# Manga OCR Translator (`parseforge/manga-ocr-translator`) Actor

Extracts text from manga page images using OCR and translates it into one or more target languages. Returns original text and translations in a flat structured dataset.

- **URL**: https://apify.com/parseforge/manga-ocr-translator.md
- **Developed by:** [ParseForge](https://apify.com/parseforge) (community)
- **Categories:** AI, Developer tools
- **Features:** Limited permissions
- **Stats:** 126 total users, 0 monthly users, 100.0% runs succeeded, 2 bookmarks
- **User rating**: 5.00 out of 5 stars

## Pricing

from $1.00 / 1,000 translation texts

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.
Since this Actor supports Apify Store discounts, the price gets lower the higher subscription plan you have.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For examples already wired to this Actor's own input schema, see the [API](#api) section below.

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).

# README

[![ParseForge](https://raw.githubusercontent.com/ParseForge/apify-assets/main/banner-v4.webp)](https://apify.com/parseforge?fpr=vmoqkp)

### Manga OCR Translator

**Extract and translate text from manga images with AI-powered OCR. Get accurate transcriptions and multi-language translations from any manga page, panel, or raw scan.**

Reading raw manga in Japanese, Korean, or Chinese is slow work when you have to look up every other bubble. Manga OCR Translator reads the text directly from your uploaded page images, runs it through a specialized OCR model tuned for vertical text and stylized fonts, then translates it into one or more languages you choose. No manual typing, no external dictionary tabs.

| Who uses it | What they scrape Manga OCR Translator for |
|---|---|
| Scanlation groups | Generating a rough first-pass translation of raw manga chapters to speed up the typesetting workflow. |
| Language learners | Quickly translating dialogue from manga panels to understand grammar and vocabulary in context. |
| Manga readers | Translating untranslated manga series or newly released raw chapters for personal reading. |
| Content aggregators | Extracting and translating text from manga pages to create searchable metadata or plot summaries. |

### What it does

This Actor accepts manga page image URLs, extracts all visible text regions using OCR, and returns the original text alongside its translations in a flat, structured record.

- **Japanese-first OCR:** The default model is optimized for Japanese vertical text, furigana, and stylized manga fonts.
- **Multi-language translation:** Translate extracted text into up to 16 target languages in a single run, including English, Spanish, French, and Korean.
- **Two-step translation enhancer:** Optionally use Lingo.dev to create a raw English base translation, which Gemini AI then refines with context for higher quality results.
- **Batch image processing:** Feed an array of manga page URLs and process an entire chapter or volume in one go.

Results export to CSV, JSON, Excel, or XML, or straight from the API.

### What you can do with Manga OCR Translator data

**Translate a raw manga chapter.**

A scanlation team uploads the URLs for a full chapter's pages, sets the original language to Japanese and target to English, and receives a complete dialogue transcript to feed into their typesetting tool.

**Read manga in multiple languages.**

A language learner processes a Korean webtoon page with target languages set to English and Spanish, then compares both translations side by side to reinforce vocabulary.

**Extract text for search indexing.**

A manga database site runs the Actor on cover pages and sample panels to extract titles and dialogue, building a text-searchable catalog of series.

**Speed up fan translation workflows.**

A solo fan translator drops a batch of newly released raw pages into the Actor, gets a rough English translation in minutes, and focuses their time on polishing the phrasing instead of dictionary lookups.

