Google AI Edge Gallery adds on-device ASR and TTS
Google Developers Blog announced on-device automatic speech recognition (ASR) and text-to-speech (TTS) capabilities in Google AI Edge Gallery. The release provides ML Kit APIs for Android and MediaPipe Tasks and LiteRT bundles for Android, iOS, web, and desktop, including Parakeet-TDT 0.6B, PocketTTS 100M, Kokoro-82M, and Phonon 31M; Google says the models can operate alongside Gemini Nano and Gemma 4 without network connectivity.
The release gives developers documented APIs and compact speech models for building fully local voice interfaces across mobile, web, and desktop applications.
On-Device Speech Recognition and Text-to-Speech in Google AI Edge Gallery - Google Developers Blog
On-Device Speech Recognition and Text-to-Speech in Google AI Edge Gallery
NOV. 10, 2026
#Google AI Edge Gallery#Google ML Kit#MediaPipe Tasks#LiteRT#Gemini Nano#Gemma 4#Parakeet-TDT 0.6B#PocketTTS 100M#Kokoro-82M#Phonon 31M