Frequently Asked Questions
Quick answers to common questions about Playto.
Translation & OCR
OCR accuracy is poor — text is garbled or missed
OCR works best when the text is clear and high-contrast. Try these fixes:
- Use Borderless Windowed mode instead of Fullscreen. This gives Playto cleaner screen captures.
- Draw the capture region tightly around the text area — avoid including game graphics.
- If the font is stylized or decorative, try Vision Mode (VLM) instead — it reads the screen as an image and handles stylized text much better.
- Make sure the game is running at your monitor's native resolution.
Translation is slow or laggy
Translation speed depends on your AI model and hardware. Try these:
- Check GPU Layers in Settings > Model. Make sure the model is offloaded to your GPU. More GPU layers = faster inference.
- Try a smaller model (e.g., 7B instead of 13B parameters). Smaller models are faster with only a slight quality trade-off.
- Use API mode if you have a weak GPU. Cloud APIs (OpenAI, etc.) are fast and don't use local resources.
- Close other GPU-heavy applications. Your game and the AI model share VRAM.
Playto is translating its own window / other apps
Playto has a window detection feature that should prevent this. If it's happening:
- Make sure your game window is focused (active) when Playto captures.
- Check your Game Pack settings — the process name should match your game's executable.
- The overlay window itself is excluded from captures automatically.
Performance & Hardware
Out of VRAM / model won't load
Your game and the AI model share your GPU's VRAM. If you're running out:
- Use a smaller model. A 7B model needs ~4GB VRAM. A 3B model needs ~2GB.
- Reduce GPU layers. Partial offloading uses less VRAM (the rest runs on CPU, slower but works).
- Switch to API mode. Cloud APIs use zero local VRAM.
- Lower your game's graphics settings to free up VRAM.
Can I use Playto without an NVIDIA GPU?
Local AI works best with NVIDIA (CUDA) but also supports AMD and Intel GPUs via Vulkan. CPU-only mode is available but slower. API mode requires no GPU at all — use cloud providers (OpenAI, etc.) for fast translations on any hardware.
Audio & Speech
Text-to-Speech has no audio / wrong voice
TTS availability depends on the language pair. Check:
- Make sure TTS is enabled in Settings > Audio.
- Confirm your target language has TTS support. Most major languages are supported.
- Check your system audio output — make sure it's not muted or routed to the wrong device.
Pronunciation test isn't working
Pronunciation uses a local Whisper model for speech recognition:
- The Whisper model downloads automatically on first use (~140MB). Make sure the download completed.
- Check that your microphone is connected and has permission in Windows settings.
- Pronunciation runs on CPU only (to avoid GPU contention with your game), so it may take a moment to process.
General
What's the difference between Free and Paid?
The Free version includes OCR translation, achievements, daily quests, and read-only game packs. The Paid version ($9.99 one-time on Steam) unlocks all features: Vision Mode, Cursor Translation, 8 Quiz Modes, Text-to-Speech, Dictionary, Overlay Cloze, CEFR Highlighting, Pronunciation Test, Journal & Share Cards, and full Game Pack editing. See the pricing table for the full comparison.
Does Playto send my data anywhere?
No. When using local AI (Ollama), everything runs on your PC. Your vocabulary, translations, and learning data are stored locally. The only exception is if you choose API mode — in that case, text is sent to your chosen cloud provider (OpenAI, etc.) for translation, but your learning data still stays local.
Which games work with Playto?
Any PC game. Playto works by reading your screen, so it's compatible with any game that displays text — JRPGs, Visual Novels, Strategy games, MMOs, and more. No game modification or modding is required.