Google DeepMind releases SL2T, a multilingual sign-language-to-text AI model for consumer devices
Model release Provisional 88% confidence first seen
Google DeepMind released SL2T, a multilingual sign-language-to-text model designed to translate signed input into written text on consumer devices. It will be used in products such as Pixel 11 features including Live Transcribe and Gboard, initially supporting American Sign Language to English, with related functionality aimed at enabling sign-based dictation for tasks like messages and search.