---
format: "aidr-story-markdown/v1"
id: "e842bdb797573ce3de9bec406515eaa5a3a5e4c5b054156b946eabe658ef8f8f"
canonical_url: "https://aidr.today/e842bdb7?lang=en"
title: "On-Device Speech Recognition and Text-to-Speech in Google AI Edge Gallery"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-11-10T17:18:45.000Z"
category: "Frameworks"
topics: ["google","inference","framework","llm"]
source_urls: ["https://developers.googleblog.com/on-device-speech-recognition-and-text-to-speech-in-google-ai-edge-gallery/","https://blog.google/products-and-platforms/platforms/android/gemini-intelligence-november-features-devices/"]
summary: "Google AI Edge Gallery supports on-device, offline Automatic Speech Recognition and Text-to-Speech capabilities. Developers can use ML Kit for optimized Android performance or MediaPipe Tasks and LiteRT for cross-platform integration. This local pipeline pairs lightweight speech models with on-device small language models like Gemini Nano and Gemma 4."
---

# On\-Device Speech Recognition and Text\-to\-Speech in Google AI Edge Gallery

> [Open the canonical story](<https://aidr.today/e842bdb7?lang=en>)

**Published:** 2026-11-10T17:18:45.000Z
**Category:** Frameworks
**Topics:** google, inference, framework, llm

## Summary

Google AI Edge Gallery supports on\-device, offline Automatic Speech Recognition and Text\-to\-Speech capabilities\. Developers can use ML Kit for optimized Android performance or MediaPipe Tasks and LiteRT for cross\-platform integration\. This local pipeline pairs lightweight speech models with on\-device small language models like Gemini Nano and Gemma 4\.

## Sources

- [Story source](<https://developers.googleblog.com/on-device-speech-recognition-and-text-to-speech-in-google-ai-edge-gallery/>)
- [Story source](<https://blog.google/products-and-platforms/platforms/android/gemini-intelligence-november-features-devices/>)