← Back to search
Hermes Jarvis Just Changed AI Forever...
AI News Today | Julian Goldie Podcast · 2026-06-22 · 8 min
Show full episode description
Hermes Jarvis: A Real-Time Voice Agent Built on Hermes + Obsidian (Daily Briefings, Wake Word, Fast API)The script demos a real-time, voice-activated version of Hermes called Hermes Jarvis that can respond instantly, open apps like Google and Obsidian, and deliver daily briefings using memories stored in an Obsidian vault, including open items, recent work, what’s on the user’s mind, and news headlines with saved briefing history. The narrator shows conversation history, built-in features (including a meditation app), wall mode on a separate monitor, wake word activation, voice switching, link-reading from chat, and the ability to interrupt Jarvis mid-speech. They explain the system was iterated for weeks using Claude and Claude Desktop and note ChatGPT real-time API replaced ElevenLabs due to speed. The episode ends by inviting feature requests and promoting access to the full setup via the AI Profit Boardroom.
✨ Episode Outline — click any point to jump to it in the episode
Problem solved
Turning
Hermes into a real-time, voice-activated AI assistant that delivers briefings, builds apps, and responds instantly.
Benefits
- Instant real-time voice in/voice out responses
- Daily and weekly briefings from Obsidian memory
- Interrupt mid-flow like talking to a person
- Wake word and tap-to-talk arc reactor modes
- Reads links sent in chat and reports back
Use cases
- Daily briefing pulling open items, notes, and news headlines from Obsidian Vault
- Read a shared JulianGoldie.com link and describe the live page
- Built a meditation app and other apps via live preview voice commands
- Switched languages mid-conversation: Chinese, then Swahili
- Stores briefing and conversation history for review over weeks
KPIs / results
- Built over weeks, ~4 hours/day of iteration
- 60% of US consumers say AI brand messaging is a turn-off
📑 Chapters — tap a time to jump there
00:00
Jokes and Languages
- Voice demo: jokes, switching between Chinese and Swahili
00:44
Opening Obsidian Briefing
- Opens Obsidian; briefing lists open items and news
01:40
Hermes Jarvis Demo
- Hermes Jarvis: real-time voice Hermes linked to memory
- Knows date, open items, recent work; stores briefing history
03:00
How It Was Built
- Built over weeks via Claude and Claude Desktop iteration
03:28
Speed and Tooling Tips
- Use ChatGPT real-time API; 11 Labs was too slow
05:15
Architecture and Features
- Weekly briefings, voice switching, reads chat links
- Builds apps with live preview; works across any model
06:26
Interrupt and Wake Word
- Wake word, arc reactor tap-to-talk, mid-flow interrupt
07:20
Build Voice Agents Now
- Encourages building voice agents now; best time ever
07:27
Join the Community
- Get setup inside AI Profit Boardroom community
Open up Google. Open Google now, sir. Tell me a joke. Very well. Why did the computer go to the doctor? Because it had a virus. That's not very funny. Give me a funnier one. As you wish, sir. How about this? Why don't scientists trust atoms? Because they make up everything. Tell me some words in Chinese. Certainly, sir. 你好。希望你今天过得很好。 Stop, stop, stop. Actually, could you start speaking Swahili with me? Certainly, sir. Let's switch to Swahili. 乌口太亚的关子吗? Could you open up Obsidian? Obsidian is now open, sir. Good afternoon, sir. Nine open items and nine notes in motion, sir. First up, Volt LLM Wiki Restructure. Finalize Atomic Note Layer. In the news, 60% of US consumers say AI and brand messaging is a turn-off. All right. Nice. Nice. One sec. I'm going to send you something in the chat, okay? Understood. Sir, I'll be ready to take a look once you send it. Can you see that? I've opened JulianGoldie.com for indeed, sir. I can see the website layout on your screen. Everything appears to be loading smoothly. So I'm going to switch off, but that's basically Hermes Jarvis, which is blowing my mind. This is a voice-activated version of Hermes that were built, and it responds in real time. It's fully working. It seems to work really well. The only thing I don't like is it doesn't have access to Obsidian in real time, which is something I'm actually building on it. So I just want to be 100% transparent with you. But it can do daily briefings like you can see. It knows the date. It knows the date. It knows what's open, what we've worked on recently. All of these are different memories inside our Obsidian Vault. It's actually linked directly to my memory folder. And also what you can see here is that it has a list of what's on my mind, recent headlines in the news, which is pretty cool. And it actually stores these as history. So if we go to the history, we can see our previous briefings here. We can click on them. We can view previous briefings over the last few weeks, and we can see our history. Now, not just that, but if we actually scroll down here, you can see our conversation history. And then if we actually scroll to this section, you can see everything that we've built with Hermes inside the voice mode. Whereas it's even built, for example, like a meditation app and all sorts of cool stuff. So my point here is like, this is a real time voice activated version of Hermes. And what we can do is we can actually have a wake word or we can set up in real time. Now, the way that I've built this is basically by