MediaPipe Tasks (AI Recognition Demo Hub)
A demo hub that lets you try 15 MediaPipe recognition tasks from a single page. It covers face, hand, and pose detection, gesture recognition, image classification and segmentation, object detection, audio classification, language detection, and text classification. The processing runs inside the browser.
How to try it
Choose an item such as Object Detector, Face Landmarker, or Gesture Recognizer from the list at the top to switch to that demo, then click a sample image or turn on your webcam to see results right away. Webcam-based items need camera permission, and audio classification uses the microphone. Each item downloads its model file on first run, so expect a short wait; the interface is English only.