DIY OpenAI Vision API App with Speech Recognition - Python, OpenAI, Google Speech Services
Eli the Computer Guy via YouTube
Overview
Learn to build an OpenAI Vision API application with speech recognition capabilities using Python, OpenAI, and Google Speech Services in this comprehensive 41-minute tutorial. Explore system architecture, automatic item identification, and full voice communication with a computer vision system. Gain practical insights into code implementation, including handling Pyaudio challenges. Follow along with detailed code explanations and demonstrations to create your own AI-powered vision and speech application.
Syllabus
Introduction
Demonstration
System Architecture
WARNING - Pyaudio is a pain
Automatic Item Identification Script - Code Explaination
Ask Computer About an Item - Code Explanation
Full Voice Communication with a Computer Vision System - Code Explanation
Final Thoughts
Taught by
Eli the Computer Guy