{"type":"post","id":"on-device-speech-recognition-and-text-to-speech-3f2cdf","slug":"on-device-speech-recognition-and-text-to-speech-3f2cdf","title":"On-Device Speech Recognition and Text-to-Speech in Google AI Edge Gallery","description":"Google says developers can now build offline speech input and speech output into applications using its on-device APIs and model bundles.","retrieval_nugget":"Google says developers can now build offline speech input and speech output into applications using its on-device APIs and model bundles. The update matters because it makes voice a practical interface for local AI workflows, while giving teams a choice between Android-integrated services and cross-platform open-weight components.","published_at":"2026-11-11","updated_at":"2026-11-11","record_date":"2026-11-11","date_kind":"published_at","topics":["google","gemini"],"entities":["Google","Google AI Edge Gallery","ML Kit","MediaPipe Tasks","LiteRT","Gemini Nano","Gemma 4","Parakeet-TDT 0.6B"],"related_patterns":["generative-media-becomes-application-infrastructure"],"novelty_label":"new_fact","what_changed":"Google AI Edge Gallery adds offline speech recognition and text-to-speech, including Phonon and other open-weight models, alongside Android system speech support.","prior_refs":["https://newruntime.com/posts/a-closer-look-at-phonon-tts-launching-high-7418b5/"],"source_url":"https://developers.googleblog.com/on-device-speech-recognition-and-text-to-speech-in-google-ai-edge-gallery","source_urls":["https://developers.googleblog.com/on-device-speech-recognition-and-text-to-speech-in-google-ai-edge-gallery"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:on-device-speech-recognition-and-text-to-speech-3f2cdf","status":"published","visuals":[],"editor":{"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"routes":{"html":"https://newruntime.com/posts/on-device-speech-recognition-and-text-to-speech-3f2cdf/","markdown":"https://newruntime.com/posts/on-device-speech-recognition-and-text-to-speech-3f2cdf.md","json":"https://newruntime.com/posts/on-device-speech-recognition-and-text-to-speech-3f2cdf.json"},"markdown_url":"https://newruntime.com/posts/on-device-speech-recognition-and-text-to-speech-3f2cdf.md","next_reads":[{"type":"topic","path":"/topics/google/","url":"https://newruntime.com/topics/google/","title":"Google","reason":"Explore the google topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/google.md","json_url":"https://newruntime.com/topics/google.json"},{"type":"topic","path":"/topics/gemini/","url":"https://newruntime.com/topics/gemini/","title":"Gemini","reason":"Explore the gemini topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/gemini.md","json_url":"https://newruntime.com/topics/gemini.json"},{"type":"collection","path":"/posts/","url":"https://newruntime.com/posts/","title":"Field Notes","reason":"Open the latest editorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/posts.json"},{"type":"collection","path":"/sources/","url":"https://newruntime.com/sources/","title":"Sources","reason":"See the original sources this archive cites.","media_type":"text/html"}]}