DeepMind Unveils SL2T Model: Pixel 11 Gets Real-Time Sign-to-Text
ZoubinGhahrama1 · x · 2026-08-13
Google DeepMind has introduced a massively multilingual sign-language-to-text (SL2T) translation model, bringing sign language AI out of the lab and into consumer products for the first time. The model currently powers sign-to-text dictation in Gboard and Live Transcribe on the Pixel 11, starting with American Sign Language (ASL) to English.
This feature enables Deaf users to sign to their phones anywhere they’d normally type, such as searching the web, drafting messages, or asking Gemini to execute tasks. In Live Transcribe, users can sign responses in conversations instead of typing. According to testers, signing in ASL is faster, more natural, and more delightful than typing in English.
Related event: DeepMind Launches SL2T Sign Language Model on Pixel 11(10 posts)→
More from Models
- DeepSeek V4 Pro Reported to Prematurely Halt in Agentic Coding — karminski3 · 2026-08-13
- xAI Launches Grok 4.6: Major Performance Boost at Same Price, Now in Hermes Agent — NousResearch · 2026-08-13
- Visualizing Benchmarks: Qwen 3.8-Max Outperforms Opus 4.8 Across Multiple Metrics — deliprao · 2026-08-13
- Grok 4.6 tested on bug bench: outperforms predecessor, becomes new default — PawelHuryn · 2026-08-13
- Grok 4.6 tops AI models under $5 workload budget, showing high intelligence per dollar — XFreeze · 2026-08-13
- OpenAI and Anthropic Models Dominate in Long-Running Autonomous Workflows — scaling01 · 2026-08-13