19:49Nate Herk | AI Automation · Demo
I Turned GPT-6 Astra Into the Ultimate AI Second Brain
A creator maps his entire business into Codex using a four-layer framework, then scores the result like a KPI.
September 7thThe argument in one line.
A five-step loop, transcribe, cut, plan the beats, apply a reusable skill, then verify, turns a desktop coding agent into a natural-language video editor that can generate synced motion graphics, subtitles, and B-roll from a single detailed prompt.
Read if. Skip if.
READ IF YOU ARE…
- A YouTuber or content creator who edits their own videos and wants to offload subtitle syncing, B-roll placement, and motion graphics to an AI agent.
- Someone comfortable running a desktop coding agent like Codex who wants a concrete, repeatable prompt-to-video workflow rather than one-off AI editing tricks.
- A creator already making reels or ads who wants an example of directing AI edits with very specific natural-language instructions instead of vague prompts.
SKIP IF…
- You're looking for a review of the underlying AI model or a technical breakdown of how Hyperframes renders its animations.
- You want a no-setup, point-and-click AI editor. This requires installing Codex, a GitHub repo, and an ElevenLabs account first.
The full version, fast.
The video demonstrates an AI video-editing workflow built on OpenAI's Codex desktop app plus an open-source toolkit called Hyperframes. Editing happens in five steps: transcribe the footage (via ElevenLabs), cut mistakes and silence, plan the visual beats against the transcript, generate the edit using saved skills, then verify by having the agent re-watch its own output. The presenter walks through a live build of a video intro, showing two full revision passes driven entirely by natural-language prompts, plus pre-made examples of a YouTube edit, two short-form reels, and two ad-style videos. The actionable takeaway: once an output style is approved, save the prompt as a named skill so future edits need one line instead of a full paragraph of direction.
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.
Create a free account →Where the time goes.
00:00 – 01:26
01 · What You Can Create
A fast preview montage of AI-generated reels and a Claude/NVIDIA explainer cuts into the real hook: an agent turning natural language into synced motion graphics, subtitles, and B-roll.
01:26 – 03:05
02 · Editing YouTube Videos
Shows the agent cutting a 14-minute YouTube video down to 9 minutes, adding backgrounds and cuts, and switching between full-screen cards and a cropped talking-head view.
03:05 – 09:32
03 · Reels, Ads, and B-Roll
Walks through pre-made short-form reels and ad examples, showing the agent sourcing its own B-roll, animating a logo, and syncing music to pacing.
09:32 – 10:58
04 · Setting Up Codex and Hyperframes
Starts the live build: creates a new local project in Codex and has the agent pull in the Hyperframes GitHub repo and install its dependencies.
10:58 – 13:41
05 · The AI Editing Workflow
Explains the five-step mental model, transcribe, cut, plan the beats, use skills, verify, and notes the same loop works for building from scratch, not just editing footage.
13:41 – 16:47
06 · Setting Up ElevenLabs
Creates an ElevenLabs API key scoped to speech-to-text, stores it in a project .env file, and adds a standing rule to agents.md to always use it for transcription.
16:47 – 22:58
07 · Directing the Intro Edit
Delivers one long, highly specific natural-language prompt covering exact screen positions, style references, and behavior for every beat of the intro, then lets the agent work.
22:58 – 23:42
08 · Turning Edits Into Skills
Explains that an approved output becomes a saved, reusable skill, so future edits need a short command instead of a full prompt.
23:42 – 26:33
09 · Reviewing and Refining the Edit
Reviews the first AI-generated pass, gives specific comparative feedback (unrealistic overlapping clips, text too small), and requests a second revision.
26:33 – 29:14
10 · Hyperframes Studio and Final Versions
Opens the underlying visual timeline editor for manual tweaks, reviews the improved second pass, and generates a third variant to compare against a ruled-out full-screen option.
29:14 – 29:57
11 · Final Thoughts and Free Skills
Wraps up by pointing viewers to the free student kit containing the skills used throughout the video.
Lines worth screenshotting.
- A single natural-language prompt can direct an AI agent to generate synced motion graphics, animated subtitles, a repositioned face-cam, and clipped B-roll in one pass.
- The reusable workflow behind this style of AI video editing is five ordered steps: transcribe, cut, plan the beats, apply a skill, then verify.
- Naming a video's visual beats, its individual scene units, lets an AI agent sync animations to specific transcript timestamps down to the millisecond.
- Once an AI editing output is approved, saving the exact prompt as a named skill turns a multi-paragraph direction into a one-line command for future edits.
- A first full AI revision pass took about 18 minutes to render; a smaller, more targeted second revision took about 10 minutes.
- The agent pulls B-roll automatically from a local video directory, so a creator's past YouTube uploads become a searchable library the AI edits into new content.
- A visual timeline editor sits underneath the natural-language layer, so a single small tweak like a font size is often faster done by hand than by re-prompting.
- Verification in this workflow is a loop, not a single check: the agent re-watches its own output and re-reads the transcript before calling an edit finished.
