Putting sign language AI into users’ hands
Google DeepMind's SL2T model enables Deaf and hard of hearing users to convert sign language into text for dictation, translation, and interaction, trained on over 100,000 hours of data across 50 sign languages, with a quarter in ASL. It achieves high-quality translation with minimal latency and addresses challenges in sign language processing, such as visual perception and true machine translation. The model is designed to support accessibility and is available on Pixel 11 devices, with plans to expand to more languages and capabilities.
More videos from Deepmind Google
Gemini Robotics 2 brings whole body intelligence to robots
Gemini Robotics ER 2: powering robotics with video understanding, task orchestration, and multi-robot collaboration
Gemini Robotics ER 2 helps robots reason, collaborate, and solve real-world tasks. It represents a step change in video understanding, tool orchestration, and multi-robot collaboration for robotic applications.
We’re launching Lyria 3.5 in Google Flow Music, with advances across musicality, lyrics, vocals, and creative control
