🎮 RSTGameTranslation

Prerequisites:

1. Download the latest version (zip file) here and extract it.

Setup Options:

🔵 Simple Setup (No Installation)

1. Run `rst.exe`
2. Go to Settings → OCR: Select OneOCR
3. Go to Settings → Language: Choose source and target languages
4. On Language tab, If you are using Windows OCR, please click the "Check" button to verify the language pack before starting
5. Go to the Translation tab, select the translation service you want to use
6. Now you can close the settings window
7. Press button Select Window: Choose window which you want to capture
8. Press Alt+Q to select area, then Alt+F to turn on Overlay
9. Press Alt+G to start/stop

🔴 Advanced Setup (Need Installation)

1. Server Setup (Only do once for each OCR method):
   • Click the SetupOCR button to start setting up the server based on the OCR method you selected in settings (If you selected Windows OCR, you can skip this step)
   • Setup can take 5-15 minutes, depending on your internet speed and computer power
   • Wait until the server setup is complete, you will see a message "... environment setup completed"
2. Start Translating:
   • Click the StartOCR button and wait until you see the message "Successfully connected to .... server" (If you selected Windows OCR, you can skip this step)
   • Select translate region (ALT+Q or Click SelectArea button)
   • Click Start button (ALT+G) to begin translation
   • Translation results are displayed in the chat window (ChatBox button, ALT+C) or in the Overlay (Overlay button, ALT+F)
3. LLM Setup:
   • Go to settings and add your Gemini API key. There are instructions on how to get the API key there.
   • You can enter multiple API keys, press Enter after entering each API key.
   • Check the other settings; the default values should be fine. Note that there is a place to enter the name of the game, which is important! The LLM knowing this will help it fix errors and create better dialogue.

Note: The first time you use EasyOCR or PaddleOCR with a new language, it has to download first! So it might seem like it's not working, just wait a minute or two and start/stop the application's translation, it will work.

Detailed descriptions and quick usage notes for each settings group (from Setting Window):

Language

• Source / Target language: choose language codes (e.g. ja, en, vi). Swap with the ⇄ button.
• Windows OCR language pack: click Check to verify/install required language when using Windows OCR.

OCR & Screen

• OCR Method: pick EasyOCR, Windows OCR, PaddleOCR, RapidOCR or OneOCR. Non-built-in engines may require server setup.
• Select Screen: choose which display to capture if multiple monitors are connected.
• Auto OCR: enable realtime auto-capture; disable to manually run OCR.
• HDR support: enable if your game uses HDR (may affect detection).
• Remove OCR Data: deletes downloaded OCR model/data for external engines if you need to reclaim space.

OCR Settings

• Block detection power & settle time: tune how text blocks are grouped and how long to wait for text to settle before capture.
• Text similarity threshold: skip near-duplicate captures (0.5–1.0). Lower = stricter deduplication.
• Char-level OCR: enable to split results into characters (useful for tightly spaced text).
• Minimum fragment / letter / line confidence: filter noisy OCR output by confidence scores.
• Multi-selection area: allow selecting multiple translation regions (useful for HUD + chat simultaneously).

Translation Context & Overlay

• Max/Min context pieces and size: control how much previous text is sent as context to the LLM for better continuity.
• Game info: enter brief game description to help LLM produce context-aware translations.
• Overlay config & auto background: adjust overlay colors and enable automatic background selection.
• Leave translation onscreen: keep translated text visible instead of showing source text.

Ignore Phrases

• Add phrases to be ignored or stripped from OCR results. Toggle Exact Match to ignore whole texts or remove occurrences.

Translation Service (LLMs)

• Select service (Gemini, Groq, ChatGPT, Ollama, LM Studio, Google Translate, Custom API).
• API keys: enter keys in the password fields and press Enter (or use Save Keys). Multiple keys supported for failover.
• Model selection: choose service-specific models. Use View Models links to open docs.
• Prompt editor: customize the prompt template per-service, Save / Restore Default are available.

Text-to-Speech (TTS)

• Enable TTS and pick service: ElevenLabs, Google Cloud TTS or Windows TTS.
• Provide API keys for cloud services; choose voice from the list (system voices are auto-detected).
• Exclude character names: toggle to avoid speaking character names in TTS output.

Audio Processing

• Auto-translate audio: starts/stops local Whisper service for live speech-to-text translation.
• Model selection: choose a local audio model (ggml .bin); use the download link if missing.
• Silence threshold/duration and max buffer samples: tune detection sensitivity for audio capture.

Server Controls

• Install / Start / Remove server: runs bundled batch scripts to setup or control OCR backends that require a server.
• Send data to server: toggle whether OCR/diagnostic data may be posted to a remote server (used by some engines).

Game Profiles

• Create, update, load and remove named profiles that store translation area rectangles and related settings per game.

Tip: when changing OCR engine, model or translation service, use Clear Context and Reset Hash (app will do this automatically) to force fresh OCR & translations.

What languages can RSTGameTranslation translate?

The software can translate most languages, but it's primarily tested with Japanese to English and English to Vietnamese translations.

I don't have an NVIDIA GPU, can I still use it?

Yes, but performance will be much lower as it will use CPU (30-50% capacity). You can try using Windows OCR for lighter performance.

Can I use RSTGameTranslation without an internet connection?

Yes, you can use Ollama or LM Studio to run 100% offline. You'll need to download the LLM models to your machine first.

How do I get a Gemini API key?

You can sign up for a free Gemini API key at Google AI Studio. After logging in, you can create an API key in the settings section.

Join our Discord community for support, discussions, and updates: