Discover how to build robust, hands-free audio experiences powered by on-device AI. We’ll cover everything you need: setting up your glasses activity, capturing mic and camera feeds, and using voice along with other audio cues as your ultimate UI. Through an exciting real-world showcase of the open-source XR Language Teacher built in the Google AI Edge Gallery app, learn to orchestrate Gemini Nano 4 (built on Gemma 4 and optimized for Android devices), and ML Kit, and leverage the LiteRT runtime to build fast XR experiences that hear, see, and speak naturally.
Resources:
Try the XR Language Teacher demo and view source code → https://goo.gle/4ze2yig
APIs for building in XR → https://goo.gle/4yDRCJY
ML Kit GenAI API → https://goo.gle/4yY3yXT
MediaPipe Task API → https://goo.gle/4kaNFIV
MLKit GenAI TTS on XR → https://goo.gle/4z9g1Z2
Speakers: Amy Zeppenfeld, Alice Zheng
Chapters:
0:00 - Introduction
1:17 - Building for Android XR
5:58 - Designing audio-first experiences
15:15 - XR Language Teacher case study
19:33 - Chaining on-device models
22:30 - Prioritizing real-time latency with two-pass design
29:27 - Adapting to other use cases with AI agents
Watch the Android XR sessions from Android Dev Summit 2026 → https://goo.gle/ADS26-XR
Watch all the sessions from Android Dev Summit 2026 → https://goo.gle/ADS26-All-Sessions
Subscribe to Android Developers → https://goo.gle/AndroidDevs
#AndroidDevSummit2026
Event: Android Dev Summit 2026
Products Mentioned: Gemini Nano 4, Gemma 4, ML Kit, LiteRT, Android XR, Media