### Why choose this scraper

|  | What you get |
|---|---|
| **Original text** | The raw OCR transcription in the source language, preserving the reading order. |
| **Translations** | A map of translations keyed by language code, so you get every target language you requested. |
| **Image source** | The URL of the processed image, so you can trace every result back to its page. |
| **Confidence scores** | OCR confidence levels for each detected text block, helping you spot areas that may need manual review. |

### How it compares

No other Store actor targets Manga OCR Translator the same way, so the honest comparison is with the alternatives teams actually weigh.

| | Manga OCR Translator | Build it in-house | By hand |
|---|---|---|---|
| Setup | Run it now, zero config | Days of engineering | None, but hours per pull |
| When Manga OCR Translator changes | Maintained for you | You fix it | You re-learn the page |
| Proxies, retries, anti-bot | Built in | Your problem | Browser only |
| Output | Fixed JSON schema, CSV/Excel export | Whatever you build | Copy-paste |
| Cost | Pay per result | Engineering time | Analyst hours |

### Configure the run

Drive the Actor with an array of manga page image URLs, set the original language of the text, and choose one or more target languages for translation. The Input tab lists every parameter.

A first run with the defaults:

```json
{
  "imageUrls": [
    "https://api.apify.com/v2/key-value-stores/S8l2sknfAAra9YPZ7/records/Chapter_113_Title_Page.jpg"
  ],
  "originalLanguage": "japanese",
  "targetLanguages": [
    "english",
    "spanish"
  ]
}
```

### Pricing

Pay-per-result: **$0.09 per result** collected. You pay only for the results written to your dataset.

| Results collected | Approximate cost |
|---|---|
| 100 results | $9.00 |
| 1,000 results | $90.00 |
| 10,000 results | $900.00 |

New Apify accounts start with $5 in free credit.

### Free users

Free-plan runs return up to 10 results as a preview. [Upgrade your Apify plan](https://console.apify.com/sign-up?fpr=vmoqkp) to collect up to 1,000,000 results per run.

### Run it

1. [Create a free Apify account with $5 in credit](https://console.apify.com/sign-up?fpr=vmoqkp).
2. Open the [Manga OCR Translator](https://apify.com/parseforge/manga-ocr-translator?fpr=vmoqkp).
3. Set your inputs and any filters, then click **Start**.
4. Export the results as CSV, Excel, JSON, or XML from the **Dataset** tab.

Run it programmatically through the [Apify API](https://docs.apify.com/api/v2) (`run-sync-get-dataset-items`) or the [ApifyClient](https://docs.apify.com/api/client/js) for JavaScript and Python.

### Use with AI agents (MCP)

Give an AI agent live access to Manga OCR Translator through the Model Context Protocol. Add the Actor to Claude, Cursor, or any MCP client:

```bash
claude mcp add --transport http apify "https://mcp.apify.com?tools=parseforge/manga-ocr-translator"
```

Then prompt it in plain language to run the scraper and read back the results.

### Troubleshooting

**The OCR is returning garbled or incorrect characters for my Japanese manga.**

Make sure the 'Original Language' input is set to 'japanese'. If it is set to a different language, the OCR engine will use the wrong character set and produce nonsense text.

**Why are some speech bubbles missing from the output?**

Check the image quality. Low-resolution images, heavy JPEG compression, or text that blends into dark backgrounds can cause the OCR to miss regions. Use the highest resolution source images available.

**The translation sounds unnatural or misses the context.**

Try enabling the 'Lingo.dev Translation Enhancer' option. This provides a base translation that the AI can refine, which often helps with idiomatic expressions and character-specific speech patterns.

**I'm getting a timeout error when processing many large images.**

Split your image array into smaller batches and run the Actor multiple times. Processing 10 to 20 pages per run is a good starting point for high-resolution files.

