Hold a key, ask anything about what you see. ScreenSense understands your screen and responds with AI-powered explanations — by voice, text, or both.
No tab switching, no copy-pasting, no context loss. Just hold, ask, and understand.
Press and hold the shortcut key anywhere on any webpage. A waveform appears — you're live.
Speak your question naturally. "What does this function do?" "Summarize this page." "Explain this error."
AI sees your screen, understands context, and responds instantly — streaming text, a spoken summary, or both.
Watch how to install, configure, and start talking to your screen.
Powerful when you need it, invisible when you don't.
Captures a screenshot the moment you ask. The AI sees exactly what you see — no need to describe or copy anything.
Hold a key, speak naturally. Powered by Whisper for accurate transcription and streaming responses in real-time.
Choose text + audio, audio only, or text only. Audio mode delivers a concise 3-second spoken summary while text gives the full detail.
Tailor responses to your audience — from explaining like you're 5 to briefing a CTO. Five levels from Kid to Executive.
Ask "What is an API?" and watch the answer adapt to who's asking.
Install ScreenSense Voice for free. Works on every website, takes 30 seconds to set up.
Clone from GitHubClone the repo, run npm install && npm run build, then load the dist/ folder into chrome://extensions with Developer Mode enabled. Follow the README setup guide for detailed steps.