Jester — Hand Gesture Video Control

Control YouTube, Netflix and more with hand gestures, an eye/head cursor and your voice. Camera and audio stay on your device.

Jester lets you control YouTube, Netflix and other streaming sites without touching your keyboard or mouse. Hold up a hand to pause or play from across the room, steer a cursor with your eyes or head, or just say what you want to watch. Camera tracking and speech recognition run on your device. Main features: • Hand gestures: a closed fist pauses, an open palm plays, a peace sign mutes, thumbs up or down change the volume, and swipes seek. You can rebind every gesture. • Voice commands: point one finger up or press Alt+Shift+J, then say "play season 3 episode 1", "next episode" or "switch to the recipe tab". Jester works through the site step by step and asks before anything sensitive. • Eye and head cursor: steer by turning your head, with no calibration, or with your eyes after a short calibration. Close your hand to click. • Your choice of AI: voice tasks use the model you pick, with your own API key: Google Gemini (which has a free tier), OpenAI, Anthropic Claude, Groq or any OpenAI-compatible endpoint. Simple tab commands work without one. • Private by design: video and audio never leave your computer, and there are no Jester servers, analytics or ads. Voice tasks share only what the task needs, such as your command and a summary of the page, and only with the AI provider you chose. Works on YouTube, Netflix, Disney+, Hulu, Prime Video and other major streaming sites. Gestures and the cursor need a webcam, and voice needs Chrome's on-device speech recognition for your language. AI providers may charge for API use. Jester is not affiliated with YouTube, Netflix or any other streaming service.