### FAQ

| Question | Answer |
|---|---|
| What image formats are supported? | The Actor accepts JPG, PNG, and WebP image formats. Upload your manga pages as direct URLs to any of these file types. |
| Which languages can it translate from and to? | It can read text in Japanese, English, Korean, Russian, Chinese (Simplified and Traditional), Spanish, French, German, Italian, Portuguese, Thai, Vietnamese, Indonesian, Arabic, and Hindi. You can translate into any of these same languages. |
| Does it handle vertical Japanese text correctly? | Yes, the OCR model is specifically tuned for vertical text layout, which is the standard in most manga. It reads right-to-left columns and preserves the correct word order. |
| What does the Lingo.dev Translation Enhancer do? | When enabled, it adds a two-step translation process. First, Lingo.dev produces a raw English translation. Then, Gemini AI takes that English text and the original context to create refined translations in all your target languages. This often improves accuracy for nuanced dialogue. |
| Can I translate into more than one language at a time? | Yes, you can select multiple target languages in a single run. The output will include a translation for every language you chose. |
| Is there a limit on how many images I can process? | There is no hard limit on the number of image URLs you can submit. Processing time scales with the number of images and the text density on each page. |
| Does it work on handwritten text or sound effects? | The OCR model is trained primarily on printed manga fonts. Highly stylized sound effects or handwritten scribbles may produce lower confidence results, but standard dialogue and narration boxes are handled well. |
| What output format does the Actor produce? | The Actor returns a structured dataset that you can export as JSON, CSV, Excel, or XML. Each row corresponds to one processed image and contains the original text and all requested translations. |

### Related actors

Browse the full [ParseForge collection](https://apify.com/parseforge?fpr=vmoqkp) for more scrapers.

🆘 **Need help?** Email parseforge@protonmail.com with your run ID, your input, and what you expected.

⚠️ **Disclaimer.** This Actor is unofficial and is not affiliated with, endorsed by, or sponsored by Manga OCR Translator. It collects only publicly available data. You are responsible for using the collected data in compliance with the source's terms of service and applicable data-protection laws, including GDPR, CCPA, and PIPL. Do not use it to collect personal data unlawfully.

# Actor input Schema

## `imageUrls` (type: `array`):

Array of manga image URLs to process. Each image will be analyzed to extract text regions. Supported formats: JPG, PNG, WebP.

## `originalLanguage` (type: `string`):

The language of the text in the manga images. This helps OCR accuracy by using the appropriate language model.

## `targetLanguages` (type: `array`):

Select one or more target languages for translation. The text will be translated to all selected languages.

## `enableLingoTranslationEnhancer` (type: `boolean`):

If enabled, uses a two-step translation process: first translates to English using Lingo.dev (raw translation without context), then refines and translates to multiple languages using Gemini AI (with context and Lingo translations). This can improve translation quality by providing a base translation that Gemini can refine. If disabled, only Gemini AI will be used for translation.

## Actor input object example

```json
{
  "imageUrls": [
    "https://api.apify.com/v2/key-value-stores/S8l2sknfAAra9YPZ7/records/Chapter_113_Title_Page.jpg"
  ],
  "originalLanguage": "japanese",
  "targetLanguages": [
    "english",
    "spanish"
  ],
  "enableLingoTranslationEnhancer": false
}
```

# Actor output Schema

## `overview` (type: `string`):

No description

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "imageUrls": [
        "https://api.apify.com/v2/key-value-stores/S8l2sknfAAra9YPZ7/records/Chapter_113_Title_Page.jpg"
    ],
    "originalLanguage": "japanese",
    "targetLanguages": [
        "english",
        "spanish"
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("parseforge/manga-ocr-translator").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = {
    "imageUrls": ["https://api.apify.com/v2/key-value-stores/S8l2sknfAAra9YPZ7/records/Chapter_113_Title_Page.jpg"],
    "originalLanguage": "japanese",
    "targetLanguages": [
        "english",
        "spanish",
    ],
}

# Run the Actor and wait for it to finish
run = client.actor("parseforge/manga-ocr-translator").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{
  "imageUrls": [
    "https://api.apify.com/v2/key-value-stores/S8l2sknfAAra9YPZ7/records/Chapter_113_Title_Page.jpg"
  ],
  "originalLanguage": "japanese",
  "targetLanguages": [
    "english",
    "spanish"
  ]
}' |
apify call parseforge/manga-ocr-translator --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,parseforge/manga-ocr-translator"
        }
    }
}
```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/vDEVaJFKkvwJxDu6t/builds/paqsiQ7qYms4WYLzn/openapi.json