iterating honestly for weeks at this point, just little bits at a time. If you watch my live streams from other channel, you might see this where like, I would say about four hours a day. I will improve something on the agent OS system here. And this morning it was actually the Hermes Jarvis version of this. Now, what we've also got is this section where we can do weekly briefings. We can switch the voice as well. So we can actually change between all the voices that we have. One thing that I should learn from this, if you want to build something like this yourself, is that you want to make sure you have chat chippity real time as the API. We had 11 labs before it was way too slow. It sounded better, but it was too slow to actually use. And the other thing that blows my mind is like we can send links inside the chat and Jarvis can read them and then come back to us. Plus we have wall mode where we can basically have this real time separate monitor voice activated ready to go whenever we need it. So it's very, very fast, very responsive response literally instantly open stuff up literally instantly. I don't know how it's been created this well, but basically what I've been doing is using Claude and Claude desktop, as you can see right here, and just going back and forth with it until we actually build something nice. And we've been going back and forth for weeks, as you see. If you look at the history here, it's like it goes on forever because it takes so much iteration. But I do want to show you this just to inspire you because I think it's fantastic what we've built. And we used to have this talk section here, but I think I'm actually going to get rid of it because now Hermes Jarvis totally replaces it. And if I have a choice between going to Hermes Jarvis or going inside the chat, for sure I'm going to go directly to Hermes Jarvis these days. Because it's just easier to use, easier to manage, easier to organize. And the other cool thing about this, you could set this up with anything. You know, it doesn't have to be Hermes. It could be Claude that you speak to. It could be OpenClaw. It could be Gemini. But I just want to show you that you can actually build something useful with Hermes. It's not just like a gimmick. It's like a genuinely useful voice agent that is getting closer and closer to something that I actually really love. Now, this is a guide that I just made a week ago on the power of this stuff and how it works. But basically, the way this works, you've got Jarvis in the middle, Hermes Jarvis, which is Hermes agent, open source project, but voice activated. And so it's got the brief. It can read your daily week to you. You can actually say show me and it will pull up on the screen. So, for example, we go over here. Show me the numbers. Certainly. Sir, the numbers are now displayed on your screen. Show me. Very well. Let's bring them up. Could you clarify which numbers you'd like to see, sir? It can also build stuff for us with a live preview. You can just talk to it voice in, voice out and actually should remember things. But that's something we need to improve as we go along. So it's pretty powerful stuff. You know, lots of cool features built into that. I'd actually be interested if you're watching this to know like, OK, what would actually be useful? What would you genuinely use out of all of these features? And then also, what would you like to see in future versions? But you can see your Hermes Jarvis. Then you've got like this wake word where you can flip it on. You have the arc reactor so you can tap it and talk. So it has fast answers, briefing ready to go, voice, and then you can type instead inside the command box as well. Indeed, sir. Versatile and efficient. Much like a trust. You can even listen in the background and then you can interrupt it as well, as you can see right now. Indeed, sir. Always ready for your next command seamlessly. So it's pretty cool. And then you've got the briefing history. The other cool thing is I can just interrupt it mid-flow, like talking to a person. So if it says something now. Understood, sir. Yes. Go again. Very well, sir. As you wish. Go again. Understood. So you get the point. I'm going to switch off now. But yeah, pretty fun to build. Really cool. If you're watching this and you've been thinking about building voice agents, I think now is the time. It's better than ever. Genuinely the first time I've been impressed by this sort of stuff. If you want to get my setup with the Hermes agent setup with Hermes Jarvis, the Agent Operating System and everything else, you can get that inside the AI Profit Boardroom. Link in the comment description or just go to theairprofitboardroom.com. I answer questions personally inside the community here. Inside the classroom, you get access to all of my best trainings. Inside the new daily update section, you can get access to the Agent OS system. You can see when it was last updated. So we've actually dropped a new version today. And then you can get all of my new tutorials inside here too. Inside the calendar, you can drop a weekly coaching course, get help and support in real time. And inside the map, you can meet people locally who are building with Hermes agent and other tools like this. So feel free to get it all. Link in the comment description or go to theairprofitboardroom.com. Thanks for watching. Cheers. Bye-bye. Here, go ahead. Here I go.