- Because the agent can pull files from local drives, an ad-style video can incorporate a creator's own past footage and screenshots without any new recording.
- A paid transcription API was chosen over the free local option specifically for speed, since the workflow depends on many repeated transcribe-and-revise cycles.
- Telling an agent what NOT to do (no full-screen cutaway, don't cover the face) narrowed the output as much as describing what to do.
A five-step loop replaces manual video editing
THE AI EDIT LOOP
Transcribing, cutting, planning beats, applying a saved skill, and verifying in a loop turns a coding agent into a natural-language video editor.
01What You Can Create
- A single detailed prompt can direct an AI agent to add synced motion graphics, animated subtitles, a repositioned face-cam, and clipped B-roll in one edit.
- Previewing the finished output before explaining the process makes the video's promise a concrete example rather than an abstract claim.
02Editing YouTube Videos
- The same agent that edits reels can take a full YouTube video, cut a 14-minute recording down to 9 minutes, and add background and scene changes automatically.
- An agent can alternate between a full-screen animated card and a cropped talking-head view based on whether there's something to show on screen at that moment.
03Reels, Ads, and B-Roll
- Short-form reels built this way switch visual elements every one to two seconds, layering B-roll, full-screen text, and talking-head shots to stay fast-paced.
- An agent can source its own B-roll: recording or generating footage itself, animating a logo pulled from a personal drive, and syncing music to the pacing.
- An ad-style video can pull specific past recordings, screenshots, and event photos to fit its message, instead of relying on generic stock B-roll.
04Setting Up Codex and Hyperframes
- The workflow runs on two separate pieces: a coding agent as the interface, and an open-source repo of skills the agent installs into the project.
- Pulling a toolkit into a new project can be a single instruction: point the agent at a GitHub repo URL and ask it to install the dependencies itself.
05The AI Editing Workflow
- The mental model for AI video editing is footage in, transcript out, then cut, then plan the visual beats, then generate, then verify, and skipping a step in that order breaks the sync.
- A 'beat' in this system is one distinct scene or animation segment, and the agent needs a timed transcript before it can sync animations to speech.
- The same five-step loop applies to building from scratch, not just editing existing footage, by skipping the transcribe and cut steps and starting from planning beats against an outline.
06Setting Up ElevenLabs
- Free local transcription works but is slower; a paid transcription API is worth a small monthly cost when a workflow depends on many repeated transcribe-and-revise cycles.
- Standing project instructions belong in one file so an agent automatically applies a rule, like which transcription service to default to, without being reminded every time.
07Directing the Intro Edit
- The most specific prompts produced the best first-pass results: naming exact screen positions, specific style references, and exact behavior all in one direction.
- Telling an agent what NOT to do matters as much as saying what to do, since it prevents the agent from filling the gap with its own default choice.
- Asking for a 'finished product' instead of a 'first version' in the initial prompt sets a different bar for how polished the returned draft will be.
08Turning Edits Into Skills
- An approved output becomes reusable the moment its prompt gets saved as a named skill, so the next edit needs one short command instead of a multi-paragraph brief.
- Skills keep improving through use: updating the skill itself after feedback, not just the one-off prompt, carries the fix into every future edit.
09Reviewing and Refining the Edit
- A first full revision pass took about 18 minutes to render, while a smaller, more targeted second revision took about 10 minutes, showing feedback rounds speed up once a base edit exists.
- Effective revision feedback names exactly which shot looks wrong and what 'fixed' should look like, rather than describing a vague overall impression.
10Hyperframes Studio and Final Versions
- A visual timeline editor sits underneath the natural-language layer, and small isolated tweaks, like a font size, are often faster made by hand there than by writing another prompt.
- Generating the version of an idea you already ruled out is a fast way to confirm a creative decision, rather than just assuming the simpler choice was right.
Terms worth knowing.
- Hyperframes
- An open-source toolkit that gives a coding agent the skills and templates needed to generate HTML-based motion-graphics video edits from a text description.
- Codex
- OpenAI's desktop coding agent app, used here as the chat interface a creator types editing instructions into.
- Beat
- In this workflow, one discrete visual scene or animation segment within an edit, timed to a specific portion of the transcript.
- Skill (in an agent workflow)
- A saved, reusable prompt and instruction bundle that reproduces a previously approved edit style with a single short command instead of a full brief.
- agents.md
- A project file that stores standing instructions an agent should always follow, such as which transcription service to default to, so they don't need repeating.
- Goal prompt
- A mode where an agent is given an end objective and keeps working autonomously toward it, rather than executing one single, one-shot instruction.
Things they pointed at.
01:12toolCodex (OpenAI desktop coding agent)
13:23toolElevenLabs (speech-to-text API)
04:04toolNVIDIA free API access (80+ AI models)
Lines you could clip.
00:44
“Isn't it crazy that with just my natural language, I can get all of these crazy motion graphics right here, and I can get all of these insane animations over here as well?”
03:17
“Stop prompting Claude. Andrzej Karpathy thinks there's a much better way to work with AI, and his method has three layers.”
