Episode Categories:
Resources:
Join the discussion on LinkedIn: Got something to say? Let us know on LinkedIn and network with other AI leaders
Upcoming Episodes: Check out the upcoming Everyday AI Livestream lineup
Connect with Jordan Wilson: LinkedIn Profile
Start Here Series in our Inner Circle Community: Join for free access
ChatGPT Voice: Unlocking True Hands-Free Workflow Automation for Business Leaders
Recent updates to ChatGPT Voice have introduced a shift in the way work can be executed using artificial intelligence, moving beyond mere interaction to tangible hands-free productivity. Instead of marketing gloss, the episode highlights concrete, workflow-focused use cases—showing how ChatGPT Voice, especially within the desktop Codex/Work platform, is moving AI from sidebar assistant to central business operator.
Hands-Free AI: More Than Just Dictation
Many are familiar with basic AI dictation or older "walkie talkie" style voice features, which simply transcribe or respond to singular voice prompts. The latest release, however, combines the new “GPT live” model with agentic execution power, allowing voice-interactive commands to translate directly into sequenced actions, both locally and across cloud-connected business systems. This hands-free approach means a mobile device can now orchestrate and relay instructions to a desktop workstation—enabling full project management, content creation, file triage, and app-to-app workflow without manual intervention 01:06.
Workflow Orchestration: Desktop Integration and Connectors
The most significant difference between traditional web-based AI chat and the Codex desktop experience is native access to a business’s data connectors and MPC integrations. ChatGPT Voice, once enabled through the desktop platform, inherits the ability to control programs, open files, triage email, draft communications, and organize cloud storage—all automatically, as prompted via natural language 01:23, 08:09, 09:16. Voice directives route work across any connected platform—Slack, CRM, Google Drive, internal servers—extending far beyond the static limitations of browser-based chat interactions.
For companies already employing dozens of connectors, this single interface becomes a real-time, always-on “agent” able to consolidate work previously siloed across apps 09:16, 17:25.
Persistent Context: AI Thread Awareness and Project Memory
Other AI solutions often isolate each conversation, making cross-project intelligence and historic context impossible unless the system incidentally commits facts to memory. By contrast, ChatGPT Voice within Codex retains awareness across threads and project folders. New or repeated tasks can be administered, and the system is able to look up, edit, and annotate any thread or business file—matching human-level continuity and vastly improving traceability 13:03, 14:45.
This persistent project intelligence creates simple, voice-driven access to historical work, ensures continuity for ongoing tasks, and enables accurate multi-step workflows and follow-up—even when the user is remote or multitasking.
Scheduling and Automation: Repeatable Tasks by Voice
Beyond ad hoc voice commands, ChatGPT Voice enables the setup of recurring business actions entirely by voice. For example, after working through a data enrichment and CRM integration task, users can instruct the AI to run the process as a “skill” at a recurring interval—automating lead triage, reporting, or other business development cycles. The scheduled skills then become part of the regular business rhythm without further intervention 19:00.
This opens up consistent, hands-off operation of complex business logic, multiplying the effect of existing workflows without additional personnel or outsourcing.
Multi-Tasking and Real-Time Interruption Tolerance
Unlike linear AI or voice assistant systems, ChatGPT Voice can stack and handle multiple assignments in one session. Natural conversation flow—complete with interruptions, corrections, and new directives—enables it to reprioritize or pause on the fly, emulating real team collaboration 21:02. This means parallel tasks, follow-up details, or sudden shifts in project direction are not lost in the shuffle.
Creating Durable Business Artifacts and Audit Trails
One common concern with voice interfaces is losing proof of work or lacking records for compliance. The latest workflow recommends always requiring AI agents to provide written artifacts—saved files, summaries, or audit logs—once tasks are completed. Automatic upload or in-line markdown summaries in Google Drive or project folders ensure every action is traceable and available for review 23:24.
This addresses risk while leveraging AI to both execute and document.
Practical Application: Remote Teamwork and Omnipresent AI
One advanced application demonstrated was controlling all desktop work from a mobile phone during an hour-long walk—initiating slide deck comparisons, transcribing YouTube presentations, cross-referencing internal content, and running polls—all without sitting at the desk 01:14, 22:25. The floating “orb,” an ever-present AI agent on the desktop, means that workflow can be initiated or resumed instantly, music and calls don’t interfere, and the user’s presence is no longer required at the workstation to maintain operational momentum 24:33.
Strategic Value for Business Stakeholders
The new capabilities go beyond technical novelty; they tangibly impact overhead, talent allocation, and productivity. With ChatGPT Voice, businesses can:
Centralize control of disparate digital workflows into a unified, accessible agent interface
Reduce manual hours spent on cross-system triage, follow-up, and content generation
Enable executives and senior staff to manage projects and review work without returning to their desk, capturing strategic focus time
Capture consistent audit trails of all AI-executed work, supporting compliance and project hand-offs
The discussed workflow upgrade is not just about convenience; it systematically redefines how high-value business processes can be executed, tracked, and scaled by integrating true agentic AI into the work environment.
