[{"data":1,"prerenderedAt":12},["ShallowReactive",2],{"stack-tr-en-mediapipe":3},{"tagline":4,"description":5,"strengths":6,"useCase":11},"Google's on-device ML solutions: hands, pose, face and gestures in real time.","MediaPipe ships ready-made tasks that run entirely on the device: hand, pose and face detection with landmarks, gesture recognition, image segmentation, and an LLM Inference API to run a compact language model locally. The same Tasks API is available in Kotlin on Android, Swift on iOS, JavaScript on the web and Python, with Model Maker to adapt a model to your own data. It's our choice when an app has to understand the user's body or face in real time without sending video to a server.",[7,8,9,10],"Real-time hand, pose and face landmarks with on-device GPU acceleration.","One Tasks API: Android (Kotlin), iOS (Swift), web (JavaScript) and Python.","Ready-made gesture recognition, segmentation, classification and object detection.","LLM Inference API: a compact LLM such as Gemma running offline on the phone.","Virtual try-on, fitness coaching, gesture-controlled interfaces, live filters and effects.",1792592355941]