23:33
“So what I just did is really the hardest it'll ever be. And then it's always just about iterating on those skills.”
25:09
“I mean, that was 18 minutes. That was a really good first pass, but let's do another version here.”
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.
metaphoranalogy
Stop prompting Claude. Andrzej Karpathy thinks there's a much better way to work with AI, and his method has three layers. Layer one is the spec.
Instead of giving Claude a task and hoping it understands you, work with it to create a detailed spec first. Have Claude interview you about what you're actually trying to achieve, then break the work into smaller checkpoints before it starts. So NVIDIA just made building with AI basically free.
They're giving developers free API access to over 80 AI models. Here's how you use it. Go to NVIDIA, choose the model you want, and generate an API key.
You can choose from models like Kimmy, GLM, DeepSeek, and loads more. So you want to start a real business, but you can't afford people for content, marketing, sales, and all the other types of work yet. Because you can now install AI agents for free.
One to help create content, one to help follow up with leads, and other types of agents to help handle the jobs that your first employees normally would do for you. Isn't it crazy that with just my natural language, I can get all of these crazy motion graphics right here, and I can get all of these insane animations over here as well.
I can have subtitles appearing at the bottom like you see. I can take my face and I can put it in the bottom right corner, or I can bring it up to the top left corner. I can even play you guys clips of a bunch of my different YouTube videos right here in this sort of 3D fashion.
So by the end of this video, you will know exactly how to actually do this, even if you've never really used Codex before or you've never edited videos before. So I don't want to waste any of your time. Let's just get straight into this video.
All right, so I hope you guys are excited to learn how to do this. What you're going to need is you're going to need the Codex desktop app and you're going to need to install Hyperframes, but I'm going to show you guys all that. Before we go through the setup, I just wanted to show you a few examples of how I've been using it and the skills that I'm going to give you guys for completely free.
So this first example is just having it help me edit YouTube videos because what it's able to do is it transcribes the audio and then it can cut out mistakes and stutters and things like that and, you know, dead space. So for example, in this one, I gave it two different recordings. I gave it my face cam and I gave it my screen recording and this was a 14 minute video that got cut down to nine minutes and now it has like the background and it also has a few cuts.
So let me just show you what I mean by that. So here's the video. It's not live yet, but this is how it starts off.
Today, I'm going over the 18 core codex concepts that you actually need to know in order to start using it right away and getting value from it. It doesn't matter if you're not technical at all or you've never used codex before. By the end of this video, you'll understand exactly how this thing actually works so that you can start using it right away.
So as you can see, that first animation with the 18 cards coming into the screen, that was hyperframes as well as codecs here driving the actual edits, the rounded crops, the background, all of this. So part one we're gonna start off here is foundations. So we're gonna kick off with concept number one, which is projects.
Now a lot of you guys, I'm assuming, have used ChatGPT or Cloud in the past. Now, all of that logic was once again, hyperframes. It basically created the card that said, you know, number one projects.
It then decided to also zoom me in here because it realizes that for the next, you know, 10 to 15 seconds, I might be talking about something, but I'm not showing anything on screen. So I prompted it in this way and I gave it the skills in this way to understand that when there's nothing going on on the screen, maybe you do a full screen, but then when it's time to do more of a tutorial, you go back into this view.
So anyways, throughout this whole video, that's basically what it does. It's able to jump between full screen and this. basically, you know, template or scene.
And then it also creates those cards in between each of the concepts. There is like a transition screen. All right.
So that's one quick example. Let's take a look at some short form content, which I think is getting much, much better. So here I have it doing two reels.
One is about Claude and one is about NVIDIA. So let me just real quick play these two for you, and then we'll break them down. Stop prompting Claude.
Andrzej Karpathy thinks there's a much better way to work with AI, and his method has three layers. Layer one is the spec. Instead of giving Claude a task and hoping it understands you, work with it to create a detailed spec first.
Have Claude interview you about what you're actually trying to achieve, then break the work into smaller checkpoints before it starts. Layer two is the verifier. Before Cloud does anything, define exactly what a good result looks like.
Then give it ways to actually check its own work, whether that's another AI model or real data or tests that it can run on its own. And layer three is the environment. Build a workspace where Cloud already has your instructions, your knowledge, your skills, and your rules every single time you use it.
So instead of becoming better at writing prompts, you're building an entire system around Cloud that makes it better every time you use it. I made a full YouTube video breaking down Karpathy's method and exactly how to build this yourself. So just comment method and I'll send it to you.
So NVIDIA just made building with AI basically free. They're giving developers free API access to over 80 AI models. Here's how you use it.
Go to NVIDIA, choose the model you want, and generate an API key. You can choose from models like Kimmy, GLM, DeepSeek, and loads more. Then take that key and plug it directly into whatever you're building with.
So you can experiment with AI apps, automations, and other projects without immediately racking up API costs. And because they're OpenAI compatible APIs, you can use them with loads of existing AI workflows. If you wanted to start building with AI but didn't want to burn your own money testing different models, this makes it way easier.
