ChatGPT Voice 2.0 Can Now Control Your Computer From Your Phone
A hands-on first look at OpenAI's overhauled ChatGPT voice mode across five demoed use cases: booking a flight from an old chat, hunting down a file mid-task, generating and assembling a product website, and running it all remotely from a phone paired to the desktop.
Posted
2 days ago
Duration
Format
Demo
hype
Views
41.1K
1.2K likes
Big Idea
The argument in one line.
ChatGPT's upgraded voice mode acts as a coordinating agent that runs parallel tasks, reads your screen, and works through your connected tools, but that full capability lives only in the desktop app — the web and mobile chat versions stay conversation-only.
Who This Is For
Read if. Skip if.
READ IF YOU ARE…
You already use ChatGPT or Codex regularly and want to know exactly what the new voice mode adds beyond talking back and forth.
You're curious whether an AI voice agent can genuinely read your screen, use your other apps, and complete real multi-step tasks unsupervised.
You want a real, informal first-hand test across several concrete use cases rather than a marketing recap of the announcement.
SKIP IF…
You want a from-scratch setup tutorial for MCP servers or Zapier — the walkthrough here is fast and assumes basic comfort installing a plugin.
You're looking for a verdict on long-term reliability — this is a single-session first look, not a stress test over weeks of use.
TL;DR
The full version, fast.
ChatGPT's new voice mode is full-duplex, so it can be interrupted mid-sentence and immediately react instead of waiting for a pause. Inside the desktop app's work mode, one spoken request can spin off several parallel tasks, pull context from an unrelated earlier conversation, act through connected tools like a travel booking site or a newsletter platform, and read whatever is on screen to give live, tool-specific help. A phone can pair to the desktop over a one-time QR-code scan and then run any of those same actions remotely, including finding and renaming local folders. A general-purpose MCP server extends reach to thousands of apps with no native plugin, and recurring tasks like a daily inbox-and-calendar briefing can be scheduled and previewed entirely by voice.
Free for members
Chat with this breakdown — free.
Sign in and you get 23 free chat messages on us — ask for the hook, quote a framework, find the exact transcript moment, generate a markdown action plan. Bring your own key when you want unlimited.
Cold open framing the voice mode update as the most underrated AI release of the year, with a five-use-case agenda for the video.
00:27 – 03:20
02 · What's New in ChatGPT Voice Mode
Explains the core upgrades: full-duplex talk-and-listen (can be interrupted mid-sentence), availability inside desktop chat/work mode and Codex, one command triggering multiple parallel tasks, use of connected tools/plugins, and screen reading.
03:20 – 04:15
03 · Where to Access It (Web vs Desktop)
Clarifies that chatgpt.com and the plain mobile app only offer conversation-only voice mode, while the desktop app (and a phone remotely paired to it) unlocks task-running, tool use, and screen reading.
04:15 – 06:59
04 · Use Case 1
Asks voice mode to recall flight details from a separate, earlier 'flight planning' conversation, has it price a same-day-connection alternative when the cheapest option falls through, then pulls the chosen flight up inside the Ease My Trip connector to book.
06:59 – 08:19
05 · Use Case 2
Has voice mode search the desktop for a specific HTML file by description while simultaneously asking it to recall the last task run, demonstrating two requests handled in parallel in one conversation.
08:19 – 09:07
06 · Bonus: Screensharing
With screen-read permission on, asks voice mode to look at an open CapCut project and explain how to apply a filter, getting a specific, tool-native answer back.
09:07 – 11:49
07 · Use Case 3
Installs the Higgsfield MCP plugin in both ChatGPT web and desktop settings, then asks voice mode to generate two different Rolex product videos in parallel across separate chats — an exploded-view animation and a wrist close-up ad.
11:49 – 13:19
08 · Turning the Videos Into an Animated Website
Invokes a saved 'animated website' skill by voice to assemble the two generated videos into a live scrolling product page, then has voice mode open the finished site in the browser.
13:19 – 15:03
09 · Use Case 4
Has voice mode inspect and list the contents of a desktop folder, then rename it by voice, confirming the rename lands on the Mac in real time — setting up the phone-remote demo that follows.
15:03 – 16:36
10 · How to Set Up the Phone-to-Desktop Remote
Walks through pairing: Settings > Connections in the desktop app, scanning a QR code from the phone, then using the new 'Remote' tab in the ChatGPT mobile app to reach past desktop sessions and run voice commands against local folders from the phone.