Topics Covered in This Episode:
- ChatGPT Voice as Jarvis-Style AI Agent
- ChatGPT Voice vs. Old Voice Modes
- Full Duplex GPT Live Model Explained
- Desktop ChatGPT Voice: Codex Integration
- Advanced ChatGPT Voice Workflow Use Cases
- Utilizing Connectors and MCP Integrations
- Stacking and Scheduling Tasks with Voice
- Hands-Free Computer Control via iPhone
- Durable Written Artifacts and Accountability
- Omnipresent Desktop Orb Agent Features
- Live Demo: Real-World Voice Command Tasks
- Productivity Gains from Voice-Driven Automation
Episode Transcript
Jordan Wilson [00:00:16]:
Many people talking about the new chat g b t voice are calling it their AGI moments, and I don't disagree. Yeah. It's changed how I work in the short amount of time that it's been out, but there's usually at least a handful of updates every quarter that do that. But this update from chat g p t voice changes how I think about work, and that has rarely happened in the nearly four years I've been doing the everyday AI show. It's like if you've ever seen Iron Man, chat g b t voice is literally like having your own Jarvis. Whether you're in front of your computer or across the country like I was the past couple of days, you can ramble hands free in natural language, and the desktop version of ChatGPT will literally just control itself. It'll do anything on your computer that any skilled human could do, but you don't have to be there doing any of it. And I really put this through its paces yesterday as I took about an hour long walk in controlling my home computer through my iPhone.
Jordan Wilson [00:01:23]:
And my computer at home was creating documents, using other desktop programs like Cloud Code, organizing my cloud storage, triaging emails, and drafting replies, and planning this very show by transcribing YouTube reviews and say bookmarks that I just didn't have time to get to creating images, all that stuff. I just gave commands and the work was just done. So, obviously, OpenAI can't call this thing Jarvis mode, but you can see how that that might be a more fitting description than the moniker of chat GPT Voice. But I will say this, I've used literally thousands of AI tools and features over the past four years of doing everyday AI, and chat GPT Voice has instantly become the number one most useful ever. So what is this chat gbt voice thing, and why is it so special, and why haven't you used it yet? Well, we'll break all those down as we put AI to work on Wednesdays on everyday AI. Alright. Here is the big picture. ChatGPT voice became an agent management interface.
Jordan Wilson [00:02:27]:
So this just came out. It has even been out a full week since OpenAI announced it, and it lives inside of the desktop version of chat g p t work and codex, which is the same thing, by the way. So chat g p t voice is powered by the new g p t live model. Little confusing, but we'll break it down. And that somewhat confusing rollout, I think, made for this being the undisputed, most criminally underhyped release in AI ever. Right? So as you see these, like, little releases come out and everyone's talking about it like, oh my gosh. This thing's gonna, you know, break how we all work. It's gonna take away all these jobs.
Jordan Wilson [00:03:02]:
It's gonna do all these things. Right? Check GPT voice, I don't think people are talking about it. Right? I'm very, ears to the ground, when it comes to these kind of things, and people should be talking about this and using this more, and that's why we're gonna be going over it on today's show. So stick with me for the next twenty five ish minutes, and here's what you'll learn. You're gonna know how the ordinary voice mode differs from the new, chat g b t voice launched inside work or codex. You're gonna know which evidence and approval rules that you need to keep authoritative sounding updates accountable because you can't just trust the voice and never go back to it. And I'm gonna give you the seven advanced chat gbt voice uses that you're gonna wanna start using and apply to your workflows, immediately. Let's get into it.
Jordan Wilson [00:03:54]:
Welcome to Everyday AI. My name is Jordan Wilson, and, well, this thing's for you. This is your daily livestream podcast and free daily newsletter, helping everyday business leaders like you and me, not just keep up with AI, but how you can use all of these updates. I tell you what matters. You go put it to work, grow your company and your career. So please, if you haven't already, subscribe to the podcast on Apple Podcasts or Spotify, and make sure you go to our website at youreverydayai.com. We're gonna be not only highlighting the big, takeaways from today's show, but also giving you all of the other AI news you need to know to stay ahead. Alright.
Jordan Wilson [00:04:30]:
So let's get into it. So, on Wednesdays, we put AI to work on Wednesday. So the latter half of this will be kind of demo based. So FYI, if you do wanna see the video version of this, it will obviously be somewhat visual because, if everything goes correctly, which for an unedited, unscripted demo, of a super smart AI taking over my computer. Who knows what could go wrong. Right? But you can always catch the video version of this on our website at youreverydayai.com or on LinkedIn, YouTube, Twitter machines. Alright? But let's first start with the two basic settings that you have to understand. It's kind of settings slash, you know, getting your mindset right on what's named what.
Jordan Wilson [00:05:15]:
And this is important, because there's a lot of confusion on this. Because most people are like, okay. Well, yeah. ChatGPT Voice, I know. It's it's not new. Right? I can just I've been able to talk to ChatGPT for a while. So yes and no. I I essentially wanna take you through four different phases or buckets of using your voice to interact with ChatGPT.
Jordan Wilson [00:05:36]:
Alright. So number one, dictation. That's been around for a very long time. Literally, some people think that that's what this is. That's not. So dictation. Right? You can click the little, microphone button, on the chat GPT interface, and it will you can talk, and it's just gonna turn your speech into text. That's dictation.