So just comment key and I'll send you the full setup. So I thought that those outputs were really, really solid. You can see that what it does is it kind of starts off with like a visual hook i guess we'll go to the clod one first we have the three missing pieces and what it did here is it's kind of creating that open loop because it's saying hey yeah you know andre carpathy uses it in this way and it's of oh wow i need to stay to the end of this short to see what all three of these are because as we go through we can see we have number one we can talk about little number one and then we go into number two the verifier and then we get into number three finally at the end which is about the environment and so About every one or two seconds here, it's switching.
You know, we've got some scenes where it's like this with B -roll up top and me down here. It's got some where it's a full screen animation. It's got some where it's full screen me.
And all of these animations are sort of like paper style. There's texture, it's 3D, they're always moving. So we're never having one element be still.
You've also noticed that it went out and it got all of this B -roll. It either created it or it recorded it itself. And the subtitles, it was made by...
hyperframes and Astra, the music, the sound effects, all of this is being synced to the actual reel for engagement. And pretty much same thing with the NVIDIA one. This one was shorter, but it's a similar style.
This one has more green accents rather than orange because it's about NVIDIA, but it has the same types of animations. It has the same types of, you know, scenes and it has the same way that it's fast paced. It's always switching.
We have music, we have real B -roll that it went out and it collected on its own. And here's even more AI generated B -roll that it created on its own. I think that this is getting really, really good.
And I've turned this into a skill and like I said All of these are skills that come inside of one sort of student kit is what I'm calling it.
So if you want to get it all for free, just go into my free school community. The link for that is down in the description. And then you're going to go to the classroom and you'll go to either AI skills or all YouTube resources.
I have it linked in a bunch of spots, so it's really easy to find, but you'll be able to find it right in here in the AI skills section. It'll be called like hyperframes student kit. Here's another quick example.
This one is an AIS reel and it made this one for me in both 16 by nine, as well as nine by 16. But let me just real quick play the nine by 16 version for you guys, because it's. kind of like a reel, but it's a little bit different because this one was meant to be an ad.
What if you could build the team before you hired it? So you want to start a real business, but you can't afford people for content, marketing, sales, and all the other types of work yet because you can now install AI agents for free. one to help create content, one to help follow up with leads, and other types of agents to help handle the jobs that your first employees normally would do for you.
It's like building your first AI -powered team before you hire your first employee. And that doesn't eliminate every future hire. It actually gives you the capabilities to start before you need them.
At AIS Live, I'll show you how to build your own AI OS, a personalized system of agents, tools, and workflows that helps you operate a real business. You'll discover the most important AI agents for starting a company and how to install them for free. You'll also see how an AIOS can support content, marketing, sales, operations, and even recruiting as your company needs to keep growing.
So if you want to start a highly profitable business without building a huge team, then click below for more details on AIS Live. Now it has similar elements, right? But what I want you to pay attention to here is all of the B -roll that it went and collected from me.
It grabbed YouTube videos of mine. It went ahead and it grabbed past AIS live, you know, segments. So here's one with me and Pat.
We can go into, here's like a VIP session. Here's a video of me like talking about my iOS and a second brain. So it was able to use the context of what the ad was about.
Here's a session with HyperAgent and Alex. It used the context of what we were talking about and it actually put it inside so that this doesn't just feel so much like theory. it feels more real.
And it even animated this logo here at the end, which I thought was just beautiful because it had to go to my Google Drive to find the AIS Live logo. And I think that this turned out really, really nice. And I'll play one more for you guys real quick, which was a call to action that I gave Codex.
Real quick, guys, just wanted to say, if you're enjoying this video and you're enjoying the way that I teach, please consider subscribing and joining my free school community. The link for that is down in the description. We're building a global community of AI builders and entrepreneurs and business owners.
We're almost at 450 ,000 members. We're almost at half a million, which is super, super exciting. And it would just mean a lot to me if you joined.
We have a lot of resources in here. We've got agent skills. We've got every YouTube video where I give away free resources.
Like I said, skills, guides, templates, docs, GitHub repos. I give it all away in here for completely free. We also have a seven -day challenge.
We have a Build Your AIOS course. We've got a lot of fun stuff going on in here. Events, certification programs, tons of cool things that we're building towards.
So if you're enjoying it, if you like the way I teach, please definitely check it out. Hope to see you guys in there. Let's get back to the video.
Now, what I liked about this is this one felt very clean, right? It wasn't super fast -paced, super energetic. There's low music.
But once again, it's proving to us that it can go grab screenshots, it can crop them, and it can use context about me and my business in order to make these feel more relevant. It grabs all of these different skills and docs, and it put them in here in a really, really nice way. We even went and screenshotted some of our courses from the community.
It grabbed, you know, event assets and pictures and videos, and it just made this call to action to feel so much more real, so much more human. So if you guys are getting excited by that, go ahead, like I said, to my free school community and grab all of those skills to be able to replicate those sorts of outputs. But now let's actually get started with building this.
Like, how do you actually do it? And I'm going to walk through a real example with you guys. If you guys remember the intro from this video, I'm going to build that out live right now with you guys.
