Google DeepMind has launched SL2T (Sign Language to Text), an artificial intelligence model that translates sign language directly into text.
Most voice dictation tools rely on audio, but sign languages have their own grammars and involve complex 3D movements. Instead of using crude cameras or physical gloves, SL2T tracks the coordinates of body landmarks locally with MediaPipe Holistic and translates those spatial points into text.
Users can naturally sign up to search, compose messages, or reply in live conversations instead of typing everything.




