NEW Hermes AI Voice Agent is INSANE!

Hey, how's your day going? Quite smooth, sir. Efficient and pleasantly uneventful, just as I like it. How may I assist you today?

Yeah, I'm doing great. Could you give me some ideas for like keywords for SEO? Certainly, sir. A reliable approach is to mix a few types.

Broad phrases that describe your main offering, long tail phrases that match specific customer needs. Actually, stop. Can you just open up Google? Perfect.

Can you tell me a joke now? Ah, certainly, sir. Why did the scarecrow win an award? Because he was outstanding in his field.

Can you teach me a couple of phrases in Italian? Certainly, sir. Here are two handy ones. First, buongiorno, meaning good day, pronounced buongiorno.

Second, per favore, meaning please, pronounced per favore. They'll serve you splendidly in most polite situations. Fantastic. I tell you what, could you just build me out a website for my SEO agency?

Very good, sir. I'll put together a clean, professional agency site concept now. So I'm just going to move that for now, but you can see here that it's building out the setup. As you can see, I'm going to switch that off now.

But essentially what this can do, this is Hermes Apollo, which is a custom made voice agent that would build into our agent offering system. We can put it in wall mode so we can have it in full screen. We can see everything that we've spoken to it about. We can see the latency details over here and it looks really beautiful.

We can also switch real time on and off and we can have a wake word, which means for example, we can say, uh, for example, Apollo, and then it will wake up automatically instead of having it listen and reply to everything that I want, whenever we want. Over here, you can see that we've got the full script of us going back and forth. And then we have everything that we've built with the AI agent as well. So it is very, very quick to reply, the fastest I've seen.

And we're using something called chat GPT real time API to build this system. And this system is something I call the Apollo voice command agent. So what we have here is Hermes plugged into my Apollo voice agent, which is basically a butler that lives in your agent OS and it can run your computer by voice. Right?

So you can talk to it. It can act, it can open up websites. It can open up apps. It can build real working apps, games, tools, apps, uh, or, or whatever you want whilst you watch hands-free in real time with no clicks, and there's no lag on it as well.

So here's exactly how it works. Now, the first thing that I would say here is that there's a bit of a keyboard problem going on right now with AI. So we all know what we want with AI, but typing and everything else is a bit of a drag, and then also if you're like doing something else in the background, you know, quite often we're coding with like multiple terminals, multiple agents, and that sort of thing. With this system, really the way that I would look at it is that you can run your whole day without having a keyboard.

So think about like the last hour at your desk, for example, maybe you wanted something, uh, maybe you wanted to create a tool, check something, spin up a quick website, whatever it is, and you have to type it. Uh, whereas with this system, you don't need to worry about that. Right? So when you actually do want to make something, you're, you're not staring at a blank editor with your hands on the keyboard, you are just instantly commanding your agent to go off and do stuff for you.

Now, some people say like, you know, voice agents, aren't they just a gimmick? But this one is actually built inside a system that you can use every single day. Right? So we've got the AgentOS, we've got all of our different tools over here.

So for example, we have GPC 5.6 plugged into Cloud Code. We have Hermes Agent with the chat over here. We have Hermes Oracle that's refreshing every 24 hours and coming up with the latest news headlines and researching my competitors and latest keywords inside my niche, and then we have Hermes Apollo that can reply to me in real time. And so this is a voice, fast brain, and a pair of hands.

And there's three pieces to this. So number one is your voice, the input. You just talk out loud, like you talk to an assistant in the room. There's no wake word to remember, no button to hold.

Uh, Apollo is just always listening whilst the panel is open. Then you have a real time brain in the middle. Now, real time means there's no awkward pauses. With most AI voice agents, it's super awkward.

Uh, you type, you wait, you read a reply. Apollo is basically like a live phone call style conversation. The moment you stop talking, it's already answering in a natural butler's voice. So under the hood is OpenAI's newest live voice model, but you never touch any of that.

You just speak. And then also you have a pair of hands, the output. So this is the part that makes it more than just like your typical agent or your typical back and forth chat. Apollo can actually do things on your computer.

So if you say open Obsidian, it'll open up. If you say, for example, pull up Google, it'll actually open up Google. If you say build a landing page for my course, it'll actually build and write the whole thing and then show it inside the gallery so it doesn't just talk about doing it, it actually does things, which is something I've seen no other voice agent do. You can see some examples of the commands that you can do that.

And the other thing as well, like you can just talk to it in a very conversational way, you can interrupt it at any point, it replies very, very quickly, and you can go between like idea to getting something done very, very quickly, which is pretty amazing. So you speak, it hears live, it picks a tool, it asks, it confirms. What we also have inside Perme's Apollo is the option to switch between agent mode and just auto mode. So auto mode was what I showed you before, but there's also agent mode that can even like, for example, write files and use different tools and everything else locally for you.

And you can switch between the voices over here as well. So it's really, really powerful. It's a full system here. So you don't type the command anymore.