Jordan Wilson [00:05:53]:
That's not what we're talking about. Then there's the old voice mode, which was technically called advanced voice mode. There was a different voice mode before that. Alright? But that was more of the walkie talkie. Right? That's the turn by turn, conversation, mode. So that is what, you know, a month ago, that's what OpenAI had. That's what Claude has today. Nothing wrong with that, but that's not what we really want out of a voice mode.
Jordan Wilson [00:06:19]:
What we want is, well, the actual engine driving this, and that is GPT live. So that is what is called this kind of full duplex voice mode. So that means, and you'll see an example of this, the voice mode GPT live, can talk and listen at the same time. It can as it's talking to you, it's using another model in the background to call tools, look up information on the Internet. You know, maybe it's running a little bit of code to give you an answer to something that's not as easy to find as you might think. Alright. So that's that natural interruptible conversation. It's just like talking with a real human, but not like walkie talkie style.
Jordan Wilson [00:06:57]:
Right? So not to be confused, but that's not what we're talking about here. Right? That came out two weeks ago, and maybe you've already used that, and it's really good. This is different. This is chat g p t voice. So this is essentially that voice model, that full duplex and g p t live voice model, that has been available in chat GPT for about, you know, two two or three weeks now. Now that lives inside of chat GPT work or codex. So this is the, the version that you download on your computer. So there is no chat g p t voice when you go to chatgpt.com.
Jordan Wilson [00:07:32]:
I know that's confusing. That's gonna be using the GPT live. So chat g p t voice is available on the desktop version. Alright? And that's kind of where your, the thing that's Jarvis mode, right, where it can literally access all of your data. It can use your computer. It can do literally anything that a human sitting down in front of your computer can't. Whereas, you know, the normal GPT Live, the new smarter thing, it's cool to chat with. Right? But it's not gonna actually do your work.
Jordan Wilson [00:08:01]:
Now we all finally have a super smart, you know, coworker sitting down that we can literally just talk to, like, a real person. Alright. So that's kind of the, the iteration of the different types of voice inside of chat g p t. Alright. So basic setting number two, which I kind of talked about it. So chat g p t voice itself is just the g p t live model plus bringing in this agentic execution layer. So aside from it being able to actually complete work for you, which the GPT live can't really do, at least not fully, right. The difference here is it has access to all of your data and connectors, which GPT live doesn't.
Jordan Wilson [00:08:44]:
Right? So that's the one thing that is missing from GPT live that I was using it. Right. If you wanna say, hey, check my email or if you have some MCP servers connected inside of chat GPT, you know, it can't access those. It can you can upload a file to g p t live, and it will be able to go through and talk about that file, but it can't access all of your dynamic data. As an example, I probably have not a ton, right, because my tech stack is not super fat, but I probably have at least 30 different either connectors or MCPs. So now with chat g p t voice on the desktop version of chat g p t work or codex, I can instantly talk and grab data from any of those. But also, I can output or have the agent output work for me, but I can just command it all via Jarvis mode. Right? So here's how it works.
Jordan Wilson [00:09:35]:
Alright. You, the the ChatGPT Voice can listen, it can speak, and coordinate all at the same time and actually do your work. Alright. So there is a little button. Right? So if you hover over it, it just says start voice chat. So not to be confused, confused, with the button on the left, which is just the microphone button, which is the dictate button. Alright. So you're gonna start a voice chat in this little orb.
Jordan Wilson [00:09:59]:
Right? This little chat g b t orb. I don't know if there's an official name for it. I just call it the, you know, you can call it the voice visualization or just the orb. So I'm just gonna call it the orb. Alright? So that's when this, kind of chat g b t voice mode is, working. So also a little confusing. That's the same orb that comes on if you're just using g b t live inside of chatgpt.com. Alright.
Jordan Wilson [00:10:21]:
So you just gotta be using this if you're trying to follow along at home, which I encourage you to do. You know, make sure you're obviously using the desktop version of chat g p t work or codex, which again, a little confusing, is the exact same app. There's just a drop down at the top because people are always like, wait. I don't have codex. Yes. You do. It's Chegg GPT work. And people are like, I don't have Chegg GPT work.
Jordan Wilson [00:10:43]:
And it's like, yes. You do. It's codex. It's the same thing. Alright. So you have to be doing this inside of that download, the downloadable program on your computer. And, well, it's just neural. It's gonna be able to listen and run these models in the background and literally do anything that you can do on your computer.
Jordan Wilson [00:11:00]:
So, there's multiple layers and kind of the biggest differentiator that I think, versus, chat g b t voice in g b t live. The voice layer just talks. Now we have this new layer that we're combining it with all of the capabilities, of codex is it just is going to work. Right? It's gonna execute your work for you. And just for ease of, not saying the wrong thing too many times from here on out, I'm just gonna say codex. Alright? But it's the same thing as chat g b t work. Right? But there's too many, chat g b t's flying around, so I'm just gonna say codex. Right? That is the, version that you download and run on your computer.
