Skip to content

Capture OCR + Transcribe

🤖 AI Drafted (Not reviewed)

Use this when: you want a capture-oriented OCR preset for newly photographed pages or uploaded PDFs. It prepares pages into OCR-ready images, enhances those derived images, then transcribes back onto the original selected documents so page text, artifacts, and provenance stay attached to the source record instead of the temporary derivatives.

Folder /Transcribe
Steps 4
Tags preset, transcribe, ocr, capture, images, pdf

Steps, in run order

1. Files

Tool: Files — Pass through input files from workflow context

2. Prepare Images for OCR

Tool: Prepare Images — Normalize images/PDF pages for OCR without modifying source files.

Settings this step uses:

Option Value
autocontrast yes
compression_quality 85
grayscale yes
output_format jpg
pdf_dpi 300

3. Enhance Images

Tool: Enhance Images — Create contrast/sharpness/denoise image derivatives without modifying source files.

Settings this step uses:

Option Value
compression_quality 90
contrast 1.25
denoise yes
output_format jpg
sharpness 1.1

4. Transcribe Capture

Tool: Transcribe — Extract text from images (OCR)

Settings this step uses:

Option Value
language auto
save_to_db yes
update_page_content yes
vision_mode auto

What this step asks the model:

Transcribe the text visible on this image.

Language: transcribe in the language of the source. Do not translate, and do not assume the document is in English.

Rules:
- Output ONLY the transcription. No headings, no preamble, no commentary,
  no summary, no notes, no explanations, no observations about quality or
  legibility, no descriptions of seals or images, no language about the
  difficulty of the handwriting.
- Preserve original layout, line breaks, and paragraph structure.
- Preserve original spelling and capitalisation, including ALL CAPS
  headers if they appear that way.
- Preserve orthography exactly as written, including all diacritics
  and accent marks (e.g., keep "Chocó" as "Chocó", never "Choco";
  keep "Ramón" as "Ramón", never "Ramon").
- Do not strip accents, tildes, cedillas, or umlauts. If a mark is
  visible, keep it.
- Include every visible text element — headers, body, marginalia, stamps,
  signatures (transcribe the signed name as written), printed labels,
  handwritten annotations.
- For text you cannot confidently read, use explicit uncertainty markers:
  [ilegible] for unreadable text and [uncertain] for plausible-but-low-
  confidence readings. Place the marker inline at the uncertain span.
  Do not guess. Do not fill in.
- Do NOT invent dates, numbers, names, or words that are not legibly
  present. Do not normalise dates ("23/7/1999" stays "23/7/1999", not
  "1999-07-23").
- Do NOT repeat any portion of the transcription. Output each visible
  passage exactly once.
- If the image contains no legible text, output the single token
  [sin texto].