Keyboards? Where we’re going, we don’t need keyboards
summary
Demo shows Microsoft Cognitive Services on Azure with live code: upload images to the Vision API and get JSON captions, tags and face rectangles with confidence scores (e.g. 78% dog, 60% orange juice). Audio streams hit speech-to-text websockets, returning transcripts that feed a published LUIS model which extracts intents and entities (book_flight, departure, datetime range next week → Apr 1–8). GitHub sample and keys used for the demo.
AI-written summary · about
chapters (10)
- 0:00Start
- 1:39The Cognitive Services Platform
- 5:52What Are the Cognitive Services Api
- 6:05Cognitive Services Api
- 8:17Speech to Text
- 8:37Knowledge Api
- 9:18The Vision Api
- 22:19Capture and Recognize Audio
- 23:51Recognized Audio
- 34:07Create a Pre-Built Entity
related talks
54mKeyboards? Where We’re Going, We Don’t Need Keyboards
01h 03mEasier AI allows everyone to build smart apps
46mBuilding accessible experiences with AI
57mEasier AI allows everyone to build smart apps
01h 09mDialogue with your Data: Interactive AI with Azure Cognitive Services
49mMake your applications intelligent (...)
01h 05mMicrosoft Cognitive Services: Making AI Easy
01h 10mSolutions prototyping using Azure AI Studio