Jordan Wilson [00:11:40]:
Alright. So let's quickly go into the seven advanced chat g b t voice uses, and then we're gonna go straight into the demo, and hopefully, it all works. But I'm gonna be doing some of these advanced, use cases as we go along. These are also kind of best practices as well. So number one, and this is, a difference in how these threads work. So you cannot go and pick up an old thread and start a new chat GPT voice conversation in there. Alright? You can't do it, unfortunately. That would be great if you could.
Jordan Wilson [00:12:17]:
Instead, you are going to, start a new chat. Okay? So whether that's inside of a current project or if you just go down and start a new chat that's not attached to a project. So, you can start any new chat, by just clicking the, start new voice chat button, and that's how you start. But here's the thing. Right? It knows everything and it controls everything. Alright. And that is just I can't emphasize how big that is. Right? I've done this many times.
Jordan Wilson [00:12:57]:
I've done live demos of it. I just checked again. Right? Co let's let's talk about Claude code. Right? Claude code doesn't know anything within what's happening under its own roof. Right? Unless it just happens to commit something to its memory, which it just does that haphazardly. Otherwise, it knows nothing. Right? So all of those conversations, you you know, let's just say that you're talking about Claude Coburg. Right? All of those conversations, unless it just commits something to memory, which, you know, maybe it does one to 2% of the content in there.
Jordan Wilson [00:13:31]:
If you start a new chat, it knows absolutely nothing, which makes something like claw desktop, in my opinion, extremely useless. Right? That's why I don't really use it. I mean, I use it to audit things that I build inside codex. Right? But the big thing with this new voice mode is it can understand any thread anywhere. Alright? So you can direct it to, hey. Go look in this project. Right? Find this project folder. So it can research any threads, see what was done, understand it.
Jordan Wilson [00:14:01]:
It can send a message to any of those threads. So it is just absolutely crazy how a voice mode because the old advanced voice mode couldn't do that. Right? Now you can't. And this is again combining the power of codex, with this technology. Right? So I'll just walk you through how I was using this on my walk this morning. I know the name of most of my projects inside codex, and I just said, hey. Walk me through every single major thread, in these, you know, project folders one by one at the end. You know, give me a a brief update and what next steps may be.
Jordan Wilson [00:14:40]:
If you're not sure of a next step, suggest one for me based on, you know, what you know about me, what's in my, agents MD file for that folder or for, you know, codex in general. So it knows my overarching goals and it knows the project goals. And then it's gonna go in there. It's gonna look at all that context and then just make me make decisions. Right? This is why I think on my walk, sorry, yesterday, I was more productive in that one hour on my phone, just talking in my AirPods, then I would have been probably in three or four hours doing the exact same thing in front of my computer. I talk about this all the time. The Internet is made to distract you. Right? And even for me, it can be distracting working in codex.
Jordan Wilson [00:15:24]:
Right? Because I have all my browser tabs open inside codex. So something about just the combination of rambling and being able to control any of these threads, and just having that real focused time. I have so much done, right, in in that one hour walk. But anyways, kind of advanced tip number one is know that you can, with your voice, any new chat can understand, read, write, and do anything to any thread. So it doesn't really matter. For me, from an organizational perspective, I would really like to just be able to go into a certain thread and pick it up from there. Right? I have all these, chief of staff threads inside of each project folder. That would be preferable for me because I like things to be a little organized.
Jordan Wilson [00:16:08]:
Right? And then you have this chat that's down there in your recents. But overall, it's okay because when it does make changes, it will actually go in there and send a message in those chats. So it's not like it gets lost, and I do have another advanced tip later that can help with this. Alright. So, number two, GPT Live can't use connectors, and codex with chat GPT live can't. So I already referenced this, but this is huge because GPT live by itself, it's great. Right? It's more of, I think, an advanced party trick, and I do hope, and I know the team has alluded to this online that they are going to eventually bring connectors to GBT live. But at least for me and how I want to use, you know, try GBT, I need it to be connected to those, you know, 30 or so, you you know, connected integrations and MCP servers.
Jordan Wilson [00:17:01]:
Right? If not, it's just, you know, a better way to browse the Internet, which is fine. Right? But I really want to use this to get work done. And that is why this combination inside codex is amazing. And I don't know why. I literally didn't see anyone talk about this or reference this. Right? I've you know, I follow the the chatter and, you know, I've watched a couple videos of people giving their, opinions on this, and no one is mentioning this. Right? This is the biggest unlock right there to be able to go and go through your entire inbox, to go through your, you know, everything in Slack and and to be able to talk about it and just say, yes. Send this.
Jordan Wilson [00:17:36]:
Yes. Draft this. No. Save that to my Google Drive. Right? Just to be able to go through all those things, it is it's this is what people have been wanting for so long. This is the Jarvis. Right? Hey. What's important? Go look in all of, you know, go look in my in my CRM.
Jordan Wilson [00:17:52]:
Go look in my, I don't know, ERP, alphabet soup, whatever you wanna say, my my my drive, my linear, whatever programs you're using that are connected inside codex. Go through all those, triage those, ask me what you want, you know, what are the most important decisions I need to make? And if you have read write access, right, you can just start making those decisions in codecs and actually just go do the work in those programs for you. Alright. So that's number two. Connectors is a big unlock. Alright. Number three. You can schedule, right, the same way that you would inside of JetGPD.
