**Julian Goldie** (0:00)
Today, I want to show you a powerful system where you can use NotebookLM inside your Agent OS to generate short videos. You can create podcasts, you can create infographics for free in one single click. You can even create amazing slide decks, as you can see with research reports, and you can create reports here. Plus we have a studio to generate and build anything that we want in one single click. They're using NotebookLM. You can do all this for free. You can even create like longer format videos, and you can see everything inside one workspace. So this is a system that was set up. I call it the Infinite Content Engine, which basically means you have one NotebookLM in using NotebookLM, and then you have like five different content formats pulled out. Basically, I rebuilt the NotebookLM section of our Agent OS around a simple idea. Every content format gets its own tab, its own generator, its own gallery of everything ever made. So you can drop sources in, and then you can get powerful outputs out in terms of the content. This is fantastic for creating content. Now, let's talk about the problem that this solves. So I call this the content treadmill problem, which is like imagine spending a whole day researching a topic that you know from cold. You turn it into one video, the video does okay, then it's gone, then the next, the treadmill resets, new post needed, new research, new script, new editing session. The podcast people want to podcast. LinkedIn wants an ifrqrvic. The client wants a deck. Each one is a separate project built from scratch in a different tool. And so the problem is you pick one format, you ship one piece and let the other four just, you know, you can't, you don't have time to do all. With this system, you avoid that treadmill. And so this breaks that cycle for good. So what is the infinite content machine? Well, basically you can use NotebookLM superpower, which is that it works from your sources and your topics. You load a notebook in and then you can generate content out. So you have one notebook and then you can create shorts and great podcasts, infographics, decks and reports all inside NotebookLM. Now you might say as well, why don't you just go directly to NotebookLM to use this tool? Like why don't you just go directly here? But the problem with that is like it's not neatly organized. It's very difficult to see what you've created. And also like where's your gallery? How do you see everything you've built? How do you quickly create something in one single click? If I had a notebook that I wanted to create about a certain topic from like a year ago, it's just gonna be almost impossible to find. And then even if I do, it's like, okay, well, you know, how do I go back and see everything I've created? How do I know which notebooks have stuff generated? I can't. Whereas with this system, I can easily see everything that I've built inside one place. I've got the studio if I need to generate more stuff, I can quickly select one single notebook here inside the library, pull that into the studio and then generate a slide deck. It's just way faster, way easier. And also everything that you do inside the agent operating system, well, it links to your memory, it links to your other agents. It's all plugged into one place, it all connects beautifully together. And that solves a massive problem.
Now you might also say, okay, how did you do this? So we actually plugged in the MCP for NotebookLM into our agent operating system. And then with a combination of NotebookLM and the MCP, we can generate content whenever we need to, which is pretty powerful. And so we just research, import it, generate the format, pull that into a gallery and then we can publish content.
So, for example, if we have a look at our library here, we have the agent OS or we have like, for example, Hermes Astrost, or we have a NotebookLM on OpenClaw here. So we can pull that in, click on that, and then we could go over to the studio and we could generate a video in like one single click about OpenClaw, just like that. That's how easy it is. And then if we go back to our reports, we've got this report section where we can generate stuff. We've got slide decks where we can generate these whenever we want. We can actually add a focus here, so we can change the focus of the report. So we could be like, okay, OpenClaw versus Hermes, like so, hit generate. That can generate a slide deck in the background. We can see all our previous research here, all our infographics, all our podcasts. And this is all free to do, which is pretty insane in itself. So you basically have a tab for every format and a gallery in every tab. And this is what we've rebuilt here. So for example, for short, we can see all our previously created videos. For podcasts, we can see all our previously created podcasts.
6 more minutes of transcript below
Try it now — copy, paste, done:
curl -H "x-api-key: pt_demo" \
https://spoken.md/transcripts/1000651996090
Works with Claude, ChatGPT, Cursor, and any agent that makes HTTP calls.
From $0.10 per transcript. No subscription. Credits never expire.
Using your own key:
curl -H "x-api-key: YOUR_KEY" \
https://spoken.md/transcripts/1000776679321