Google has unveiled a new Gboard feature that converts American Sign Language (ASL) into text, allowing deaf and hard-of-hearing users to communicate with their phones and others without typing. The technology, called SL2T (sign-language-to-text), was developed in partnership with the Deaf community and represents one of the most significant accessibility updates from Google's recent Made by Google event.

How Does Google's Sign-to-Text Technology Work?

The SL2T model processes signing in a fundamentally different way than previous attempts at sign language recognition. Rather than treating sign language as individual hand gestures that directly correspond to English words, the technology analyzes movements across the hands, arms, body, head, and face to understand the full context of communication. This holistic approach allows the system to capture the nuanced grammar and meaning embedded in sign language itself.

The feature integrates into both Gboard and Google's Live Transcribe service, enabling users to sign messages, enter search queries, draft documents, or interact with Gemini without manually translating their thoughts into written English first. According to Google, testers found signing in ASL faster and more natural than typing in English.

What Makes This Development Significant for Accessibility?

The scale of training data behind SL2T underscores Google's commitment to this feature. The model was trained using more than 100,000 hours of data covering more than 50 sign languages, with approximately 25 percent of that training data coming from ASL specifically. This extensive dataset helps the system recognize signing patterns across different users, hand preferences, and communication styles.

Privacy was a core consideration in the design. The sign-to-text system does not need to send raw camera footage to Google's servers for translation. Instead, an on-device MediaPipe model identifies pose landmarks, after which only geometric coordinates are sent for processing; the original video can then be discarded. Google has also worked to reduce latency and improve performance for one-handed signing and left-handed users.

Steps to Access and Use the New Sign Language Feature

• Device Availability: The SL2T-powered sign-to-text functionality is initially available through Gboard and Live Transcribe on Pixel 11 devices, with plans to expand to more devices in the future.
• Communication Tasks: Users can employ signing for everyday smartphone tasks including messaging, searches, document creation, and interactions with Gemini without needing to type.
• Language Expansion: Google plans to add support for additional sign languages beyond ASL as the feature rolls out to more devices and users.

The development process itself reflects a meaningful shift in how major tech companies approach accessibility. Google stated that SL2T was developed in partnership with the Deaf community, with Deaf perspectives included in data collection, testing, evaluation, and deployment decisions. This collaborative approach ensures that the technology serves the actual needs of sign language users rather than imposing external assumptions about how signing should work.

"One of the most important updates coming out of Made by Google today is our new sign-to-text feature in Gboard and Live Transcribe. Built in partnership with the Deaf community, this can help people who sign ASL communicate more seamlessly with their phone or with those who don't sign," stated Sundar Pichai.

Sundar Pichai, CEO at Google

The timing of this announcement comes as Google continues to refine its broader AI strategy. Earlier this week, Google rolled out Gemini 3.7 Flash, a lower-cost AI model designed for software coding and automated business tasks, at an introductory rate of 75 cents per million input tokens and $3.75 per million output tokens through the end of the year. While that model targets enterprise efficiency, the sign language feature demonstrates Google's parallel focus on making AI tools more inclusive and accessible to underrepresented communities.

The sign-to-text feature represents a meaningful intersection of advanced AI capability and genuine accessibility need. By training on extensive sign language data and designing the system with input from the Deaf community, Google has created a tool that respects the linguistic integrity of sign language rather than treating it as a secondary form of communication. For millions of ASL users worldwide, this feature could fundamentally change how they interact with technology on a daily basis.