Jordan Wilson [00:18:30]:
So, yeah, this is another one of those things that you can't overlook just that you're using voice mode. You can't overlook just the normal power of JGPT. Right. So one of the things, if you use chat GBT online or, the chat GBT work online, is you can have repeatable tasks. So even when you're talking, right. I did this a couple of times. I'm like, ah, I'm gonna keep missing this thing. Right? So, you know, I said, hey.
Jordan Wilson [00:19:00]:
You know, every, you know, Monday at 7AM, you know, run this task. This thing that we just did together that, you know, me and, Che GPT just collaborated on via this, Che GPT just collaborated on via this, Che GPT voice, That needs to be run, you know, every Monday morning or every Friday afternoon or, you know, every day at 4PM. This what we just did, let's turn that into a skill, and then let's, have this be a scheduled run. So another big, thing. So, you know, as an example, maybe every single day you wanna go in through and see any new lead that's come in via HubSpot. You want to enrich that data with Clay and then, you know, use the condo MCP. That's one I use to help manage my LinkedIn messages to see if you have a LinkedIn connection with those people. Right? So you can literally do that all via voice first.
Jordan Wilson [00:19:47]:
It's gonna learn how to do it all, and then you can say turn that into a skill, run that every single day at 9AM, and then you can literally, once it's done, go and talk and be like, hey. What happened here? Right? That process right there as an example, going into your HubSpot, seeing who's new, going in, enriching all that in clay, and then, you know, seeing which of these people. Right? If especially if you're in b two b enterprise sales or SaaS to sales. Right? You know? And you have a big LinkedIn network, you know, like I do. That's something that takes a lot of time to do all those things manually. Right? That might be every single day. I don't know if you're an SER, BDR. That might be a third of your day.
Jordan Wilson [00:20:24]:
It can be done for you. Right? Set it up once in chat GBT voice, set it up as a schedule, and then every day, you can also be like, hey. Check-in. Walk me through. Give me a game plan on this. And, you know, in a ten minute, Cheggi p voice conversation, you've already done what would have normally taken you three hours and ten minutes. Alright. Let's go next.
Jordan Wilson [00:20:42]:
Number four. Stack multiple tasks at once. Yeah. You don't just have to give one. You can just kind of ramble on and just keep giving more and more assignments. You know? As you are going back and forth, remember, sometimes chat g b t will interrupt you. You can interrupt it, which is actually fine because that's how a normal conversation goes. Right? Normal business conversation, sometimes you just interrupt each other.
Jordan Wilson [00:21:05]:
Right? You might not do that in a big business meeting or if you're meeting with the president of the company. But if you're working with colleagues or people on your team, you probably interrupt each other all the time. Because if you see someone's going down the wrong path, you don't necessarily wanna give them thirty seconds or three minutes to keep going down that path. You're like, oh, no. No. Wait. Hold up. That's not what I was talking about.
Jordan Wilson [00:21:24]:
Let's let's rewind a little bit. Right? You can do the exact same thing, but also just stack those multiple tasks, and the voice will just only return when it needs more, information from you or when it has updates. Alright. The big unlock here, use your iPhone. My gosh. But it's a little tricky because remember. Alright. Codecs doesn't have an app.
Jordan Wilson [00:21:47]:
It is in the chat g p t app. So confusing part here. If you go into the chat g p t app and you're looking for that, little button I told you to push, that's just gonna launch g p t live, which is not what you want. So you're gonna go onto your iPhone. You're gonna click remote. Then at the bottom of the screen, you're gonna click that, that button to start a, Chatt GPT voice. Alright? So don't just open your, ChatGPT app on your iPhone and click the voice chat button. You need to first click remote because that's essentially then at that point, and this is what I was doing today, that's how you are literally on the phone.
Jordan Wilson [00:22:25]:
Right? For me, quite literally hands free. I had an AirPod, you know, one AirPod in my ear, and I was literally controlling my entire computer working on multiple projects. Right? Going through all those folders, and it was downloading, uploading, opening programs, changing things, doing the things that I would normally be doing, doing it all hands free. Just giving, you know, my my Jarvis instructions. Alright. Alright. Number six. A spoken update is not proof.
Jordan Wilson [00:22:53]:
Alright. And I talked about this earlier. You should require a durable artifact. What does that mean? Alright. When you go back, especially right? And this is something I really found yesterday morning. I was looking back through the the, transcript of what I said, and I'm like, wait. How did we get this done? Right? Because sometimes all you get is what you said and what Chad GPT said. So, you know, one thing I would encourage you to do in this voice conversation or, you know, you can leave this in your, agents MD file inside of any project folder is just say, hey.
Jordan Wilson [00:23:24]:
Always require written evidence when you're done. Right? Or, you you know, build a, you know, an outline every single time that you complete the tasks. You know, make sure you outline what was done. Or maybe you have a folder, a file, you know, whether it's locally, etcetera. Every time you, you know, complete a run, complete a task, complete a project, upload this file, and say exactly what was changed, what was done, where the file location is, etcetera. That's huge. You always need written evidence because, yeah, it's nice to be able to just flow with voice mode, but sometimes you need that data. You need that data.