So the first thing that I want you to do is you're going to open up a new project. open up a new folder in your desktop or something. And we'll just call this one for now.
I'm gonna call this HyperFrames Demo. And that is the project that we're gonna be working inside of. So I've got this folder on my desktop now.
I'm going to come into here on the left -hand side and open up a new project. I'm gonna choose for this to be a local project. I'm going to give this a name.
So HyperFrames Demo. And then I'm gonna choose that actual folder so that Codex can work inside of it. So that was in my desktop and it was called HyperFrames Demo.
Cool. So there's the project. I'm going to select that and open this up.
So when you open up a new chat in this project, there's going to be nothing in here. So if I go over here and I go to my files, there's literally nothing here. But we're going to start to fill this up with things like video projects and different renders and different files and things like that.
So the first thing I want you to do is I want you to go to this GitHub repo, which I will link in the description. And this is called HyperFrame. So you're basically just going to copy this URL for the HyperFrames GitHub repo.
You're going to open up Codex, paste that in there, and then basically just say... Hey Codex, I need you to basically pull in this HyperFrames repo so that I can use it to have you edit videos for me and stuff. I need you to make sure that all the dependencies are installed and everything like that and grab in some skills or things that you need inside of this Codex project in order to actually make this stuff useful.
So that's the first step. You're going to go ahead and shoot that off. Now, while this is getting set up, let me talk about the mindset and the idea of what we're actually doing here when we're editing videos with AI.
So there's a few steps, right? And in this case, I'm taking the example of we're giving it some sort of footage and having it edit it and animate it and things like that. But it can also create things from scratch.
So if you gave it a rough outline and you wanted just motion graphics and like sizzle reels or like SAS demos, it could do that 100%. but that's not what I'm gonna be focusing on right now, you would just remove this first step. So basically in my mind, step one is you have footage, and what you need to do is you need to transcribe it.
And basically that means it needs to find out all the text that you're saying in that clip. and exactly when it happens, the exact second to the millisecond of when you say certain words so that it could sync it up with different animations and different texts, like subtitles, for example. So transcribing comes first.
You can do this with a free local thing that it can set up like called Whisper, but I actually like to use 11 Labs for this. So I'm gonna show you how to set that up as well. After you transcribe then, the next thing that we wanna do is we probably want to cut.
So basically having it cut out, you know, mistakes or... five seconds of silences and things like that. So that would be step two.
Step three then in my mind is to plan the beats. That's kind of what it calls our beats. So beats are basically different scenes.
So for example, with this reel, like this install capability slide, this is one beat and then like this is one beat and this is one beat. Every basically scene is a different beat. So now what we like to do is we like to have Astra, the model, read through the text, understand the intent and start to plan out the beats of what's actually going to go inside of this reel or inside of this video.
And then what it's going to do is it's going to use its skills and it's going to use. hyperframes and it's gonna use other tools like this in order to actually do the generation of the HTML. It's basically just creating HTML and it's animating it and that's what really gives us all these 3D elements and it gives us this text and it gives us what we are basically looking at and considering the motion graphics or the motion design.
And by the way, part of planning the beats is understanding that there's going to be music that's going to sync to it and sound effects and all of that is basically coming into this element of planning. And the thing about it is we have to have transcribed and cut all of that first in order to be able to do this properly.
And then the last step here is basically, honestly, it's kind of a loop. So the last step is basically to verify, meaning have the agent watch through all of this again. It will watch through it.
It will take screenshots. It will look at the transcript again. And basically what we want to do is we're going to do this loop of verifying and then going back into here.
and using the skills again and then verifying and then using the skills again. So we get in this loop of just going like this until the agent is confident that everything is in bounds and everything syncs properly and everything feels how it should. So that's kind of the flow.
Let's actually go get set up. So we are now inside of this project and it's still getting everything set up. So what I want to show you what to do next is we want to do 11 labs to transcribe.
So you're going to go to a new page. You're going to open up 11 labs. and create an account if you haven't.
You can get started on this for like a five bucks a month plan, which it'll last you quite a while. So you're gonna come in here and then what you're gonna do is you're gonna go on the bottom left to developers and you're gonna click on API keys right here and you're going to go ahead and create a new key. I'm just going to call this Astra demo.
You can have this expire. You can just leave this at never. And then as far as restricting the key, if you want to say, okay, this key is literally only going to transcribe stuff.
that would be speech to text you could give it access to speech to text if you also want to give it access to like sound effects and music generation and image and video generation you can give it access to other things as well but right now i'm just going to start with just speech to text because all we really need for this endpoint is the transcription so i'm going to create this key this gives us basically a password so don't share this with anybody and i'm going to delete this as soon as i'm done filming so don't even think about it but you're going to copy this to your clipboard you're going to go into codecs And then we're gonna come into your files right over here.
And you can see now it's starting to build out some folders and files and things like that. And what you need is you need a file called a .env, which lets you store secrets and passwords like your 11 Labs API key. So all you have to do is just, you can chuck in a message even while it's working here.
