Develop A Hands-Free Ai Smart Speaker In 100 Lines Of Js

How to use Speech Synthesis in the Browser
How to use Speech Recognition in the Browser
How to use OpenAI GPT-3
Client-server communication
How to rapidly build an application with JavaScript
Requirements
Google Chrome
A Text Editor
NodeJS
An Account on OpenAI will be required to complete the project - (account creation covered in the class)
Speech Synthesis and Recognition are at a Beginner Level, GPT-3 and Client-Server are a bit more complex
Description
At the end of this course, you will know how to develop a hands-free AI smart speaker that can engage you with intelligent conversation. Starting from "Hello World", we will develop a short application using speech synthesis, recognition and OpenAI GPT-3 to create a smart speaker better at conversation than any major hardware smart speaker in the world. The final result will be < 100 lines of code. The total amount of Video Lecture is 47 minutesIn terms of difficulty, I believe anyone with interest and basic skills and perseverance could complete this course and build the project. The complexity ramps up gradually:The Speech Synthesis module is appropriate for beginning programmersSpeech Recognition is slightly more complexSending queries to GPT-3 via NodeJs is more complex, and requires an account on OpenAISending queries from the browser to the server is also a bit more complexWhat you need:Google ChromeA Text EditorCommand Line/TerminalNodeJSOpenAI AccountOpenAI Accounts are free, and come with plenty of free tokens to begin. You can also set a spending cap so you never spend more than you want to. Currently $0.02 USD pays for 1000 tokens which is roughly 750 words.Not covered in this course:Front end frameworks like React/AngularTypeScriptVersion Control, like GitMobileProcesslease follow along at your own speedMistakes are learning opportunitiesAsk questions via Q&A, Direct Message or Twitter @sam6reidDiscussion:How do you want your smart speaker to behave?What customizations did you make?What do you want to build next?
Overview
Section 1: Introduction
Lecture 1 Introduction
Lecture 2 Hello World!
Section 2: Speech Synthesis
Lecture 3 Speech Synthesis
Section 3: Developing Speech Recognition
Lecture 4 Developing Speech Recognition
Section 4: OpenAI GPT-3
Lecture 5 OpenAI GPT-3
Section 5: Client-Server Communication
Lecture 6 Client-Server Communication
Section 6: Combining Recognition + AI + Synthesis
Lecture 7 Combining Recognition + AI + Synthesis
Section 7: Conclusion
Lecture 8 Conclusion & Discussion
Beginning Programmers interested in AI,Beginning Web Developers interested in Speech Synthesis and Speech Recognition,Software Engineers interested in using GPT-3,Speech Synthesis and Recognition are at a Beginner Level, GPT-3 and Client-Server are a bit more complex

Homepage