16:36 – 18:39
11 · Connect 9,000+ Apps With the Zapier MCP
Explains that native ChatGPT plugins cover only a limited set of tools, and shows the Zapier MCP as a workaround that connects ChatGPT to 9,000+ apps, then asks voice mode to pull newsletter subscriber and open-rate stats from Beehiiv through it.
18:39 – 20:36
12 · Use Case 5
Creates a recurring 8am scheduled task by voice that reads Gmail for emails needing replies and pulls the day's Google Calendar events into one daily briefing, then triggers it immediately as a live preview before wrapping up.
Atomic Insights
Lines worth screenshotting.
The upgraded ChatGPT voice mode is full-duplex — it can be interrupted mid-sentence and immediately stops to process what was just said, instead of waiting for a pause.
A single spoken instruction can spin off several parallel task threads that a voice agent coordinates and reports back on, rather than running everything as one blocking request.
The web version and plain mobile app of ChatGPT voice mode cannot run tasks, use connected tools, or read the screen — only the desktop app, or a phone remotely paired to it, has full capability.
Voice mode can retrieve context from a separate, previously-run conversation by name, without the request being re-explained from scratch.
With screen-read access enabled, voice mode can give real-time, app-specific instructions for software it can see on screen, rather than generic advice.
Two unrelated AI video-generation requests can be issued in the same voice command and processed in parallel across separate chats, cutting total wait time.
A saved 'skill' — a pre-built set of instructions — can turn finished video and image assets into a fully assembled, scrollable marketing website with no further design input.
Once a phone is paired to a desktop via a one-time QR-code scan, any local file action available on the desktop, including finding and renaming folders, is also available from the phone's dedicated remote tab.
A general-purpose MCP server can bridge apps that have no native ChatGPT plugin, giving voice mode access to over 9,000 additional applications through a single one-time connection.
A scheduled task can be defined by voice and immediately triggered as a one-off preview to confirm it behaves correctly before its first real scheduled run.
When a cheaper option has a scheduling conflict, the agent can independently price and explain a next-best alternative rather than simply reporting the conflict and stopping.
Voice mode's always-on overlay can be repositioned anywhere on screen and queried mid-task without switching away from whatever application is currently open.
Takeaway
What ChatGPT's Voice Mode Actually Unlocks
WHAT TO LEARN
Full-duplex voice control turns ChatGPT's desktop app into an agent that runs parallel tasks, reads your screen, and can be triggered from your phone once it's paired.
02What's New in ChatGPT Voice Mode
Full-duplex conversation: the agent can be interrupted mid-sentence and immediately adjusts, instead of waiting for you to finish before it starts processing what you said.
The upgraded voice mode now lives inside the desktop app's chat mode and work mode, plus inside coding agents, not just the standalone voice interface.
A single spoken instruction can kick off several separate task threads at once, with the voice agent acting as a coordinator that reports back across all of them.
It can act through whatever tools or connectors are already configured, and it can read whatever is currently on screen to give real-time, click-by-click help.
03Where to Access It (Web vs Desktop)
The web version at chatgpt.com and the plain mobile app run a scaled-down, chat-only version of voice mode that cannot run tasks, use tools, or read a screen.
The full capability set — running tasks, using connected tools, reading the screen — is only available in the desktop app, or via a phone's remote connection to it.
Toggling 'work mode' (versus plain chat mode) inside the desktop app is what lets voice requests reach and act on local folders.
04Use Case 1
The agent can retrieve context from an entirely separate, previously-run conversation by name, without the user re-explaining the task from scratch.
When a cheaper flight option turns out to have a scheduling conflict, the agent can price a next-best alternative on its own and explain the tradeoff before asking to proceed.
Once a decision is confirmed by voice, the agent can pull the exact listing up inside a connected booking tool so the person only has to click confirm.
05Use Case 2
A single voice conversation can run two unrelated requests at the same time — searching for a file while also recalling the last task worked on — and report both results back together.
Voice mode can locate a file by description alone (name and rough creation date) rather than requiring the exact file path.
The always-on voice overlay can be moved anywhere on screen and queried mid-task, without needing to switch out of whatever app is currently open.
06Bonus: Screensharing
With the screen-read permission on, the agent can look at an open editing app and give specific, tool-native instructions rather than generic advice.
This turns voice mode into an on-demand, app-specific tutor for software the person doesn't already know well.
