Built at a hackathon, this accessibility-focused tool takes a video as input, extracts the spoken audio, transcribes it using OpenAI Whisper, then translates the text into sign language and renders it as an animated overlay directly on the original video. The pipeline combines speech recognition, NLP translation, and real-time pose rendering using MediaPipe — making video content accessible to the deaf and hard-of-hearing community without requiring any manual captioning or separate interpretation.