Handwriting

🤖 AI Drafted (Not reviewed)

Historical handwriting transcription

Tool id	handwriting
Category	vision
Uses a language model	yes
Needs a generative model	no
Runs over many items	yes
Item handling	batch
Structured output	yes
Human-verified	not yet

What it reads

Port	Type	Required	What it is
Files (files)	files	yes	Image files
Context (context)	any	no	Previous text/transcription
Metadata (metadata)	json	no	Existing metadata
Documents (documents)	json	no	Document metadata

What it emits

Port	Type	Required	What it is
Text (text)	text	—	Raw text response
Value (value)	any	—	Parsed value
Texts (texts)	array	—	Per-item texts
Values (values)	array	—	Per-item values
Results (results)	json	—	Full results
Records (records)	array	—	Per-document text records [{doc_id, text}, …].
Artifacts (artifacts)	json	—	Artifact IDs

Options

Option	Type	Default	What it does
choices	array	—	Valid choices. (Not shown in the editor.)
chunk_size_chars	integer	0	Chunk large input text above this character budget (0=auto).
era	string	unknown	Historical era. One of: medieval, renaissance, colonial, 18th_century, 19th_century, early_20th_century, modern, unknown.
force_ocr	boolean	no	Force image processing instead of existing text.
handle_diacritics	boolean	yes	Preserve diacritics.
language	string	auto	Document language.
match_mode	string	prefer	Match mode. One of: prefer, strict, inform.
max_image_dimension	integer	8192	Max image size.
max_items	integer	10	List max items.
max_tokens	integer	8192	Max response.
max_words	integer	50	Word limit.
metadata_field	string	—	Save to field.
model_name	string	—	Model name.
output_format	string	text	Response format. One of: text, boolean, choice, number, words, list, json.
prompt	string	—	Custom prompt.
provider_name	string	—	LLM provider. One of: openai, anthropic, google, ollama, lmstudio, groq, together, deepseek, mistral, openrouter, dashscope, xai, perplexity, fireworks, deepl.
quality_gate	boolean	yes	Stop the run if output is unreadable.
reference_values	object	—	Known values to match. (Not shown in the editor.)
save_to_db	boolean	yes	Save to library.
save_to_file	boolean	no	Export to file.
script	string	unknown	Script type. One of: latin_modern, latin_colonial, latin_medieval, secretary_hand, copperplate, gothic, arabic, hebrew, cyrillic, cjk, devanagari, greek, mixed, unknown.
temperature	number	0.7	Creativity.
thinking_mode	string	off	Chain-of-thought reasoning depth. One of: off, short, medium, long.
vision_mode	string	auto	Vision engine. ‘auto’ picks based on the resolved provider: apple → Apple Vision OCR; anything else → LLM vision path. One of: auto, apple, llm. (Not shown in the editor.)

The prompt it sends

This is what the tool asks a model, with every option left at its default. Changing the options above changes this text.

Transcribe this historical handwritten document.

Identify the script type and adapt your reading accordingly.






DIACRITICS AND SPECIAL CHARACTERS:
- Preserve ALL diacritical marks exactly as written (accents, tildes, cedillas, umlauts, etc.)
- Distinguish between decorative flourishes and meaningful diacritics
- If a diacritic is ambiguous, include it with a note [?]
- Use proper Unicode characters for special marks
- Common marks: acute (á), grave (à), circumflex (â), tilde (ñ/ã), umlaut (ü), cedilla (ç)



DAMAGED OR UNCLEAR TEXT:
- Use [...] for completely illegible passages
- Use [word?] for uncertain readings
- Use [---] for deliberately struck-through text
- Note torn, stained, or faded areas that affect readability

TRANSCRIPTION RULES:
- Transcribe exactly what is written, preserving original spelling
- Maintain line breaks where clearly intended
- Preserve capitalization as written
- Include marginalia or interlinear additions in {curly braces}
- Note any page numbers, folio markers, or archival references

Output the transcription as plain text, preserving the document structure.