07Use Case 3
Once the Higgsfield MCP plugin is installed and enabled in both web and desktop settings, voice mode can generate video and image assets without opening Higgsfield's own interface at all.
Two unrelated video generation requests can be issued in the same breath and run in parallel across separate chats, cutting total wait time roughly in half.
The agent chooses its own model and settings for each generation request based on the described creative brief, rather than requiring the user to pick a model manually.
08Turning the Videos Into an Animated Website
A separate installed skill can take finished video and image assets and assemble them into a live, scrollable marketing website with no further design input.
The full build runs in the background while the person can just check in periodically by voice, rather than babysitting the process.
The finished result can be opened directly in the browser by voice command, with no manual URL lookup needed.
09Use Case 4
Voice mode can inspect the contents of a specific local folder and describe every file inside it, then act on that folder — like renaming it — using an ordinary spoken request.
Anything doable this way on the desktop app can also be triggered remotely once the phone is paired to it — the phone is not a weaker channel for local file actions.
10How to Set Up the Phone-to-Desktop Remote
Pairing is a one-time QR-code scan from Settings > Connections on desktop, after which the phone's ChatGPT app gets a dedicated 'Remote' tab.
The remote view lists every past desktop session, so a specific past project or conversation can be picked up again from the phone, not just started fresh.
A remote voice session connects live to the paired desktop and can query or modify local files on it in real time.
11Connect 9,000+ Apps With the Zapier MCP
Native ChatGPT plugins only cover a small slice of common tools; a general-purpose MCP server (Zapier's, in this case) is the workaround for apps with no direct plugin.
Setting it up is a one-time connection per app inside the MCP server's dashboard, after which voice mode can query any linked app's data on request.
Demoed live: asking voice mode for newsletter stats — subscriber count, open rate, delivery numbers — that live inside an email tool ChatGPT has no native connector for.
12Use Case 5
A recurring scheduled task can be defined and confirmed entirely by voice, specifying both the trigger time and which connected sources it should read from.
The agent can be asked to run a newly created scheduled task immediately as a one-off preview, before its first real scheduled run, to confirm it's built correctly.
The same scheduled workflow can extend into action, not just summary — drafting replies to flagged emails so the user doesn't have to write them from scratch.
Glossary
Terms worth knowing.
Voice mode (ChatGPT)
A live, spoken conversation mode in ChatGPT that, on the desktop app, can also run tasks, use connected tools, and read the screen — not just talk back and forth.
Work mode
A toggle inside the ChatGPT desktop app that lets voice or chat requests act on local folders and files, as opposed to plain chat mode which cannot.
MCP (Model Context Protocol) server
A connector standard that lets an AI assistant read and act on data from an external application it has no native, built-in plugin for.
Zapier MCP
A specific MCP server operated by Zapier that bridges ChatGPT to thousands of third-party apps through a single one-time connection.
Skill (ChatGPT)
A saved, reusable set of instructions the assistant can invoke by name to complete a specific multi-step task, such as assembling a website from video assets.
Scheduled task
A recurring, time-triggered ChatGPT job, like a daily briefing, that runs automatically at a set time without the user starting it manually.
Remote (ChatGPT mobile)
A tab in the ChatGPT phone app that lets a paired desktop session be viewed, queried, and controlled from the phone.
Higgsfield
An AI creative platform offering multiple image and video generation models that ChatGPT can call through an installed MCP plugin.
Resources
Things they pointed at.
00:00toolChatGPT voice mode
01:34toolCodex
04:15toolEase My Trip
08:19toolCapCut
09:07toolHiggsfield
16:36toolZapier MCP
17:04toolSkool
17:29toolBeehiiv
18:52toolGmail
18:58toolGoogle Calendar
Quotables
Lines you could clip.
00:05
“OpenAI just dropped their new voice mode, and I personally think this is the most underrated AI release of the year.”
Tight, punchy hook that doubles as the title claim→ TikTok hook↗ Tweet quote
01:04
“It's basically like we're talking to a normal human instead of this back and forth we're so used to when it comes to voice AI models.”
Plain-language explanation of the full-duplex upgrade→ IG reel cold open↗ Tweet quote
13:13
“We literally did not even have to type a single word or a prompt in order to generate this. This is all done with voice mode.”
Strong payoff line right after the website reveal→ newsletter pull-quote↗ Tweet quote
20:20
“It really feels like we now have this, like, Jarvis moment in AI where we can now use our phone and speak into it and can literally have ChatGPT going and performing tasks on our computer.”