And look, it actually opened up a local host, which is kind of how we can see our video projects. This is just, you know, it just lets us test them and look at them and even like move elements around and stuff, which is really, really cool. But I'm just gonna close out of that because that was just an example.
But what I can do is say, when you do the transition, I want you to use Eleven Labs. So can you please create me a .env so I can put my Eleven Labs API key in there?
And also make sure that you include this in the agents .md. that says whenever Nate wants you to transcribe a video, use 11labs for that. So the agents .md is this file.
This basically just explains how the project works. So right now, because there's not much information in there, it just has some very basic stuff from HyperFrames. But as you start to learn more about the way you like to edit videos and the way you like to store your projects, you'll basically want to come in here and update it with certain information.
So right here, you can see it says, okay, I will add that rule into the agents .md so that... In the future, I'll stop the Whisper setup, which is that local thing that I talked about. Now nothing's wrong with Whisper, it's just slower.
And so 11Labs, yeah, you have to pay for it, but it's much quicker and I like that speed and it's not that expensive. So now our .env has a placeholder for the 11Labs API key. So what you're gonna wanna do is just paste in your 11Labs API key right inside of here.
And by the way, if it's not letting you paste or type anything in here. which it should. But if it doesn't, then you can just go into here and click on open in default app.
And for me, that opens up in my notes. I can paste in the API key, hit save. And then as you can see, it's going to refresh live right inside of here.
All right. So at this point, we have enough information in here to actually be able to use hyperframes. So I'm not going to use my skills that I mentioned that I showed all of these examples where I use my skills.
I'm not going to use these right now because I just want to show you what this kind of looks like at its core. But don't forget that you can definitely grab those skills and come in here and make these things better. And so one thing that you can do is you can give it a video file and just say, hey, edit this for me, you know, add motion graphics, make it tell a story, blah, blah, blah.
Or you can be very specific, which is what I'm going to do for this specific example. So let me pull up the video that we're going to be working with. It's right here.
It's called edit intro. So let me actually open this up and we'll give it a quick watch.
Okay, anyways, so now you see that I'm basically planning out what I want to happen as it's happening. So here's what I'm gonna do. I'm going to grab the file path of my video.
I'm gonna come back into here. I'm gonna do a slash goal prompt for this, which basically just means that I'm setting a goal and it's gonna keep pursuing until it hits that goal. I'm gonna paste in the file path of that video and I'm just gonna start instructing what I want to happen when I want it to happen.
But first I have to set up the loop of transcribing, cutting, planning the beats, and then it's going to go ahead and get to work. But instead of planning the beats, I'm kind of directing this a little bit more. So this is kind of like plan slash accept beats.
But anyways, let me show you what this is going to look like as I instruct this thing. So I just dropped in a video for you. This is going to be an intro.
So I need you to help me turn this into a super premium and polished edited video. So the first thing you need to do is I want you to transcribe the video because we need all of the beats and all of the motion graphics to sync exactly when I say them. And then I need you to cut out anything if there's mistakes or if there's silence.
There shouldn't really be like a second or a half second of silence. I want this to feel fast paced. After you've done those two things, it's time to start actually animating this video.
So let me tell you what I'm looking for when it comes to the animations. So I start off this intro by saying something like, isn't it crazy that I can use just my natural language to get all these crazy motion graphics over here and all these crazy animations over here? What I want to happen then is I want this whole vibe of this video to be very, very like Apple style motion design.
So like , clean animations, and they feel very professional. So when I say motion graphics over here, I believe that my hand was on, it was pointing to the left side of the screen. So on the left third of the screen, I want them from top down, sort of like my hands are creating these motion graphics.
I want them to come into screen and just make them, you know, against like some sort of liquid glass card where we see three different types of motion graphics, maybe like... cards and documents moving around or laptop screens and charts and elements that are being like animated and things like that. Just make things over here that are impressive and that tell a visual story.
And then similarly, when I go into the insane animations over here as well, that's on the right side of the screen. So same thing, I want them to come in from top down like I'm drawing them in. I want these to be 3D.
So I want these to be against some sort of um maybe a little overlay in the back so that we can see them against the background just like a subtle dark overlay and these should be 3d so they should maybe look like they're spinning they should have shadows they should have depth and these can just be 3d like letters or 3d animations and i don't know like symbols that are moving just make these you know subtle and professional but they should certainly give some sort of like wow factor and for those two beats i want them to stay on the screen while i'm talking about them and then i want them to leave the screen or sort of like fade away at the same moment so the motion graphics on the left come in first animations on the right come in second and then they leave the screen at the same time the next section is pretty simple when i say i can have subtitles appearing at the bottom as you see i just want a super super clean overlay at the bottom of the screen with subtitles they shouldn't cover
my face so they should be sort of near the lower third and if you could just have the words like subtly highlighted with maybe like the words are white but they're highlighted in blue when I'm actually saying them so make sure they're synced exactly to the transcript when I'm saying them. Now in the next section I go on to say you know I can take my face and I can move it to the bottom right corner or the top left and what I want you to do for that is I want you to take my face cam and sort of shrink it into like a a vertical rounded crop.