You just say it and the machine does the rest. Now this is already inside the agent OS as well, which means that the great thing about this is if you're using a voice agent or if you're using Claude and then ChatGPT, especially with the new updates, like I I've seen people getting confused with all of these systems. With this setup, you have everything ready to go inside the agent OS. So you don't need to worry about getting confused about different features.

You can switch between tabs very quickly. You can hide stuff if you don't want to see it anymore. And then if you want to go to Apollo, you just go to the Apollo tab, super easy and simple to do, and you can just do that in one click. Now you also might say, is this listening to me all day?

No, because you can switch it off. And if you switch between tabs, it will automatically switch off. So it's only activated when you want to activate it. It's only listening when you want it to listen.

And the great thing about this is for the small stuff, you know, I don't need to use my keyboard. I can just have this voice agent running in the background. It's working whenever I open it up and it's good to go, right? So it's a butler working for you in real time, 24 seven.

So this is the Apollo voice command engine. So the voices you stop typing and clicking, you just talk hands-free, no wake word, no button. Then you've got the real time with chat GPT, uh, live API. Then you have the hands.

You stop doing yourself, uh, stop doing things yourself. So if we switch this back on, for example, we'll switch on real time here. And if I say something like open up obsidian, it opens up right. Very, very quickly.

So it replies very quickly and we can just switch off the real time. So it stops listening to us as well. And then we also have the hands. So you stop doing things yourself.

Like it can open up the apps. And also if we go to the memory section over here, everything that we do with Hermes Apollo is logged inside this section. So that for conversation that we just had is logged inside our obsidian vault, and that fills out the knowledge inside our memory galaxy. So it's all linked, um, beautifully organized inside one place.

You also might say, well, doesn't this use a lot of tokens? So you can actually run the agent OS itself on free models and free systems if you prefer. So for example, we've got the memory galaxy and that uses obsidian, which is free. We've got Hermes agent, and that can use HY3, which is another free API.

So like, if you prefer to use just free APIs and go around it that way, you can, right, you don't have to worry about tokens that way. And if you look at the old way versus a new way here, the old way is like every small task you have to type, click, repeat, and you've got like thousands of tiny clicks, just quietly eating up your whole day, but you feel like sometimes you just click in between tabs and type and stuff, and that takes up a lot of time and energy. Then also, for example, if you want a quick tool, you have to go back to an IDE or you have to open up Claude or whatever and mess around with it. Whereas with this system, you can say, open that and it opens.

The voice replies very, very quickly, faster than any other AI that I've seen really, when it comes to voice agents, you can say, build me something and it'll actually just build it in about 90 seconds. It's completely hands-free. So you could be drinking your coffee and it will still keep in flow mode. And also everything is saved inside the memory.

So you can see everything that you've built, right? So for example, if we want to go back and see our recent creations with Hermes Apollo, all we do is we just scroll down and you can see everything that we've created over here, right? So that page that we were just talking about a minute ago is already built, and we can actually open that up in full. But the great thing about this is we never lose anything, right?

Cause it's all saved inside one place and it's ready to go. And it's much easier to organize. This is far more organized than if I was going into Claude and then chat, cheaper tea, and then Google and everything else, right? Way faster.

You also might say, well, is it real time or does it lag like Siri? This is way faster than anything else I've seen using this API. And you might also say, you know, I'm non-technical. Can I actually set this up?

So all you need is the API key from chat duty, which is, you know, anyone could do that. And then for the agent OS system, we have 198 pages of people building this stuff out and getting amazing results with it. So for example, Carl, he built his own agent OS. He just joined recently.

You can see, for example, that loads of people are building out the agent OS and getting awesome results with it. Like for example, Shin, he was saying the agent OS system is by far beyond the worth of value it provides. Rick said he joined the school in within 30 minutes. He set up the agent OS.

So like loads of people are using our system. I'm non-technical as well. I'm not a coder and I can build this out as well. So if you want to get it, it's all, all it's inside the AI platform community.

Of people say, well, talking to the computer is a gimmick, but this is way faster and it actually works. Like I've proven in many different scenarios, it works and it's way more powerful and neatly organized as well. And then some people think like you actually have to sit down and code to build apps, but actually you can build apps in like one single voice command. As you saw with this website, we just built a second ago.

So if you want to get this whole system, you can get it inside the AI profit boardroom, you get the Apollo voice command engine, you get the full agent operating system zip file so you can install it with Apollo and every tool. Pre-wired in ready to talk to you get coaching calls where we can set up the voice butler together, step-by-step you get free local models as well. A room of 3,900 operators running this exact stack and daily tutorials, a 30 day roadmap and amendment map for your city. So you can get it all inside the AI profit boardroom.

If you want the agent OS, just go to the classroom, then go to agent OS over here for the full system. And then you can see, we add new daily tutorials based on what's actually useful. Inside the community, you can ask questions, get help and support real time. And then inside the calendar, you can jump on weekly coaching calls, share your screen, ask questions, meet other members inside the classroom.

You also get all of our best trainings. And then in the map, you can meet people in your local area who are building with the agent OS and other systems like it. So thanks for watching. That is Hermes Poly, Apollo.