ChatGPT Voice Update is WILD!

Open up Google inside my Chrome browser. Sure. Opening that now. Can you type hello into Google?

Typing that in. Would you be able to increase your speaking speed by like 50%? Sure. I'll speed up.

Write a journal inside the notes app and just journal about like what you did today, what you learned, et cetera. On it. I'll keep it concise. I think a quick daily journal and notes would be a great way to capture what you did, what you learned and what's next.

Perfect. Can you see my face right now? Let me check. Not right now.

I'm seeing your notes app, not your camera feed or face. You can't see me in Descript? Checking that. I can see you if Descript is open with its camera preview visible, but right now I'm still seeing notes.

Bring Descript to the front and I'll check. Can you sing for me? La la la, la la la. Reorganize like my windows so everything fits on one screen.

Got it. I'll arrange the layout. That'll do. You can stop there.

Okay. Stopping now. So this is the new Chatubity voice update in the desktop app, which means that you can control your computer and run multiple AI agents coding in the background, just using your voice. You can also bounce it around like a basketball.

Look at this. Having a great time. And this is the new update. So you can see that it basically, it's kind of sticky as a pet on your desktop, and then you can control it.

You can mute it and stop it speaking at any time as well. So you just click these buttons so that it doesn't speak to me whilst I'm explaining this to you. And from here, it's powered by GPT live. So it can speak, you can listen, it can coordinate work.

It's also pretty good because as well, like if you were building your own voice agent, it would actually be pretty expensive to use the real-time voice agent API, and then if you run out of credits, you have to go and update and add your billing and everything else. It was super annoying. So how good is it? So far, it's pretty impressive.

It's quite fun. It does break at times. So for example, you probably saw before it took a screenshot and it's got my camera on the screen right now. So it's easily visible, but it couldn't actually understand that.

So there are some things where it's great. And there's some things where it's like not that great, but it can also do pretty cool stuff in the background. Let's test out on something else now. So if I log into a different account, as you can see, we're going to see if it can actually just like do something useful, like posting a tweet for us.

So let's try this right now. Can you post a tweet about the power of ChatGPT Voice for me, please? Checking that. I'll draft something tight and show it to you for approval before posting.

Something like ChatGPT Voice is like having a collaborator. Just, um, just post it. Just go onto X and write it right away. I've drafted it for the AI playbook account.

Say publish and I'll post it. Publish. Posting it now. Done.

Perfect. It's submitted. And can you just open it up as well? Opening it now.

It's open in Chrome. So it can actually post tweets straight away as you can see here. So it posted this tweet, pulled it up, control my browser whilst I was talking to you. The only thing that I don't like about it is it's still a little bit of a delay, but I can understand why, especially if you're using a thinking model.

So one thing that actually might be really useful is you just switch the API you're using for this and maybe use something like Instant instead of thinking models. But yeah, it actually works. It actually does stuff. It did rearrange my windows before.

One thing that was super useful actually was whilst trying to record this video, I needed to record the sound on my desktop, but my setup wasn't correct. So what did it do? It actually configured it properly inside this mixer so that I could record the sound of my computer and also hear the sound of my desktop, both of those things I couldn't do before. And it configured that for me like perfectly on the screen, which is great because I didn't want to mess around with this for ages.

So like technical bugs, pretty good. Posting social media content, pretty good. I like the fact that you can just come back to it anytime. You can click on this and see the conversation.

If we have a look through here, we did ask it to increase our speaking speed by 50%. That didn't work. I just want to be fully transparent on you. I'm like, is this magic?

Is this like literally Jarvis? I wouldn't say so, but at the same time, you can see where we're going. You can see this is a big step up versus what we had before. And the fact that this can also work in the background is really good too.

So what it can actually do is like when you're using browser use, for example, you can open up a separate tab in the background whilst you're doing something else, so it doesn't interrupt what you're doing. And then also, for example, we actually got it to journal inside the notes app and it can do that in the background. So we don't actually have to be like physically using the app ourselves. We can be clicking around, typing, doing other stuff in the background whilst it's working on this.

And also you can actually, you can turn off the sound for the voice chat. So you could actually have it still doing stuff in the background without it speaking out loud to you so that it doesn't, for example, interrupt you speaking to someone else, if that makes sense. And so it's pretty cool. Let's try on something else now.

Can you set like a 10 second timer whilst I go and do something else? Okay. So it's actually creating that timer now, but it takes longer than 10 seconds to actually create a timer, if that makes sense, no one will tell you this stuff. Like no one on YouTube is going to tell you like it doesn't work on a lot of practical stuff, but I just want to be fully transparent with you and just show you what's working and what's not.

Now what I'm going to say is, okay, can you just open up the habit tracker and then can you start coding in there and just improve the UI of the habit tracker, you see the project inside Codex for us? I'll take a look. Quick heads up, that timer setup wasn't ready to start. So I'm leaving it inactive and moving on to the habit tracker UI.