Closing thesis line, doubles as the video's title framing→ TikTok hook↗ Tweet quote
The Script
Word for word.
Read-along
Don't just watch it. Burn it in.
See every word as it's spoken — crank it to 2× and still catch all of it. The same dual-channel trick behind Amazon's Kindle + Audible.
17px
metaphor
OpenAI just dropped their new voice mode, and I personally think this is the most underrated AI release of the year. And it seems like nobody is talking about it. You can even speak with it on your phone, and it can literally control your computer and get work done for you.
And on top of that, it can run multiple tasks in parallel while you're speaking with it. So in this video, I'm gonna show you what's new with it, where you can use it, and then five different use cases you can run right now so you can understand just how powerful this is. So without further ado, let's dive in.
Alright. So before we dive into a demo as well as show these different use cases, we need to understand what is new inside of ChatGPT voice mode. Because we have had previous voice modes, but this is much more capable.
And once we understand the foundation of how this works, you'll be able to see some of the use cases you could apply yourself. Now the first big thing that's different with the new voice mode is that previously, it was like speaking on a walkie talkie. And what I mean by that is we would speak to Chatuchibi voice mode, and it would have to wait until we finish talking in order to process what I just said.
Well, now with the new voice mode, it can talk and listen at the exact same time. So if we need to interrupt ChatuchuBT, it will immediately stop talking and then begin processing exactly what we're saying.
Basically, mid conversation, mid sentence, we could interrupt and it will adjust automatically. It's basically like we're talking to a normal human instead of this back and forth we're so used to when it comes to voice AI models where you have to cut it off when it goes on a run on sentence, and it just throws off the whole process of the conversation.
Next up, this voice mode now lives on the desktop app. So we could use this in things like ChatGPT chat mode, the new work mode that they just released last week, and then codecs. And there's something I'm gonna talk about later in this video that is extremely powerful if you're using codex, and you could basically speak to ChatGPT voice mode from your phone in order to trigger codex on your desktop.
But we're gonna talk about that and dive deeper into that later in the video. Now there's a couple more features here where when you truly understand how this works, it can begin to feel like magic that we can speak with an AI agent like Chatuchupti voice mode and have it do countless amounts of things for us in real time.
Now one thing we could do is we could give it one command while we're speaking with it, and it can perform many tasks at the same time. So what I mean by this is we could start multiple different threads inside of Chatcha PT, and we could almost use voice mode as, like, this coordinating agent to understand what's going on in parallel across those different conversations and tasks.
And I'm gonna show you later on in this video exactly how that works because it's genuinely mind blowing, and it kind of gives you a taste of the future of how we're gonna interact with AI in our own operating systems. Next, we could have voice mode use our actual tools. So any of the different plug ins or connectors that we have configured inside of ChatuchuBT, we can now perform tasks across.
So whether that's Gmail, your calendar, Slack, or any of the different tools that you use on a day to day basis, we can speak with voice mode and it can go and perform actions across those as well as pull information from them. Next up, voice mode can actually see our screen on our computer. So let's say you need help navigating a specific website or application you're trying to use.
You could have ChatGPT voice mode walk you through exactly where to click on the screen or explain complex topics for you in real time. This next feature allows you to work from your phone in order to control your computer. This allows you to use voice mode on your phone in order to pull different files from your computer and basically run any of the different tasks you would do inside of Chatuchi BT or Chatuchi BT Work or even Codecs.
Now there's a few places we can access this with a couple of caveats, so make sure to stick with me. First of all, we come to chatchibit.com, we have the voice mode right here that we could activate, but this does come with some limitations that I'm gonna talk about here in a second.
Now the next place to use it, and I highly suggest this over chatchibit.com, is the chatchubiti desktop.
That is inside of the desktop app. On top of that, we could also access this on our mobile app on our phone, which comes with some pretty cool capabilities, which I'm gonna show you later on in this video.
Now let's quickly talk about the difference of using chatchubiti.com versus the desktop. So if we're using this on our phone or the web application, it does not have the ability to run different tasks for us and use our actual screen, pull information from our computer, etcetera.
Think of this like using normal chat GBT mode. You could talk back and forth with it, and the model sounds really good, but it doesn't have the full capability. Whereas in the desktop app, we can run tasks and specific agents and basically do everything that I'm gonna show you in this video.
Now let's move on to testing this out in real time. So first of all, I'm inside of the Chat BT desktop app. And up top, you can see we have two modes.
