Sales.
…

Is your file a scan?

JPG is a raster photo, not a document with a hidden text layer. Deep Read charges 1 credit per image and adds Markdown structure from visible cues, but underlines, stamps, and shadows can be interpreted as textual marks.

Options and when to change them

extractTablesAsGfm
Leave this on when the JPG contains receipt rows, lab schedules, or other table-like sections.
preserveLayout
Use it for photographed forms where the location of a value next to a label affects meaning.
languageHint
Set this for short labels, stamps, or bilingual notes that lack enough context for automatic detection.

Do it yourself

Tesseract + Pandoc

bash
tesseract note.jpg stdout --psm 6 > note.txt
pandoc note.txt -t gfm -o note.md

Pandoc can normalize the text file, but it will not know which OCR line should be a heading or a table.

JPEG to Markdown 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=md.

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=md" \
  -F "deepRead=true" \
  --output output.md
API reference

When this is the wrong conversion

  • If the JPG is a simple note and you do not want Markdown markers, use /convert/jpg-to-txt.
  • If the photo contains invoice or receipt rows, /convert/jpg-to-xlsx gives typed numeric cells for the amount columns.
  • If the image should remain visually editable, convert the photo to PNG or crop it before OCR rather than using Markdown.

JPEG to Markdown questions

Why did a line of underscores appear?

The model treated the drawn underline as a text-like separator. Remove that artifact when the underline was just a visual stroke under handwriting.

Can JPG to Markdown keep measurement units?

The inspection sample kept both psi readings with their units. Review decimals and units when the photo is blurry or compressed heavily.

Is Markdown a good target for receipt photos?

Use it for a readable note or reimbursement narrative. Choose XLSX or CSV when the amounts need to land in columns.

Related conversions