I'm sketching a cleaner layout, clearer spacing and a more consistent look. I created a dedicated habit tracker task to improve the interface, preserve how it works and verify the result. Doesn't it say like invalid or failed to create work tree, like it didn't actually work. Let me check that.

You're right. The habit tracker work tree didn't get created. So no code changes have started. I've restarted that task directly in the saved project and it's now running.

It's genuinely underway. Okay, perfect. And then can you start building out your voice system into our agent OS, see the folder for the new agent OS example system? Got it.

I'll check that. Perfect. And what I want you to do is use like the, ah, so you've got the habit tracker now as well, I can see that open. Mm-hmm.

I created the new agent OS example task. It's now underway to build the foundations of an integrated voice system without disrupting what you already have. I'll keep you posted as soon as there's something concrete to review. So I'm just going to mute the voice chat here.

So you can see like it failed on the first task when it was coming up, but then when I actually explained it, it started coding in the background for this, and it's also started using the voice agent inside the agent OS. So it will start building that in directly as well, which is pretty cool. So like, it's still not that smooth. At the same time, I would say this is the worst it's ever going to be.

And it's better than using the API because that's, that can get quite expensive. Um, at the same time as well, the other thing I would say is like, it's more built for like controlling your whole computer. So for example, what will happen is with this, you have like the full permissions. You have full access, so like everything on your, your, your computer and the local files and everything else.

Whereas if you look at like a traditional voice agent that you would build yourself to do something like this with chat-shupity real-time API, it wouldn't be as smooth as this, and I know because I've, I've tested out myself. So it is really interesting. I think the, the hardest part, like always just training your brain to understand how to use it. And bear in mind as well, like the voice itself sounds very realistic and doesn't sound like an AI voice.

It sounds like very smooth. It does take a little bit of time to reply. But again, I think you could probably edit, um, how fast it replies and that sort of thing. The other thing you can do is you can go to the voice section inside your settings here, and you can change the voice.

So you can switch which microphone you're going to use. Then we can move the pet around, or we can even hide this. If you don't want to see the sticky pet with the details of your voice. Um, you also get these sticky notes where it like shows you, okay, here's what it's doing and here's what it's working on.

So you can click back to that and just go back to that whenever you want to. And then also, if we go to our settings inside the voice section here, you can see that we've got voice and then we can select between multiple different voices here. I think I prefer Maple the best to be fair. And then you can also choose whether you want it to have screen context.

So this means, you know, can it see what you're working on or not? And then we've also got this option for a voice chat hotkey. So what that means is like, you could be working on something and then you just press a button. And it can just start working on something straight away.

So it is really, really cool. I'm tempted to do like a full one hour course on it. If you want to see that, just let me know in the comments and I might start working on that. If nobody cares about it, then I won't do it.

Um, but yeah, I want to know, like, do you want to see this or not? Like a free YouTube course that they will do for you. Just LBR. Um, so that's basically it on the voice system.

It's pretty cool. It is a little bit slow. You can see here that it has started working on both tasks in the background, which is super useful. And actually the UI that it created here is pretty good.

So it uses like the full capability of Codex and you can have multiple, it's basically like an orchestrator with a voice. So it's like, you can have multiple parallel agents working in the background and then it can go off and do something else. It can work on multiple tasks. It can control your screen.

It can control your browser. It can fix things and bugs, and it can also speak about 10% faster. If you ask it to speak like 50% faster, it's not going to work. Um, yeah, but pretty cool.

Worth checking out. Would I use it all the time? I think if I train my brain to actually start using this and build up muscle, you just need to remember it's there. Um, but yeah, it looks really, really cool.

Great feature. So thanks so much for watching. If you want to get more training on this sort of stuff, you can check out the AI Prophet boredom community link in the comments description or go to the AI Prophet boredom.com inside the community, you can post questions, get help and support in real time. Inside the classroom, you get access to all of our best trainings on this sort of stuff.

Bear in mind, you can also use this inside chatcheapyt.com, not just inside the Codex app. Um, and then also as you get updates, like you see right here, actually pops up right there. But yeah, if you want to get all of our best trainings on this sort of stuff, you can get it inside the AI Prophet boredom. We have courses on, for example, Codex, Chatcheapyt Work, Cheapty 5.6, Kimi K3.

If you're a complete beginner, you can go from beginner to expert over here. And then if you want our new daily updates, you can check out all of our best new systems. Like, so we're going to add a new guide on chatcheapty voice today. Inside the calendar, you can drop a weekly coaching calls, get help and support in real time.

And inside the map, you can meet people in your local area who are building with AI agents like chatcheapty and other things. So would I say it's quite like Java's level yet? No. One thing I'm interested to test is that you can actually use chatcheapty voice on your phone.

And then you can control your browser with remote sessions as well, which would be pretty interesting. So you could control your computer as long as it's switched on with your phone using remote access and the voice feature as well, which is pretty nice. So I hope to see you inside the AI Prophet boredom. Thanks so much for watching.

I'll see you on the next one. Cheers. Bye.