# Live demo of GPT-4o realtime conversational speech

## Метаданные

- **Канал:** OpenAI
- **YouTube:** https://www.youtube.com/watch?v=1uM8jhcqDP0
- **Дата:** 13.05.2024
- **Длительность:** 2:25
- **Просмотры:** 221,640
- **Источник:** https://ekstraktznaniy.ru/video/11525

## Описание

This was a live demo from our OpenAI Spring Update event.

Read more about GPT-4o: https://www.openai.com/index/hello-gpt-4o/

## Транскрипт

### Segment 1 (00:00 - 02:00) []

hi I'm uh I'm Barrett hey I'm Mark so one of the key capabilities we're really excited to share with you today is real-time conversational speech let's just get a demo fired up so I'm taking out a phone if you are wondering about this wire it's so we have consistent internet and if you see there's this little icon on the bottom right of the track GPT app and this will open up GPT 40's audio capabilities hey chat GPT I'm Mark how are you oh Mark I'm doing great thanks for asking how about you hey so I'm on stage right now I'm doing a live demo and frankly I'm feeling a little bit nervous can you help me calm my nerves a little bit oh you're doing a live demo right now that's awesome just take a deep breath and remember you're the expert I like that suggestion let me try a couple deep breaths can you give me feedback on my breaths okay here I go whoa slow a bit there mark you're not a vacuum cleaner breathe in or a count of four okay uh let me try again so I'm going to breathe in deeply and then breathe out for four and then exhale slowly okay I'll try again breathing in and breathe out that's it how do you feel I feel a lot better thank you so much so Mark you've been working on these capabilities for a while now can you tell us a bit how it's different from voice mode right so if you've used our voice mode experience before you'll notice a couple key differences first you know you can now interrupt the model you don't have to wait for it to finish your turn before you can start speaking and you know you can just butt in whenever you want second the model is real time responsiveness so that means that you don't have this awkward 2 to 3 second lag before you wait for the model to give a response and finally the model picks up on emotion right when I was breathing super hard there it could tell and it knew hey you might want to calm down a little bit you're kind of running a little bit too fast so you know it really has that capability across the board to perceive your emotion