# ramjke/Translumo

Advanced real-time screen translator for games, hardcoded subtitles in videos, static text and etc.

Repository: https://github.com/ramjke/Translumo
Canonical: https://ross.abutalabs.com/products/translumo
Language: C#
License: Apache-2.0
License Family: permissive
Topics: easyocr, game-translation, mlnet, ocr, translation, autotranslate
Last push: 2026-06-14T06:38:55+00:00

## Health v2 (maintenance only)
Score: 72/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 87, release rhythm 47, longevity 83
- inputs: {"age_days": 1174, "days_push": 80, "days_rel": 352, "gap_med": 0.5, "n_releases_24m": 3}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5697, forks 351 (observed 2026-08-28T04:09:28.030100+00:00)

## What it is
Translumo is a Windows desktop application that performs real-time screen translation by capturing on-screen text with OCR and translating it. It combines multiple OCR engines (Windows OCR, Tesseract, EasyOCR) with an ML model that scores results to maximize recognition accuracy, targeting games and hardcoded video subtitles.

## Use cases
- translate hardcoded subtitles in videos in real time
- translate in-game dialogue text while playing PC games
- capture and translate static text anywhere on the screen
- combine multiple OCR engines for higher recognition accuracy
- translate Japanese or Chinese game text to English

## When to choose
- you need real-time OCR translation of text that cannot be copied, like games or burned-in subtitles
- you want to combine several OCR engines and let an ML model pick the best result
- you are on Windows and want a ready-to-run desktop tool with no setup

## When to avoid
- you need OCR on Linux or macOS, as it is Windows-only
- you need to translate languages outside its supported recognition set (English, Russian, Japanese, Chinese, Korean)
- you want a library or API to embed OCR into your own application rather than a standalone app

## Facets
- artifact type: application
- maturity: active
- function: ocr, internationalization, machine-learning, image-processing
- domain: gaming-tools, desktop-applications
- platform: windows, dotnet
- tags: screen-translation, real-time-ocr, game-translation, hardcoded-subtitles, easyocr, tesseract, deepl, natural-language-processing, localization, desktop

## Member repositories
- ramjke/Translumo (main) score 72

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:28.030100+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:53:37.646565+00:00, confidence not recorded.
  - readme: https://github.com/ramjke/Translumo (fetched 2026-08-28T04:09:28.030100+00:00, sha f2fa437f929c)
- Data as of 2026-08-30T08:39:29.467469+00:00.