Translate
🤖 AI Drafted (Not reviewed)
Transcribe each file (reusing any existing text layer), then translate the extracted text into your preferred language using an LLM. Target language, source language, model, and prompt are all editable on the Translate node. The LLM node uses the $small model alias — set your default small model in Settings → AI Defaults.
| Folder | /Translate |
| Steps | 3 |
| Tags | preset, translate, text, language, small |
Steps, in run order
1. Files
Tool: Files — Pass through input files from workflow context
2. Transcribe each file
Tool: Transcribe — Extract text from images (OCR)
Settings this step uses:
| Option | Value |
|---|---|
language |
auto |
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].
3. Translate Text
Tool: Translate Text — Translate extracted or transcribed text into the user’s preferred language. Target language, source language, and model are all editable on the node.
Settings this step uses:
| Option | Value |
|---|---|
preserve_names |
yes |
provider_name |
$small |
source_language |
auto |
target_language |
English |
What this step asks the model:
Translate the following text into English.
Rules:
- Produce a faithful, accurate translation into English. Convey the full meaning of the source — do NOT summarize, omit, paraphrase away, or add information.
- Preserve the document structure: keep paragraph breaks, lists, and line layout.
- Keep proper names, place names, institutions, and archival citations in their original form — do not anglicise or translate them.
- If a passage is illegible or marked [ilegible] / [uncertain], carry the marker across unchanged and do not replace it with a guess.
- Output ONLY the English translation, with no preamble, notes, or the original text.
- Return PLAIN TEXT: no markdown formatting, no trailing spaces on lines, and no added blank lines beyond the original paragraph breaks.