Read Lines (Kraken lines, vision model)

🤖 AI Drafted (Not reviewed)

Use this when: you want Kraken to find each written line on the page and a vision model to read each line it found (the line reader): Kraken’s own baselines and outlines carry the model’s text, so the result is a line-by-line pass a person can correct and a Kraken reader can be trained on. The vision model is the run’s model (a recipe’s reading step names it). Install the Kraken runtime first (Settings → AI → Local Inference); a cloud model sends each line’s picture to its provider.

Folder	/Transcribe
Steps	2
Tags	preset, transcribe, htr, kraken, line-reader, vision-model

Steps, in run order

1. Files

Tool: Files — Pass through input files from workflow context

2. Kraken lines, read by the vision model

Tool: Transcribe — Extract text from images (OCR)

Settings this step uses:

Option	Value
language	auto
lines_read_by	model
regions_first	no
update_page_content	yes
vision_mode	kraken

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].