brief introduction

The main functions are input translation, screenshot translation, selected translation、Hover Ball Translation、Screenshot OCR、Screenshot Silence OCR、Clipboard listening translation

Interface

方式	描述	预览
Screenshot translation	Press the screenshot translation shortcut key (default Alt + W) to intercept the area to be translated
Selected translation	After selecting the text to be translated, press the word translation shortcut key (the default is Alt + E)
Input Translation	Press the input translation shortcut key (default 'Alt+Q'), enter the text to be translated, and use the 'Enter' key to translate
Hover Ball Translation	After selecting the text to be translated, click the floating ball icon (it is closed by default, and needs to be opened in the settings by itself)
Screenshot OCR	Pressing this shortcut key will recognize the text according to your screenshot area
Screenshot Silence OCR	Pressing this shortcut key will recognize the text according to your screenshot area, and the recognized content will be automatically written into the clipboard without opening the OCR window

Currently, integrated with translation/text recognition services

Translation source/text recognition application reference

• Translation source

  • TTime (built-in)
  • Google Translation (built-in)
  • DeepL Translation (built-in) = DeepLX Translation
  • Bing Translation (built-in)
  • Bing dict Translation (built-in)
  • Tencent TranSmart Translation (built-in)
  • NiuTrans (built-in)
  • ECDICT Translation-Offline (built-in)
  • Tencent Translator
  • Baidu Translation
  • Alibaba Translation
  • Google Translation
  • OpenAI(ChatGPT) Translation
  • YouDao Translation
  • DeepL Translation
  • Volcano Translation
  • NiuTrans
  • CaiYun Translation
  • Papago Translation

• OCR

  • TTime
  • TTime Online OCR
  • Baidu OCR
  • Baidu Image Translation OCR
  • Volcano OCR
  • Ocr Space
  • Iflytek OCR
  • Tencent OCR
  • Tencent Image Translation OCR

Development Guide

development environment

NodeJs Version >= 16

Npm Version >= 8

Dependent download

npm run npm-i-extend-modules-update

Project Run

npm run dev

Projects Build

npm run build:win
npm run build:win:portable
npm run build:mac

简单快速新增翻译/OCR源

Adding translation/OCR sources is very simple. You only need some JS/TS basics and interface debugging capabilities to integrate. Take Maverick Translation as an example

1.Add Type

Edit file to add a translation source enumeration

src/common/enums/TranslateServiceEnum.ts

Note here: After the source enumeration definition is translated, subsequent file names need to be named according to the enumeration name method. For details, refer to the naming rules in the following steps

static NIU_TRANS = 'NiuTrans'

2.Add Logo

Copy the logo file to this file path

src/renderer/src/assets/translate/NiuTransLogo.png

3.Add Translation/OCR Source Information

Add translation/OCR source information file

src/common/channel/translate/info/NiuTransInfo.ts

4.Add translation/OCR source implementation

Add translation/OCR source interface implementation

src/main/service/channel/interfaces/NiuTransRequest.ts

Add translation/OCR source interface call callback page results

src/main/service/channel/product/translate/NiuTransChannel.ts

Thanks

• Thanks electron-vite The provided electron framework saved me a lot of time and cost
• Thanks Bob Main sources of inspiration
• Thanks bob-plugin-openai-translator Reference for the original implementation of OpenAI
• Thanks eSearch Reference for offline OCR and initial version screenshot implementation