DeepMind's SL2T Goes Gloss-Free: End-to-End Sign Language to Text on Pixel 11

DeepMind's SL2T model, launched August 12 on the Pixel 11, translates sign language wireframes directly into text — skipping the intermediate "gloss" layer used in traditional sign language recognition pipelines. Trained on 100,000+ hours of multilingual sign language data, the end-to-end approach could reduce the cost of adding new language pairs. At launch, only ASL-to-English is available.