Nothing matches that. Try a shorter word, or browse the topics.
The intelligence layer: a complete conversational service, speech in and out with pluggable cloud providers, and recognition that runs entirely on the device — so biometric data and scanned documents never have to leave it.
Chat, speech, wake word and message history in one service
A centralized AI conversation service combining Microsoft.Extensions.AI chat completions with speech recognition, text-to-speech, wake word detection and audio feedback — text chat, voice chat and hands-free mode behind one interface.
Speech-to-text, text-to-speech, audio capture and playback
One API for speech-to-text, text-to-speech, audio capture and playback across Android, iOS, Windows, the browser and Linux, with pluggable cloud providers.
On-device face enrollment and recognition
Face enrollment and recognition entirely on-device, using ArcFace embeddings and nearest-neighbour vector search — a dependency-free core with swappable models and stores.
On-device speaker recognition from voiceprints
Speaker enrollment and recognition built on the same architecture as Face Intelligence. Capture stays in your app, so it works with any audio pipeline.
Native document scanning plus on-device data extraction
The native document scanner (VisionKit, ML Kit, Vision) behind one IDocumentScanner, plus on-device extraction of structured data from what it scans.
