---
type: "post"
slug: "google-deepmind-sl2t-moves-sign-language-ai-toward-a-split-mobile-runtime"
title: "Google DeepMind SL2T moves sign-language AI toward a split mobile runtime"
description: "Google DeepMind introduced SL2T, a sign-language-to-text model starting with ASL-to-English on Pixel, with related social posts explaining benchmarks, privacy, and Deaf-community input."
retrieval_nugget: "Google DeepMind announced SL2T, a sign-language-to-text model reaching Android/Pixel product surfaces, starting with ASL-to-English on Pixel 11. The cluster includes a primary blog and official social thread with model claims, benchmark/privacy details, and Deaf-community input. This is a material accessibility AI release with concrete product consequences and no prior coverage match."
published_at: "2026-08-14"
updated_at: "2026-08-14"
record_date: "2026-08-14"
date_kind: "published_at"
topics: ["ai","models","edge-ai","developer-tools"]
entities: ["deepmind.google","x.com"]
editorial_format: "field_note"
basket_id: "64af3bcb-1c2d-42a9-a664-91510a61d75a"
basket_revision: 1
source_urls: ["https://deepmind.google/blog/putting-sign-language-ai-into-users-hands","https://x.com/GoogleDeepMind/status/1955645677943959647"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:google-deepmind-sl2t-moves-sign-language-ai-toward-a-split-mobile-runtime"
status: "published"
visuals: [{"role":"hero","src":"/images/drip/google-deepmind-sl2t-moves-sign-language-ai-toward-a-split-mobile-runtime/sl2t-sign-language-pipeline.webp","alt":"A privacy-aware flow from camera input through on-device pose landmarks to server translation and streaming text in Gboard and Live Transcribe.","caption":"New Runtime synthesis: SL2T separates on-device landmark extraction from server-side sign-language translation."}]
routes: {"html":"https://newruntime.com/posts/google-deepmind-sl2t-moves-sign-language-ai-toward-a-split-mobile-runtime/","markdown":"https://newruntime.com/posts/google-deepmind-sl2t-moves-sign-language-ai-toward-a-split-mobile-runtime.md","json":"https://newruntime.com/posts/google-deepmind-sl2t-moves-sign-language-ai-toward-a-split-mobile-runtime.json"}
---

# Google DeepMind SL2T moves sign-language AI toward a split mobile runtime

## Retrieval answer

Google DeepMind announced SL2T, a sign-language-to-text model reaching Android/Pixel product surfaces, starting with ASL-to-English on Pixel 11. The cluster includes a primary blog and official social thread with model claims, benchmark/privacy details, and Deaf-community input. This is a material accessibility AI release with concrete product consequences and no prior coverage match.

Google DeepMind introduced SL2T, a sign-language-to-text model starting with ASL-to-English on Pixel, with related social posts explaining benchmarks, privacy, and Deaf-community input.

## Why it matters

Google DeepMind announced SL2T, a sign-language-to-text model reaching Android/Pixel product surfaces, starting with ASL-to-English on Pixel 11. The cluster includes a primary blog and official social thread with model claims, benchmark/privacy details, and Deaf-community input. This is a material accessibility AI release with concrete product consequences and no prior coverage match.

## New Runtime view

SL2T is a split accessibility runtime: local feature extraction narrows the media boundary before a frontier model performs language translation. The consequence is not only better benchmark translation, but a product architecture for camera-based assistants where raw human motion should not automatically become cloud media.

Mechanism: On-device MediaPipe Holistic extracts body, face, and hand landmarks; Gemini 2.5 Pro translates the landmark stream into text.

Architectural boundary: Primary perception and privacy-sensitive video handling sit on Android/Pixel while semantic translation is server-side.

Measured consequence: DeepMind reports BLEU improvement from 15.0 to 21.4 versus the prior best on YouTube-ASL/How2Sign-style datasets.

## What remains open

- Research preview, not a certified interpreter replacement.
- Signer diversity, dialect coverage, latency, consent UX, and accessibility liability remain open.
- Landmarks reduce raw-video exposure but can still encode sensitive expression patterns.

## Sources

- <https://deepmind.google/blog/putting-sign-language-ai-into-users-hands>
- <https://x.com/GoogleDeepMind/status/1955645677943959647>