DeepMind Unveils SL2T Sign Language Translation Model, Lands on Pixel 11
GoogleDeepMind · x · 2026-08-12
Google DeepMind has introduced SL2T, a breakthrough massively multilingual sign-language-to-text translation model. It directly translates simultaneous movements of the hands, body, and face into text, overcoming long-standing technical challenges in sign language AI.
The technology has moved out of the lab into consumer products. On the Pixel 11, Deaf and hard-of-hearing users can now use ASL to type, search, and reply in conversations via Gboard and Live Transcribe. To protect privacy, body pose tracking is processed on-device, while translation occurs on servers.
Related event: Google DeepMind Launches SL2T Sign-to-Text Model, Debuting on Pixel 11(18 posts)→
More from Models
- GLM 5.3 Flash scores 39 on Artificial Analysis index, beating larger Mistral and Muse models — airesearch12 · 2026-10-16
- Open-source ASR built on a Qwen3-4B decoder posts 3.54 average WER across 5 languages — rohanpaul_ai · 2026-10-16
- Google's "Paid Pro" paywall in Antigravity angers Pixel buyers and bundle subscribers — Chance-Okra-5920 · 2026-10-16
- GLM 5.3 Flash is now free in OpenCode coding tool — DanielLockyer · 2026-10-16
- GPT-6 Sol runs a potion shop flawlessly but its reasoning mistakes stock for its own stats — liminal_bardo · 2026-10-16
- Codex convert says Claude app is 2-3x better optimized with a far smoother UI — ItchyResearcher5671 · 2026-10-16