What is the benefit of the Batch API integration?

By using the Gemini Batch API instead of real-time requests, this skill provides a 50% cost reduction for large-scale book processing jobs.

Does it preserve original formatting and metadata?

Yes, it uses a standardized Markdown format with specific tags for marginalia, page numbers, printer's marks, and technical vocabulary.

What model does this skill use for OCR and translation?

The skill specifically utilizes gemini-3-flash-preview to ensure the highest accuracy for vision tasks and cost-efficiency through the Gemini Batch API.

How does the skill handle two-page spreads in scans?

It includes a dedicated 'generate_cropped_images' step that detects split pages and extracts individual page images before the OCR process begins.

Batch Book Translation & OCR

Name: Batch Book Translation & OCR
Author: Embassy-of-the-Free-Mind

byEmbassy-of-the-Free-Mind

内容管理

Processes historical book scans through an end-to-end pipeline of image cropping, vision-based OCR, and contextual translation.

关于

This skill automates the complex workflow of digitizing and translating historical volumes. It manages a multi-stage pipeline that first splits two-page spreads into individual images, performs high-accuracy OCR using Gemini vision models, and finally translates the text while maintaining context across page breaks. Designed for scholarly and archival projects, it leverages the Gemini Batch API to reduce costs by 50% while producing semantically tagged Markdown output that preserves the structure and metadata of the original work.

主要功能

Cost-optimized processing via Gemini Batch API integration
High-accuracy OCR for historical fonts using Gemini vision
Semantic Markdown formatting with specialized archival metadata tags
Automated image cropping for split two-page spreads
Context-aware translation that maintains continuity between pages
0 GitHub stars

使用场景

Creating searchable, multi-lingual digital editions of rare primary sources
Digitizing and translating large volumes of historical Latin encyclopedias
Automating the extraction of structured text from scanned archival book spreads

关于

主要功能

Cost-optimized processing via Gemini Batch API integration
High-accuracy OCR for historical fonts using Gemini vision
Semantic Markdown formatting with specialized archival metadata tags
Automated image cropping for split two-page spreads
Context-aware translation that maintains continuity between pages
0 GitHub stars

使用场景

Creating searchable, multi-lingual digital editions of rare primary sources
Digitizing and translating large volumes of historical Latin encyclopedias
Automating the extraction of structured text from scanned archival book spreads