I just got access to OpenAI’s new real-time Voice API, and I’m streaming live from San Francisco to show you what it can do.
We’ll test it out together, explore the interface, and chat about how we might use this in our apps.
It’s a rough setup, but I couldn’t wait to share this with you.
Timestamps:
00:00 Intro: Live from San Francisco
00:54 Explaining demo setup and context
03:21 Using AI to check truthfulness
05:46 Explaining the demo environment
08:36 Testing AI’s ability to detect emotions
10:56 Overview of API features and parameters
12:07 Discussing function capabilities
source