ocrhero 0.1.0

OCR Hero CLI — AI-powered OCR for math, science, and technical documents

OCR Hero CLI

AI-powered OCR for math, science, and technical documents — from the command line.

Install

pip install ocrhero

Quick Start

# 1. Get your API key at https://ocrhero.com/developers
# 2. Login
ocrhero login --api-key ocrhero_sk_your_key_here

# 3. Process a single document
ocrhero process -i document.pdf -o output/

# 4. Batch process a folder
ocrhero batch -i ./documents/ -o ./results/

Commands

Command	Description
ocrhero login --api-key KEY	Save your API key
ocrhero logout	Remove saved API key
ocrhero whoami	Check authentication status
ocrhero process -i FILE	Process a single document
ocrhero batch -i DIR	Batch process all files in a folder
ocrhero jobs	List recent processing jobs

Options

# Output as Markdown only
ocrhero batch -i ./documents/ -o ./results/ -f md

# Output as Word document only
ocrhero batch -i ./documents/ -o ./results/ -f docx

# Both Markdown and Word (default)
ocrhero batch -i ./documents/ -o ./results/ -f both

# Merge all results into one file
ocrhero batch -i ./documents/ -o ./results/ --merge

Option	Values	Default	Description
-i, --input	file or directory	required	Input file or folder
-o, --output	directory	. or ./results	Output directory
-f, --format	md, docx, both	both	Output format
--merge	flag	off	Merge all results into one file

Environment Variables

Variable	Description
OCRHERO_API_KEY	API key (overrides saved config)
OCRHERO_API_URL	Custom API URL

Supported Formats

PDF, JPG, JPEG, PNG, BMP, TIFF

Python SDK

from ocrhero.client import OCRHeroClient

client = OCRHeroClient(api_key="ocrhero_sk_...")

# Process and get result
result = client.process_and_wait("document.pdf")
print(result["text"])

# Download DOCX
job = client.process("document.pdf")
client.wait_for_completion(job["job_id"])
client.download_docx(job["job_id"], "output.docx")

Links

• Website: https://ocrhero.com
• Developers: https://ocrhero.com/developers
• Support: [e-mail]