Jordan Wilson [00:23:59]:
Right? Maybe you want it in a markdown file. Maybe you wanna upload it to your Google Drive. Maybe you just want it in line in the in the thread inside codex, right, as a bullet point, but you need that written proof. And then last but not least, and this one's really cool. Another one that I haven't seen many people mention, but there's literally on the desktop version, If you click that little orb, you can drag it. All right. And you don't even have to have codex kind of active or open on your screen. This is one thing I'll hope I'll be able to, to kind of demo.
Jordan Wilson [00:24:33]:
But all you have to do is pull the little orb, away. Right? Which it's kind of hidden. Right? You don't even know that you can do it. A lot of times, right, one thing I do when there's new features, I just click around because, you know, OpenAI is known for, you know, hiding little fun Easter eggs. You know, if you're talking about, like, codex pets or anything like that. But, yeah, I just clicked, and I was like, You can drag this thing. Right? And then I saw maybe one or two other people mention this. But, yeah, for the most part, you can just have that little orb just chill on your desktop, and you have this omnipresent agent that's just gonna chill.
Jordan Wilson [00:25:09]:
It's gonna do absolutely nothing until you tell it to. Right? So one little, little, I guess, not cheat code, but best practice for this, especially right? I like to listen to music a lot, and you can't really do that because it's listening for any word. Right? So I will just have an AirPod in listening to music. And then on my Mac, I just, you know, set the output to my AirPod so I could still listen to music or be on a call with a colleague. Right? Something like that. And then I can still, you know, I can still mute the mic, but, if it's just me in front of my computer, that's all I really need to do. I can listen to my music in, an AirPod and use my my, my computer microphone to then talk to the orb. Right? That sounds weird talking to an orb.
Jordan Wilson [00:25:54]:
Alright. But it just, allows you to have that omnipresent agent. Alright. My gosh. What could go wrong? Here we go. Let's go live. I'm not I'm not gonna lie. Sometimes, especially because I I have a lot of, more, kind of, private, you know, personal private information in my codex.
Jordan Wilson [00:26:14]:
You know, sometimes when I'm like, oh, I gotta share my my entire codex. I'm, you you know, sweating bullets a little bit, but I I always want you guys to see, you know, see how this, goes live and kind of, see how it works. Alright. Let's try this live live stream audience if you could. Let me know if you can see my screen. Alright. And hopefully, we'll be able to hear the audio as well. So, as a reminder, this is the and, yeah, if you do wanna see the video version of this, if you're listening to the podcast, in the show notes, there's always a link to the episode page on our website.
Jordan Wilson [00:26:51]:
You can go watch the video version. So just skip to, you know, I don't know, about twenty six minutes or so. Okay. So at the bottom here, you'll see, there's a normal microphone. Don't click that. That is the dictation. The other one is to start a new voice chat. Alright.
Jordan Wilson [00:27:09]:
So let's just go ahead. I'm gonna go to, make this an unattached chat thread, and then I'm just gonna riff a little bit here. Alright? So if you hear me talking, I might hit the pause, the mute button so I can keep talking to you all and explain what's going on. But, otherwise, assume that I'm just talking from here on out, to chat GPT. So let's get it going. I'm gonna actually, work on a project that I wanted to do because I put a lot of work into a recent, speech that I did, and there were some things that happened in there that I'm like, I should probably pull that, and do do something more with that speech that I did. So, let's go ahead and get started here. Gotta love the live demos.
Jordan Wilson [00:28:06]:
I've literally never seen this, this screen come up before where it said voice chat couldn't start. That's funny. Alright. Let's try it again. Hey.
ChatGPT Voice [00:28:19]:
What would you like to try again?
Jordan Wilson [00:28:21]:
Alright. Cool. No. So, can you look it's maybe in my downloads folder, but, maybe from, like, two or three weeks ago. I did this presentation for Affirm and, there's probably like a PowerPoint. It was about, ChatGPT work. Let me know if you can find it.
ChatGPT Voice [00:28:42]:
I'll check your recent presentation files for that.
Jordan Wilson [00:28:46]:
Alright. So
ChatGPT Voice [00:28:46]:
chat GPT work PowerPoint in your downloads so you can open it from the file card on your screen.
Jordan Wilson [00:28:52]:
Oh, cool. Great. So can you just kind of go through and bullet point what I talked about and what I didn't? And then while you're doing that, can you also open, Chrome and then go to YouTube and find the live stream that OpenAI did a couple of weeks ago for the chat GPT, work announcement. It's probably, like, two weeks ago or so. And then copy that link, from that OpenAI live stream, and then use computer use, and open up an app on my computer. It's called Parrot. It's an app that I built. And then I want you to take that YouTube, URL from the OpenAI live stream, and I want you to paste it into Parrot and create a transcription.
Jordan Wilson [00:29:42]:
And I want you to look at that transcription, which will tell you, you know, what they talked about in that thirty or so minute live stream. And, essentially, I want you to look and find, what I did not cover, in my Affirm presentation that was covered in the OpenAI live stream. So, just take take your time and start working on that.
