Google introduced SignGemma, an AI model translating sign language into text, at Google I/O 2025.
Currently in testing, it's available to developers and select users, with a wider release planned by year-end. SignGemma aims to improve accessibility and inclusion globally by offering real-time sign language-to-text translations.
SignGemma is described as Google's "most capable sign language understanding model ever." It stands apart due to its open model framework and ability to deliver real-time, accurate translations.
Initially, SignGemma is most accurate with American Sign Language (ASL) to English. Google plans to expand its support for other sign languages over time.
Google is inviting developers, researchers, and Deaf and hard-of-hearing communities to test SignGemma. This collaborative approach ensures the tool is useful and respectful.
The tool is poised to transform communication and redefine accessibility in the digital age.