[Release/Web-App] EbookCC: AI-Powered Comic Translation & Batch Processing Tool

[kollo]

Hi everyone,

I’d like to share a new tool I’ve been working on called EbookCC, designed for comic enthusiasts and translators who want to streamline their editing workflow. It’s a web-based application that leverages the latest AI (Google Gemini) to detect, OCR, and translate speech bubbles in batch.

What is EbookCC?
EbookCC is an open-source (or free-to-use) web application that automates the tedious parts of comic editing. Instead of manually cleaning bubbles and re-typing text, EbookCC uses AI to "see" the comic panels and handle the heavy lifting.

Key Features:

Batch Processing: Drag and drop an entire folder of images, or your .ZIP / .CBZ comic files, and the app will queue them for processing.

AI-Powered OCR: Powered by the gemini-2.0-flash-lite model, it features incredibly accurate text detection even in stylized comic fonts.

Automatic Cleaning: The app attempts to detect bubble boundaries and can provide "cleaned" versions of the pages.

Built-in Translation: Support for over 100 languages. You can batch-translate an entire volume with one click.

Text Overlays: View the translated or OCR’ed text directly over the original comic page using selectable overlays.

Privacy-Focused: The app runs in your browser. While it uses the Gemini API for analysis, your files are processed locally in your session.

How it works:

Upload: Drop your comic pages (ZIP/CBZ/JPG/PNG) into the dashboard.

Analyze: The AI scans for text bubbles and panels.

Translate/Edit: Select your target language and refine the detected text in the built-in editor.

Export: Export your findings as a text file or use the snapshots for further editing.

Why use it?
If you’ve ever tried to translate a manga or digital comic manually, you know how much time goes into "redrawing" and re-typesetting. EbookCC aims to reduce that time significantly by providing a smart starting point.

Get Started:
You can try the demo here: https://ebookcc.cptd.workers.dev/

Note: The app includes a generous free tier via Gemini's API (up to 1,500 requests per day), but you can also plug in your own API key in the settings for higher throughput.

I'd love to hear your feedback or feature requests!

[GigaCat]

This looks promising. But I figured that people might not be comfortable inserting their API key since the app is not local. Is this app's code open-sourced? That would certainly help a lot.

Alternatively, you can charge them according to requests. Like most other apps.

[kollo]

Originally Posted by GigaCat

This looks promising. But I figured that people might not be comfortable inserting their API key since the app is not local. Is this app's code open-sourced? That would certainly help a lot.

Alternatively, you can charge them according to requests. Like most other apps.

Thanks for the feedback, GigaCat! I totally understand the security concerns regarding API keys.

Security: To address this, the app is designed so that your API key is only stored in your browser's local storage and is sent directly to the AI provider via encrypted HTTPS. It never touches our servers.

Open Source: Yes, transparency is key! I am currently adding a new feature to create comic panel collages and cleaning up the codebase. I plan to host it on GitHub very soon so everyone can audit the code or host it locally.

Local Processing: I am also looking into supporting local models (like Gemma/Ollama) in the future to keep everything 100% offline.

Stay tuned for the repo link!