ChatGPT Voice [00:30:04]:
I'll get started on that. I'm comparing your Affirm deck with the OpenAI work launch stream now using Chrome and Tera for the transcript.
Jordan Wilson [00:30:15]:
Alright. So I just put this on mute, so you'll probably still hear Chegg GPT. Oh, it's not on mute. All right. There we go. I think, I think I'm on mute now. I'm not, I have no clue what's going on. Okay.
Jordan Wilson [00:30:35]:
That's that's weird. Another time, this it's it's it's showing the transcript here, but, obviously, I'm talking to the live stream audience now, not Chad GBT even though it's still, transcribing. So, hey, Chad. Are you still listening to this? Okay. Interesting. Love love doing these, love doing these these live streams, here. Because I I always run through and do the demo, and then I always get these weird things that that happened that didn't happen before. So, it was muted, but it was still, dictating what I was saying, which, didn't happen in all of my testing.
Jordan Wilson [00:31:21]:
Anyways, so let me explain what I did and what's happening now because it's already opened up this program that I created called Parrot. Right? Just as, awesome program that I've, you know, built up over the past, however long. So I told it, go find this presentation I did two weeks ago. I don't remember what was in it, because I literally had to build it, like, rebuild it the night before because it was right when OpenAI announced chat g b t work. And I didn't remember if I got everything from the live stream into that presentation, and I thought that maybe at some point, I'll do an entirely new course or something like that, on codecs or CHAD g b t work. So I'm like, well, I put together a lot of work in this presentation, and I thought it was pretty good. But there's probably some things I didn't get to. So what's already happened is, codecs went in or CheggiBTE voice inside codecs went in.
Jordan Wilson [00:32:18]:
It opened up this program that I built. It grabbed the, the URL, and it went in and pasted it. It looks like it has the transcript up, and we'll see what's what's happening here.
ChatGPT Voice [00:32:33]:
The parent transcript is captured, so I could ground this in what they actually covered. Here's the quick take. Your deck focused on the desktop agent and agents MD workflow. The stream emphasized connected workflows and shareable outcomes. Those connectors across Slack, Calendar, and Excel to PowerPoint to
Jordan Wilson [00:32:51]:
Can you maybe just give me people. Can you maybe just give me bullet points? Didn't cover. Can you maybe just give me bullet points of the biggest things that I did not cover in my Affirm presentation that was in the live stream? Sure.
ChatGPT Voice [00:33:15]:
The biggest things you didn't cover were connected work across tools like Slack, Gmail, and calendar, end to end finance workflows like Excel to PowerPoint reporting, interactive sites for dashboards or internal tools, starting tasks on mobile
Jordan Wilson [00:33:31]:
That's a good point. Go down. I think that there was a new update a couple, like, maybe it was Thursday, but I don't even think OpenAI put anything on their website about it. It was something in sites. So see if you can look up maybe their, change log for codex or sorry, for sites. I think it was something about there are some new analytics. Can you look that piece up?
ChatGPT Voice [00:33:54]:
Yeah. I'll check that.
Jordan Wilson [00:33:57]:
Also, look in my, transcripts for your everyday AI, because I you know, every Friday and Monday, we go over kind of, like, new features and new updates. So can you just check this, the last week's, shows? Because I think there were a couple other, codex updates in there. So you can just, you know, open that up, or I think there's a folder, on my desktop if you wanna or not my desktop, maybe in documents, if you wanna use computer use, or you can just go to our website and look at the transcript there. Because sometimes they only update their, kind of change log, like, once a week. So we obviously put out shows, you know, every day. So just go, specifically on sites. I want you to get more information on that.
ChatGPT Voice [00:34:46]:
Got it. I'll check the official notes, the site's docs, and your recent transcripts for anything site specific.
Jordan Wilson [00:34:53]:
Okay. And while you're doing that, or maybe first, can you just, create a very simple, document and then just download it and save it to my computer? That just shows kind of what I talked about in the Affirm presentation and then what I did not cover. Just kind of download that to my computer, but also save it to my Google Drive just so I have it and then, you know, name it so it's easy for me to see and understand what's in there too.
ChatGPT Voice [00:35:21]:
Got it. I'll put that together and save it both places.
Jordan Wilson [00:35:27]:
Okay. So I realized what I did wrong now, guys, earlier. When I'm like, wait. I it's still catching me speak even no. That was a human error. I accidentally, turned off the speaker, instead of the microphone. So that was my fault. So right now I have both muted.
Jordan Wilson [00:35:47]:
So, you know, JGPT is still talking to me, but, it's not super important. You know, essentially, I just wanted to show you those capabilities because what just happened even though I kind of fumbled through that demo quite a little bit. Right? This is something I was gonna do because I knew I put together, like I said, a lot of good information from this, Affirm presentation. Just going over the some of the features, you know, I had some good visuals, some good content, all that stuff. Right? So why would I start from scratch? But I knew that there is new things that needed to be updated. I didn't have thirty five minutes to go rewatch the, you know, chat g p t livestream. So I just had it literally, use its built in browser. Go find the YouTube channel for OpenAI.