We have chat mode, and we have work mode. Voice mode works in either of these different platforms, but if we want the full capabilities, I'm gonna toggle on work mode. So this way, it's able to work inside of different folders on my computer.
Alright. So for this first use case, I'm gonna speak with ChatuchuBT voice mode in order to pull context from a previous task that I ran actually last week. And this is a conversation right here.
So I was using Chatcha BT work in order to create a travel plan for me. It's using this connector called ease my trip in order to pull flight information and find the cheapest and the best flights for me coming back from Europe. On top of that, it even generated this ChatchaBeeTee site for me, breaking down everything that it found when researching the best travel plan for me.
So what I'm gonna do is I'm just gonna toggle this on right here. Hey. What's going on?
Could you do me a favor? I want you to look at that Europe trip flight that you were helping me book. Can you pull some of the information on what you think will be the best can you pull some information on what you think will be the best flight options for me?
I'll check the trip details and see what flight options fit best. For your Europe trip, I don't have the details in this chat. What are your departure city, destination, and travel dates?
Yeah. So you actually had this in the previous conversation. Can you pull from that?
The name of the conversation was called flight planning. Okay. I'll check that.
I'm locating that flight planning task now.
I found the trip details, Barcelona to Redmond on August 14. You want him to lie flat without paying for business all the way.
The best value route was through Boston,
but I'm checking updated availability since fares can shift. Okay. Cool.
Once you find the best flight for me, can you actually pull up, um, inside of Ease My Trip so I could book this? Got it. I'll see if I can bring that up there.
I'm seeing a snag.
The cheapest live flat option now arrives too late for a same day connections, what would mean overnighting.
I'm pricing that against a faster through ticket that keeps the trip simpler. The lowest risk value option is a one stop through ticket via London and Seattle landing in Redmond the night of the fourteenth. That's fine.
Can you just go ahead and pull it up so I could book that? Sure. I'll open that.
I pulled up the lower cost lie flat option and eased my trip, Barcelona to Boston on August 14. It requires an overnight in Boston, then a separate Redmond flight the next day. Okay.
Perfect. I think I'm gonna book this. Thanks.
Alright. So there you go. You saw a Chateappiti voice mode in action.
It went ahead. It pulled from a previous thread conversation that I had, and this was actually, like, last week, so I was able to use that as context. And then it used this application here that I have connected and even pulled this up in my browser so I can go and book this flight automatically right now.
Alright. So for use case number two, I'm gonna use ChatuchuBT voice mode in order to find a specific file that's living on my computer. So I generated this a couple of days ago, and let's say we don't wanna have to go and, like, try to search for this all across our computer.
Instead, let's offload this task to Chatcha b t in order to do it. So as you could see right here, it's living on my desktop, this co work setup teaching HTML pack that I have open right here. So I'm just gonna come over to Chatcha b t and have it find this for me.
Hey. Can you go on my computer, and I want you to find the Chatcha b t co work setup HTML that you generated for me a couple of days ago. Got it.
I'll look for that file and confirm what I find. Also, while you're while you're doing that, what was the last task that we were running inside of Chatcha b t? I'll check that too.
Now as you could see, it's running and doing multiple tasks at the exact same time, which is the power of using the new Chatcha BT voice mode, and it's pretty cool when you have multiple different tasks you have running at once. I found and opened the simple Claude co work setup teaching pack on your desktop. Last created July 17.
Yeah. This is exactly The last task? This is exactly what I was wanting.
Thank you. Great. Glad it matches what you needed.
Now what was that task you said that you found, like, last task you ran for me? Let me pull up the exact last task for you. It was the voice mode update chat where you asked if the new voice mode had launched recently and then to see your most recent Gmail message.
Perfect. Thank you so much. Now one thing I wanna mention that's pretty pretty cool is you could see this little Chatchubiti voice blob, and we could basically put this anywhere on our computer.
So let's say I'm editing this video right here, for example. You could still see Chatchubiti voice mode, and I could just basically come here and say, hey. I want you to look at my screen.
What does it look like I'm working on right now? I need help with this. Okay.
I'll take a look.
I'm reading what's on screen now. You're actively editing a roughly seven minute project in CapCut with the clip's basic settings open. Yeah.
Could you actually break down how I can apply filter? I can't figure out how to do it. I'll check that real quick.
In CapCut,
click filters in the left sidebar, then choose one and drag it onto your clip in the timeline. To apply it across the whole video, drop it onto the main video track, then adjust it since it's in the right panel. Fixed it.
Nice. Good thing. So for this next use case, I'm gonna use it to generate images and videos with voice mode using the Higgs Field MCP.
Not only am I gonna generate one video or image, I'm gonna generate multiple at the exact same time since we're able to run these voice mode tasks in parallel. And if you don't know what Higgs Field is, it's an all in one AI creative platform that has access to all the top image and video models so we could generate basically anything we want in terms of videos.
And the best part about this is we don't even need to be inside of this user interface here. We could simply just talk to voice mode, and it will go and generate all these different videos using whatever model it thinks is best. Now it's really easy to set this up, so I'm gonna show you how to do that right now.
First of all, we're gonna go to the link in the description to use the Higgs Field MCP. From here, we're gonna see this landing page right here. And what we wanna do is we want to select ChatGPT, and simply, we're gonna click this add Higgs Field plugin right here.
Next, I'm gonna click on install plug in and sign in to my Higgs Field account. If you don't already have one, make sure to sign up for an account in order to use the MCP. I'm just gonna click on allow here.
And then just like that, we now have Higgs Field installed. It's really simple to do. Then make sure to do the exact same thing inside of the desktop app.
So, basically, just come to plugins, search up Higgs Field, click on this right here, and then make sure to enable it. Now let's come back into ChatGPT and test this out right now. Hey.
So I want you to use the Higgs Field MCP in order to generate two different videos for me in parallel in separate chats.
I want this to be a product video of a Rolex, and I want this to almost be like an exploding animation where the different parts of the Rolex kind of come apart that we could use for a scrolling website.
Then the second video that I want you to generate is going to be more of like a luxury product video advertisement
that shows a Rolex up close on somebody's wrist. Sure. I'll set those up.
I'm checking the video setup and prepping both Rolex concepts, one exploded view and one wrist worn ad. I've split them into separate generation tasks.
So the exploded view website animation and the luxury wrist close-up ad are both running in parallel now. Alright. So a few minutes later, and we now have both of these videos generated, so let's take a look.
I mean, this looks pretty cool. It's zooming in on this Rolex Submariner, then right there, you could see the different parts of this watch kind of coming apart. I think this would look really good and smooth on an animated website.
I mean, that is really good, and this only took one prompt and not even, a prompt. I basically just told Chatcha b t voice mode in order to go and do this. And then here is the second video that it generated.
This is more of, like, an up close, um, product shot of the Rolex Submariner on somebody's wrist. I mean, again, that looks super solid as well. So now I'm just gonna come back here and say, hey.
I just took a look at these, and they look really solid. What I want you to do now is turn these into an animated website using the animated website skill that you have. I'll start shaping that into an animated site.
I'm mapping the animations into a simple product page flow. And so now what this is doing is it's locating the animated website skill that I've downloaded inside of Chatcha b t, which is basically a set of instructions to take videos and animations like that and turn it into an actual scrolling website. So as we scroll, these animations are gonna play.
So it just really makes a stunning website for somebody to look at. So it's been running for a couple of minutes. Let me come back to voice mode and just ask, hey.
How's it going? Did you finish the website? Let me check on the build real quick.
Yes. The website is ready, including the exploded view sequence and the wrist film closing section. Perfect.
Could you open it up for me? Sure. I'll pull it up.
I'm opening it now. The animated Submariner site is open. Alright.
So it pulled it up inside this browser inside of ChatGPT. What I'm gonna do is I'm just gonna copy this URL and view this in my browser so you could see a full view. And, man, this looks super good.
I mean, it's the exact same animation that we just created with the, you know, the Rolex kind of exploding here. I like the typography. I like the font of this website.
And then if I scroll to the very bottom, you can now see that it even shows this wrist shot, which I could actually view right here. All this was generated with Chatuchibi voice mode and the Higgs Field MCP. We literally did not even have to type a single word or a prompt in order to generate this.
This is all done with voice mode. Now for this next use case, hold on to your seat because this is where it gets extremely powerful. It's blown me away after playing around with this, showing what's capable with voice mode.
So in order to show you what I mean, take a look at this folder right here on my desktop called Opus five animated websites. Inside of this folder, we have a couple of different thumbnails that I generated just yesterday. And what I'm gonna do is I'm gonna use voice mode from my phone in order for Chatuchi BT to go onto my computer and find that exact folder and then analyze those images for me.
Now the reason why this even matters is because anything that we can do on our computer inside of Chatuchi BT work or codecs, We can now do directly from our phone using voice mode. And I want you to let that sink in because it can be extremely powerful if we use this correctly. So what I'm gonna do is I'm simply going to click on this voice mode, then I'm gonna come and say, hey.
I want you to go on my computer and look at the Opus five animated websites folder. I then want you to tell me what images I have inside of there. Sure.
I'll take a look. I see six images, insane websites, Opus five websites,
two copies of 15 k websites,
and a lighter clawed colon animated dash website graphic. Amazing. Can you do me a favor?
And I want you to rename this folder to say Opus five websites.
Okay. I'll take care of that. I found the folder and am updating its name now.
Done. The folder is now called Opus five websites.
Now I wasn't able to screen record both my phone and my computer at the exact same time, but literally right when my voice agent told me that it changed the name, I actually saw this name of the folder change. And I know this is a really basic use case, but basically anything you could have codecs do on your computer, you can now trigger Chatcha BT to do it with the voice mode from your phone.
Alright. So I'm gonna show you exactly how to set this up now before we move on to the next use case. So what we're gonna do is we're gonna come inside of our Chatcha BT desktop app.
Then at the very bottom left where you see your account, you're gonna click on this, and then click on settings right here. From here, underneath coding, you wanna click on connections. And then we're now gonna see this right here where we can control our Mac from our phone.
So now we're gonna click this add button. Now we're gonna see this QR code right here. I'm gonna pull up my phone and then scan this.
And then now inside of the ChatGPT app on our phone, what we're gonna do is we're gonna come over to the left hand side, swipe to the left, and then you're gonna see this new remote button right here with this little green icon. I'm gonna click on this. And then now you could see the different projects that we have that we've ran in the past.
So for example, I could then go to the Rolex animated website that I created, and we could view any of these sessions that we ran on our desktop app now on our phone. And in order to use voice mode and have it go perform a task for us, we just click on this little voice icon right here. It's gonna open this up.
It's connecting locally to your desktop, and then we could chat with it. Hey. What's up?
Can you Source. Hey. What's Got it.
What's on your mind? Yeah. Can you do me a favor and go inside of my IG Carousels folder on my desktop and then let me know what's inside of there?
Sure. I'll check that folder. I'm checking that folder now.
Inside your IG Carousels folder, there are four sets. Five Claude code skills I can't live without Perfect. Seven sets.
Thank you so much. Five So there you could see exactly how easy it is to trigger this from your phone, and this is gonna be really powerful if you're on the go and wanna have Codecs or ChatGPT go and do something if you're not at your computer. Now I'm gonna quickly talk about how to add a plugin, and then I'm gonna show you a hack to connect ChatGPT to 9,000 plus different applications so you could work across your entire tech stack.
First of all, if I come over to plug ins on the left hand side, there are a few different public plug ins that we can connect to directly inside of ChatGPT, but this is kind of limited right here, and it won't have all the different apps that you wanna use. A really good workaround for this is using the Zapier MCP, which connects to 9,000 plus different applications, and it's really easy to use.
So to show you this in action, this is this MCP server that I have configured. I then have it connected to Beehive. I also have it connected to School, and these are a couple of different applications that I use every single day to run my business, but there's no way to connect them inside of Chatuchiki without using this MCP server.
And to show you exactly what I mean, let me use voice mode in order to pull email newsletter information from Beehive, and it's gonna do so using the Zapier MCP. Hey. I want you to check inside of Beehive via the Zapier MCP and give me some relevant information about my email newsletter list.
Okay. I'll check the Beehive details now. I'm checking the connected Beehive data source now.
Your active newsletter, Brock Masara, AI for Non Techies, shows 1,694
free subscribers and no paid subscribers with about a 29% average open rate. The latest delivery numbers are 449 delivered, 131 opens, and nine clicks.
There's also a similarly named publication that's empty right now. Perfect. Thank you so much.
And so as you could see, it was able to access Beehive even though it's not connected directly inside of Chatcha b t, and it's able to do this with a Zapier MCP. If you guys wanna try it out, there will be a link in the description, and it's as simple as coming here, clicking on creating a new MCP server, and then we're just gonna select whatever agent we're using.
So for this use case, we're gonna be using Chatcha b t. So we'd select this, and then we just go through these steps right here, and it's gonna walk you through exactly how to connect this. And then once you've configured that, all you need to do is add our different applications that we wanna connect, and there are, again, 9,000 plus that we could connect to.
Now this next use case I'm gonna show you is really helpful for automating specific tasks that you do every day or every week, for example, and that is using it to generate scheduled tasks inside of ChatGovT. So I'm just gonna come here and say, hey.
I want you to create a scheduled task where every single day you pull from my Gmail, and at 8AM, you remind me everything that I to reply to for the day, as well as I want you to pull from my Google Calendar so I can know what to look forward to throughout the day. Okay.
I'll check your Gmail and calendar and see how to set that up. I'm checking the connected mail and calendar capabilities
so that the daily briefing can cover both replies due and your schedule. So what it's doing now is it's pulling from both of these different apps because I have connected them, and it's gonna pull all the relevant information for me. I could then even use voice mode to draft email replies to all these emails that I need to reply to so I don't personally need to do it myself.
Your daily briefing is set for 8AM. It'll highlight emails that need replies and summarize your day's calendar in one snapshot without changing any messages or events. Perfect.
Can you run this scheduled task right now so I could see how it works in action? Got it. Running it now.
Today's briefing is ready, and I'm checking if we can trigger it immediately for a live preview. Your briefing shows a few items worth replying to, including a couple of creator partnership invites, a Slack invite, an account reconnection notice, and a package pickup reminder. Your calendar is clear today, so you've got some room to tackle those.
Perfect. Thank you. And this will run tomorrow?
Let me confirm it's set for tomorrow too. Yep. You'll get the briefing tomorrow morning at 8AM
and every day after that. Perfect. Thank you.
Alright. There we go. That is a new Chatchubiti voice mode.
You should now have a sense of how powerful this is and different ways that you can use this right now. I'm personally absolutely stoked about this. It really feels like we now have this, like, Jarvis moment in AI where we can now use our phone and speak into it and can literally have Chatcha b t going and performing tasks on our computer.
If you enjoyed this video, subscribe to the channel for more videos like this. Let me know what you think in the comments, and I'll see you in the next video.
The Hook
The bait, then the rug-pull.
OpenAI quietly overhauled ChatGPT's voice mode into something closer to a coordinating agent than a chat feature, and the presenter spends the video finding out how far it runs on its own: booking a flight from an old conversation, hunting down a file while a second task runs in parallel, generating and assembling a product website by voice alone, and finally controlling the whole thing from his phone.
Frameworks
Named ideas worth stealing.
03:20list
Where Voice Mode Runs vs. What It Can Do
chatgpt.com (web) and the plain mobile app: full-duplex conversation only — no tasks, no tool use, no screen reading
ChatGPT desktop app (work mode) and a phone remotely paired to it: runs tasks, uses connected tools/plugins, reads the screen, controls local files
The video draws the same 'same name, two different things' distinction its own on-screen slide makes: which surface you're using changes what voice mode is actually allowed to do.
Steal forA quick capability cheat-sheet before recommending any AI voice feature to someone who might try it on the wrong surface first
CTA Breakdown
How they asked for the click.
VERBAL ASK
20:20subscribe
“If you enjoyed this video, subscribe to the channel for more videos like this. Let me know what you think in the comments, and I'll see you in the next video.”
Standard soft close — subscribe ask plus comment prompt, no product or affiliate pitch.
FROM THE DESCRIPTION
PRIMARY CTAWhere the creator wants you to go next.
A three-tool workflow — Higgsfield for visuals, a packaged skill for the scroll effect, Opus 5 to assemble it — turns one reference photo into a finished animated site inside a single Claude window.
A 72-minute, screen-by-screen course on turning Claude Cowork into an entire marketing department — voice skills, image and video generation, lead scraping, live dashboards, auto-scheduling, and AI SEO.
00:12
00:19
00:46
01:01
01:25
01:41
01:59
02:18
02:36
02:48
03:04
03:40
03:48
04:08
04:15
04:34
04:55
05:12
05:45
06:01
06:17
06:34
06:50
07:16
07:39
07:55
08:04
08:38
08:59
09:31
09:47
09:58
10:19
10:36
10:52
11:08
11:24
11:40
11:56
12:11
12:26
12:51
13:04
13:34
13:49
14:11
14:25
14:42
14:55
15:03
15:32
15:41
16:12
16:28
16:58
17:07
17:29
17:45
18:00
18:15
18:31
19:00
19:15
19:30
19:59
20:12
20:24
13:03
11:42
09:35
1:12:16
10:57
15:30