---
title: "On-Device Speech Recognition and Text-to-Speech in Google AI Edge Gallery"
description: "Google AI Edge Gallery now includes on-device Automatic Speech Recognition (ASR) and Text-to-Speech (TTS), enabling offline voice interactions on phones and wearables. ML Kit for Android delivers multilingual ASR across 100+ languages at 10x real-time speed with 8-9% Word Error Rate on FLEURS, and a diffusion TTS that begins speaking in ~100 ms, synthesizes 24 kHz audio at up to 50x real-time speed, and cuts power by over 50%. For cross-platform apps, MediaPipe Tasks and LiteRT support open-weight models like Parakeet-TDT 0.6B, PocketTTS 100M, Kokoro-82M, and Phonon 31M, packaged as single .litertlm files. These models run alongside on-device small language models like Gemini Nano and Gemma 4, powering the XR Language Teacher showcase with bilingual TTS code-switching and voice-enabled AI Chat with sentence-synchronized playback. All building blocks, including ML Kit APIs, MediaPipe Tasks, and LiteRT model bundles, are available today for developers to integrate into their own apps."
---

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

[Google](https://yomu.fyi/company/google) · Google AI Edge Team, Android ML Team · Nov 10, 2026

**Type:** Announcement

## Summary

Google AI Edge Gallery now includes on-device Automatic Speech Recognition (ASR) and Text-to-Speech (TTS), enabling offline voice interactions on phones and wearables. ML Kit for Android delivers multilingual ASR across 100+ languages at 10x real-time speed with 8-9% Word Error Rate on FLEURS, and a diffusion TTS that begins speaking in ~100 ms, synthesizes 24 kHz audio at up to 50x real-time speed, and cuts power by over 50%. For cross-platform apps, MediaPipe Tasks and LiteRT support open-weight models like Parakeet-TDT 0.6B, PocketTTS 100M, Kokoro-82M, and Phonon 31M, packaged as single .litertlm files. These models run alongside on-device small language models like Gemini Nano and Gemma 4, powering the XR Language Teacher showcase with bilingual TTS code-switching and voice-enabled AI Chat with sentence-synchronized playback. All building blocks, including ML Kit APIs, MediaPipe Tasks, and LiteRT model bundles, are available today for developers to integrate into their own apps.

## Context

Voice interaction on mobile and wearable devices often requires a network connection for cloud-based speech processing. Google AI Edge Gallery now provides on-device ASR and TTS to enable fully offline, low-latency voice interactions using compact speech models that run alongside on-device small language models.

## Approach / What changed

The release integrates system speech models via ML Kit for Android, offering multilingual ASR across 100+ languages and a diffusion TTS model. For cross-platform apps, MediaPipe Tasks and LiteRT support open-weight models like Parakeet-TDT 0.6B, PocketTTS 100M, Kokoro-82M, and Phonon 31M, packaged as .litertlm files. The pipeline powers the XR Language Teacher showcase with bilingual TTS code-switching and voice-enabled AI Chat with sentence-synchronized playback.

## Takeaways

- ML Kit’s on-device ASR achieves 8.0-9.0% Word Error Rate on FLEURS across 100+ languages and transcribes speech 10x faster than real time, with end-to-end speech translation wait times reduced by 35-44%.
- The on-device diffusion TTS model begins speaking in ~100 ms, synthesizes 24 kHz audio at up to 50x real-time speed, and reduces active device power by over 50% compared to traditional autoregressive TTS.
- For cross-platform apps, MediaPipe Tasks and LiteRT support open-weight models like Parakeet-TDT 0.6B, PocketTTS 100M, Kokoro-82M, and Phonon 31M, all packaged as single .litertlm files, with a growing catalog from the Hugging Face LiteRT Community.

## FAQ

### What languages does the on-device ASR support?

The on-device ASR supports multilingual transcription across 100+ languages, achieving 8.0-9.0% Word Error Rate on the FLEURS benchmark.

### How fast is the on-device TTS?

The on-device TTS begins speaking in approximately 100 ms and synthesizes 24 kHz audio at up to 50x real-time speed, generating a 27-second paragraph in about 500 ms.

### Can I use custom speech models with this pipeline?

Yes, LiteRT provides a rich set of multimodal model examples and supports custom implementations. The Hugging Face LiteRT Community offers a growing catalog of open-weight models like Whisper, Qwen3-ASR, and Moonshine for ASR, and Qwen3-TTS and Matcha for TTS.

**Tags:** [Android](https://yomu.fyi/topic/android), [ASR](https://yomu.fyi/topic/asr), [Google AI Edge Gallery](https://yomu.fyi/topic/google-ai-edge-gallery), [On-Device](https://yomu.fyi/topic/on-device), [Text-to-Speech](https://yomu.fyi/topic/text-to-speech)

- Source: [Google](https://developers.googleblog.com/on-device-speech-recognition-and-text-to-speech-in-google-ai-edge-gallery)
- Source URL: https://developers.googleblog.com/on-device-speech-recognition-and-text-to-speech-in-google-ai-edge-gallery
- Ingested by Yomu: 2026-11-10T18:01:09.560Z

[Read original post](https://developers.googleblog.com/on-device-speech-recognition-and-text-to-speech-in-google-ai-edge-gallery)
