Slide 1

Slide 1 text

Building a Fortune Teller App with OpenAI: From Chatbot to Voice Assistant

Slide 2

Slide 2 text

• Introduction • OpenAI model • OpenAI API • LINE x OpenAI • Conclusion Agenda

Slide 3

Slide 3 text

Introduction

Slide 4

Slide 4 text

AI is All Around Us!

Slide 5

Slide 5 text

AI is All Around Us!!! Source: https://www.pcgamer.com

Slide 6

Slide 6 text

We’re Building an AI Fortune Teller App! Today, we’re going back to the basics of OpenAI to create something special for Thai people: an AI Fortune Teller App the ultimate use case!

Slide 7

Slide 7 text

Demo 🔮

Slide 8

Slide 8 text

No content

Slide 9

Slide 9 text

How do we build this application? 🔍

Slide 10

Slide 10 text

OpenAI Models

Slide 11

Slide 11 text

What is AI Model? Input Output Model “An AI model is a program that learns from data to perform tasks like understanding text, recognizing images, or generating speech based on the patterns found in the data.” 
 “Input as Text” 
 “Output as Text” Prompt

Slide 12

Slide 12 text

What is Multimodal Model? Input Output Multimodal
 Model “A multimodal model 
 is a type of model that handles multiple data types, like text, images, 
 or audio.” 
 “Input as Text, Image 
 or Audio” 
 “Output as Text, Image 
 or Audio”

Slide 13

Slide 13 text

OpenAI Model Group Model Speech 
 Generation Image 
 Generation Text 
 Generation

Slide 14

Slide 14 text

OpenAI Flagship Models Input Output Model GPT-4o, GPT-o1, etc Whisper TTS DALL·E

Slide 15

Slide 15 text

OpenAI APIs

Slide 16

Slide 16 text

OpenAI API (OpenAI architecture) HTTP
 Request HTTP
 Response Model OpenAI API Simple HTTP Protocol

Slide 17

Slide 17 text

Text Generation API

Slide 18

Slide 18 text

Completion API Request Response Model
 GPT-4o OpenAI API Looks good, right? But remember, this API is stateless! (Text Generation API)

Slide 19

Slide 19 text

Assistant API (Text Generation API) Stateful API with many more features!!! Request Response
 Model
 GPT-4o OpenAI API

Slide 20

Slide 20 text

Speech to Text API

Slide 21

Slide 21 text

Audio Transcription API (Speech to Text API) Request Response
 Model
 Whisper OpenAI API

Slide 22

Slide 22 text

Text to Speech API

Slide 23

Slide 23 text

Audio Speech API (Text to Speech API) OpenAI API Request Response
 Model
 TTS OpenAI API

Slide 24

Slide 24 text

Realtime API

Slide 25

Slide 25 text

Realtime API (Speech to Speech API) OpenAI API Request Response
 Model
 GPT-4o-realtime OpenAI API

Slide 26

Slide 26 text

Playground

Slide 27

Slide 27 text

LINE X OpenAI Let’s building a Fortune Teller App with LINE and OpenAI

Slide 28

Slide 28 text

Architecture of Fortune Teller App (Chat Assistant Version) LINE Messaging API Webhook

Slide 29

Slide 29 text

Architecture of Fortune Teller App (Voice Assistant Version) LIFF

Slide 30

Slide 30 text

Architecture of Fortune Teller App (Voice Assistant Version with Realtime API) LIFF

Slide 31

Slide 31 text

Use case More fl exibility Better for complex conversation Low latency Less complexity Each option offers its own benefits! &

Slide 32

Slide 32 text

Conclusion

Slide 33

Slide 33 text

LINE x OpenAI = Future! 🔮

Slide 34

Slide 34 text

No content