Jordan Wilson [00:36:29]:
Find that livestream. Take that link. It opened up a program that it wasn't even pinned to my desktop, so it just found it. It opened up the program that I built. It transcribed it, and then it compared, kind of everything that was in that PowerPoint that it opened in its file browser, to the transcript, from the opening a live stream. Now, right now, it's putting it together, and it's already it just told me that it's, put that document together, and it's done. So that's good. And it also said it confirmed the missing sites update.
Jordan Wilson [00:36:58]:
So alright. I I do wanna show maybe one or two other things quick. So I'm gonna start a new voice chat, and here we go. Hey. Can you, use the Beehive MCP and look at my, poll from yesterday, and tell me what the results from the poll were.
ChatGPT Voice [00:37:29]:
Yeah. I'll check yesterday's beehive poll results quickly.
Jordan Wilson [00:37:37]:
Alright. So I just muted chat, but, what I'm showing for our livestream audience here is I'm actually minimizing. I'm gonna minimize codex here, and you'll see here kind of this little orb, floating around on my desktop.
ChatGPT Voice [00:37:53]:
OpenAI's new Jarvis live mode is leading with 32. Claude Opus five hands on has 21, and six people picked other.
Jordan Wilson [00:38:03]:
Okay. Could you just start that over? I missed the beginning. Sure.
ChatGPT Voice [00:38:09]:
Yesterday's AI working Wednesday's poll has 59 votes. OpenAI's mute Jarvis live mode is leading with 32. Klon Opus five hands on has 21, and six people picked other.
Jordan Wilson [00:38:24]:
Cool. Can you tell me, what my open rate was yesterday, or sorry, on Monday, July 27 versus the Monday before that. I just wanna see kind of what the open rates were over those last ones.
ChatGPT Voice [00:38:42]:
Okay. I'll pull up both Mondays and compare them.
Jordan Wilson [00:38:46]:
So, essentially, what I'm doing right now, I just muted both, is well, I got rid of codex, and now I just have this little floating orb here. Right? So I'm dragging it around my screen. I can put it literally anywhere. It's showing me, even though I haven't muted, what the open rate was. It says, this yesterday or two days ago, it was about 55%, and, the money before it was 58%. That's still because, you know, opens keep, trailing in a couple of days after. So, pretty cool. You can see right there, some of the basic things.
Jordan Wilson [00:39:18]:
So I went through showing you, multiple tasks at once, kind of stacking those using different connectors and MCPs. Right? I used my, you know, Google Drive that's a connector. I used an MCP, which is a model context protocol for my newsletter because it doesn't have an official chat g p t connector. I, you know, did things like browsing the web, you know, pulling, you know, opening other programs on my computer. And, you know, it was clicking around, you know, you probably saw it. It happened very quickly because computer use is very fast inside GBD five six soul. So that's a wrap for the demo portion. It didn't go too bad.
Jordan Wilson [00:39:59]:
Right? Maybe we'll see how this actually turns out. Hopefully it recorded all that audio. But here's the takeaway. This is a completely new way to work. Right. In almost a new way to think about work. Right. Because even before, right.
Jordan Wilson [00:40:22]:
Honestly, like even just ten days ago before this update came out, for the most part, when I wanted to be the most productive, I was still sitting in my chair and, you know, clicking around. Right. Which is not bad necessarily. Right. But distraction overwhelm. And sometimes what I found is when you're not actually looking at a screen and when you're able to just kind of ramble and yap. Right. Sometimes you get much better results because you can communicate things sometimes in a much clearer way.
Jordan Wilson [00:40:58]:
Because sometimes, especially if you're typing, right, not everyone can, you know, especially if you work in an open office, you can't always ramble. Right? Or if you're working on something private, maybe you work at home and you can't, you know, talk about certain things, you know, with other people around. This is something that for me, I I'm not saying I I've struggled to adjust how to work, but I've I've had to rethink what it means to work. Right? And I had a great day working. Right? I had a great day working yesterday. Went out and, like I said, took an hour walk, and it was not only being able to go get outside and touch grass here in Chicago, I actually think that I got a lot more done in that one hour than I would have gotten done two or three hours doing something very similar using codecs or even Chegg GPT Voice in front of my computer with all my screens because it's distraction. And then I would have said, oh, I I have to go do all these other things. Right? So it is definitely the new chat GPT Voice is like having a Jarvis.
Jordan Wilson [00:41:58]:
And at least for me, I'm even though I've been codex pills since the day it came out, sometimes I still find myself still doing some of the work. Right? And this has been a refreshing, change in that because I'm actually just using my brain and thinking a little bit more, trying to think more strategically and creatively, and, you know, being able to communicate things in a different way and, you know, being able to describe all the nuance and, you know, having CheggiBudd voice sometimes poke holes in my plan. So it's been for me a lot more talking and iterating and working through my voice, which for me is really easy and maybe it will be for you. But I hope this episode was helpful. Maybe this won't be for you, but there's a good chance that using the new chat g p t voice is could be the biggest paradigm shift in how you've worked since maybe chat g p t came out or even more so than that. So, thank you for tuning in if you haven't already. Again, please go to youreverydayai.com. Sign up for the free daily newsletter.
Jordan Wilson [00:43:02]:
Thanks for tuning in. We'll see you back tomorrow and every day for more everyday AI. Thanks, y'all.