Translate your games in real-time with AI-powered OCR and LLM technology
📥 Download • ⚙️ Settings guide • 📖 Vietnamese Guide • 🐛 Report Bug
- Real-time Translation with multiple OCR options (OneOCR, Windows OCR, PaddleOCR, EasyOCR, RapidOCR)
- AI-Powered Translation with Gemini, Groq, ChatGPT, Google Translate, Ollama, Mistral, LM Studio
- Smart Recognition with game context awareness and character name detection
- Flexible Display options with overlay and chat window
- Text-to-Speech feature (text reading)
- Speech-to-Text functionality (Recognize speech from game audio and translate it)
- Windows 10+ and game in windowed/borderless mode
- NVIDIA GPU recommended but optional
- Download from Releases and extract
- Run
rst.exe - Go to Settings → OCR: Select OneOCR
- Go to Settings → Language: Choose languages
- Go to Settings → Translation: Select Google Translate
- Press button Select Window: Choose window which you want to capture
- Press Alt+Q to select area, then Alt+F to turn on Overlay
- Press Alt+G to start/stop
-
OCR Options: (Setup is only needed the first time the new OCR is chosen, no need to reinstall.)
- Built-in: OneOCR, Windows OCR (no setup needed)
- External: Click SetupOCR for PaddleOCR, RapidOCR, EasyOCR (5-15 min wait)
-
Translation Services:
- No API needed: Google Translate
- API required: Gemini, Groq, Mistral, ChatGPT (add keys in Settings)
- Local options: Ollama, LM Studio
-
Start translating:
- Click StartOCR (if using external OCR) and wait until it starts successfully (You will see a red notification line at the bottom right corner)
- Press button Select Window: Choose window which you want to capture
- Select area (Alt+Q) then turn on overlay (Alt+F)
- Start translate (Alt+G)
RSTGameTranslation will automatically check for updates when you start it. If there's a new version, you'll see a notification asking if you want to download it. To update:
- Download the latest version from the notification or from Releases
- Close RSTGameTranslation if it's running
- Extract the new files to your current installation folder
- Done! Your settings and options will be preserved
- OCR: OneOCR or Windows OCR (built-in, no setup)
- Translation: Google Translate (no API key needed)
- OCR: PaddleOCR (Asian) or RapidOCR (Western) or EasyOCR
- Translation: Gemini Flash lite 2.5 (Need API key)
- Hardware: NVIDIA GPU recommended
- OCR: OneOCR or Windows OCR
- Translation: Ollama or LM Studio (100% local)
- Smaller areas = faster processing
- Add multiple API keys for failover
- First language download takes 1-2 minutes (external OCR)
Join our Discord for support and updates!
If you find RST useful and would like to support development, you can buy the author a coffee — thank you! 👋
This project stands on the shoulders of giants. We gratefully acknowledge the following open-source projects:
- WPF (Windows Presentation Foundation) - UI Framework
- PaddleOCR - Awesome multilingual OCR toolkits
- EasyOCR - Ready-to-use OCR with 80+ supported languages
- RapidOCR - Cross platform OCR library based on OnnxRuntime
- SocketIOClient - Socket.IO client for .NET
- System.Text.Json - High-performance JSON serialization
- Hugging Face - For various AI models and datasets
- NAudio - Audio and MIDI library for .NET
- System.Speech - .NET Speech Synthesis Library
- Whisper.Net - .NET Speech To Text Library
BSD-style attribution - see LICENSE.md
Acknowledgments: Includes software developed by Seth A. Robinson - UGTLive
 |
Free code signing provided by SignPath.io, certificate by SignPath Foundation. |
|---|
Made with ❤️ for the gaming community
⭐ Star this project if you find it helpful!