So you kind of just bring in the left and right sides to keep me centered and you make it rounded crop with a drop shadow and you put it against this background, which is the full screen background. And so here what I'm doing is I just paste it in this picture, which I like to use as my background in some YouTube videos.
And I want you to make that background 50 % opacity. So it's a little bit darker. And then for the next part, when I say I can play you guys these clips from my YouTube videos, I want you to go to my YouTube video directory locally.
which I'll give you the file path to. So I will just copy in this file path real quick, right there. What I want you to do is just grab a few of my most recent videos, maybe like four or six, and I want you to sort of fan them out, like animate the process of you fanning them out and have these be 3D with like a little bit of a drop shadow.
And they're sort of like rotating and swiveling back and forth just to create a really cool effect. But I want them to actually be playing throughout. I don't want them to just be static images of the videos.
I want you to just play, you know, all of them are sort of actually playing at the same time. And then to end off the video, what I want you to do is basically against that background I gave you, if you could bring my main face cam. sort of align it on the left side of the screen, but make it bigger so it kind of touches the top and bottom of the screen.
But we should still see the rounded crop and the drop shadow. And then on the right side of the screen, we can just have some other text and other motion graphics that tell a story based on what I'm saying. So like, you know, you don't have to be technical.
You don't have to have used codecs before. You don't have to have a video editing background. If you could just make little icons and animate them in a fun way to tell that story.
And then at the end, you know, it says like, hey, I don't want to waste any time. It just gets right straight into the video. Do the exact same thing there.
And that's going to pretty much be the end of this intro. After you have then done all of that, I just want you to make sure it looks good. I want you to sort of like verify it by taking some screenshots and looking through, making sure that the beats actually sync to the.
text that I'm reading out and make sure that everything's in bounds and everything looks professional and it's giving off the quality that you want it to. I'm not looking for a POC or a version one. I'm looking for a finished product ready to go here.
Out of breath a little bit. So that was a massive prompt, right? That was me being super, super specific about what I'm actually looking for here.
And that's kind of what this looks like to start. The way that I got to all of these skills that I now use for YouTube videos, lessons, reels, ads is because I did that so many times. And now if you get an output here that you really, really like, you say, cool, that was awesome.
Turn that into a skill. And the next time you don't have to give such a big prompt. You basically just say, hey, edit this video, use this skill.
And then when it comes back, if you have feedback, say, hey, I didn't like this. Make sure you do this next time and then update the skill too. So what I just did is really the hardest it'll ever be.
And then it's always just about iterating on those skills. So I'm just going to go ahead and let this cook a little bit. I will check in with you guys when this one comes back with the first version.
And hopefully it's what you saw. the beginning of this video okay so i have not yet watched this but you can see that this went from the original being what was this a little over a minute a minute and five seconds to now being cut down to 28 seconds let's go ahead and give this a watch and see how this looks isn't it crazy that with just my natural language i can get all of these crazy motion graphics right here and i can get all of these insane animations over here as well i can have subtitles appearing at the bottom like you see i can take my face and i can put it in the bottom right corner or i can bring it up to the top left corner And I can even play you guys clips of a bunch of my different YouTube videos right here in this sort of 3D fashion.
So by the end of this video, you will know exactly how to actually do this, even if you've never really used Codex before or you've never edited videos before. So I don't wanna waste any of your time. Let's just get straight into this video.
Okay, not bad. Not bad for a first pass. You can see how my very specific prompting obviously benefited us here.
I think that these look good, right? Like we get some 3D animations, we get some motion graphics. I like it.
I think that's a good way to start. I do think maybe... We need something more in the first two seconds.
Yeah, I think we should add something right there in the first two seconds just to make it more engaging. But the other thing I noticed is right here. It's playing videos, which is good, but they're like interlapping with each other, right?
So it's not realistic. What we need to do is make this feel more legit. And also I wanna make this text bigger.
I don't think that text is big enough. And I think this looks fine. This is all simple, nice little animation as well.
Basically, that's my feedback. So let us shoot off prompt number two. I'm gonna once again do another slash goal prompt.
Awesome, so. I mean, that was 18 minutes. That was a really good first pass, but let's do another version here.
What I want is a couple of things. First of all, in the first two seconds, I want you to get creative here. Do something that feels on brand to make the first two seconds more engaging.
I'm not sure I want like a full screen cutaway and I don't want anything that's going to lay on top of my face. But you know, I start off the video by like, isn't it crazy that with just my natural language. Some sort of animation some sort of motion graphic make that a little bit more emotional Just do something right away to sort of like hook the viewer in now besides that the only other changes I need are in the part where you show my YouTube videos you show the four I like how these look like they're 3d and they have depth but if you could make this more realistic because they clearly are like Cutting through each other almost like it's not realistic.
We need this to be more like the physics of it need to feel better. So if you could just maybe make them thicker and make sure that they're, they're fanned out behind each other rather than like cutting through each other, that would be great.
And then the text on that screen, it says like your videos or something. Um, if you could just make that larger, cause that text was pretty small. I want it to be bigger and easier to read.
But besides that, everything else I thought looked really good and it matched the transcripts really well also. So make those changes please. And then let me know when you're done.
So that is prompt number two going off as another goal. Now you can see that this is the actual hyperframe studio that it created for us. This is at 107.
Let's just reset that. And what's cool is I can literally move things in here. So I can actually take this element and I could increase the text size over here.
I think font, this is where I would do it. I could change this to what, like 80 and see how that looks. So it would reload and now I can just sort of manipulate this stuff right from here, which is pretty cool.
You know, you can move stuff around and you can see there's even different elements for the actual like 3D. and the actual video inside. So I'm not gonna mess with that right now.
I honestly don't use that interface too much. But if you're editing a really long video, let's say it's like a 10 minute video, and you just wanna be able to like tweak one thing really subtly, it's probably easier to come in here, make a little tweak, like just move this over. and then export it rather than having to do the prompt layer again.
So it's really nice that HyperFrames gives you this local host environment as well. But for something as simple as what we're doing, I just wanted to shoot off another natural language prompt. So I will check in with you guys once this one has finished up.
All right, so that took 10 minutes now and V2 has come back. Let me go ahead and open this up full screen and we'll give it a watch. Isn't it crazy that with just my natural language, I can get all of these crazy motion graphics right here and I can get all of these insane animations over here as well.
I can have subtitles appearing at the bottom like you see. I can take my face and I can put it in the bottom right corner or I can bring it up to the top left corner. And I can even play you guys clips of a bunch of my different YouTube videos right here in this sort of 3D fashion.
Okay, so this was much better. The text got larger and this feels more 3D and it also just feels like, you know, it just looks better. And so right here, this is pretty much the only section where I didn't tell it exactly what I wanted.
And this is what it came up with. I don't honestly love it, but for now, I'm just going to keep it in because I told it I didn't want a full screen takeaway, which would have meant it created its own animation to be the full screen. But actually, let's just see what that would look like if I just shoot off that quick prompts real quick and say.
Awesome. Now, can you create me one more version where in the first two seconds before you cut into like the motion graphics and everything, let's see what this would look like if you did a full screen takeaway. So it would be the full screen is animated against some sort of background that feels on brand with the rest of the intro.
And maybe the text is sort of. comes in in an animated way that says, isn't it crazy? So anyway, I was just gonna shoot that off.
This really shouldn't take long at all, but just to show you guys that it can also do things like a full screen cutaway and animate it in that way too. So I'll show you guys that in just a sec. All right, so that one came back and it's done.
And I have a feeling that it's basically just gonna be super simple right here. I'll play it from this interface. Isn't it crazy that with just my natural language, I can get all of these crazy motion graphics right here and I can get all of these.
Cool. So that is looking good. We can see basically all this did was just add some very simple animated text that came in here and had a little bit of layering as well with these little liquid glass looking cards.
And it kept the background consistent to what we actually use later over here. So I thought that's pretty good. Anyways, guys, at this point, we've set up the project.
You've set up something to transcribe. If you decided to use 11 labs and you understand now the loop that we actually go through. In order to do all this, I didn't dive too much into this actual interface and how you control it.
But like I said, it's very, very intuitive once you get in here and it's a nice touch by hyperframes. So don't forget if you want to get the student kit that has all of the skills that you need to build these sorts of reels and videos, you can download this for completely free by going to my free school community. The link is in the description.
You'll go to classroom and click on AI skills and it will be in there. But guys, that is going to do it for today. So I really hope that you enjoyed the video.
You learned something new. And if you did, please give it a like. It helps me out a ton.
And if you want to see other stuff that you can do with Codex and with GBD6 Azure, then definitely check out this playlist that I'll link right up here. I hope to see you guys over there. But thanks for watching until the end.
And I'll see you in the next one. Thanks.
The Hook
The bait, then the rug-pull.
The video opens with a rapid-fire preview of AI-generated reels, a Claude workflow explainer and an NVIDIA free-API pitch, before cutting to the real premise: an agent that turns a spoken description into synced motion graphics, animated subtitles, and B-roll with no manual editing.
Named ideas worth stealing.
12:20list
The AI Editing Loop
- Transcribe
- Cut
- Plan the beats
- Use skills/hyper
- Verify
The five-step order the presenter uses for every AI-directed edit: get a timed transcript first, remove dead space, plan the visual beats against that transcript, generate using a saved skill, then loop back through verification until the result holds up.
Steal forAny agentic content-creation pipeline: transcript-first, then structure, then apply a reusable skill, then verify in a loop before calling it done.
How they asked for the click.
VERBAL ASK
08:05link
“please consider subscribing and joining my free school community”
Dropped as a natural pause while a render was in progress rather than a hard sell, and tied to a community-size stat (almost 450,000 members) instead of a discount or urgency.
MENTIONED ON CAMERA
FROM THE DESCRIPTION
PRIMARY CTAWhere the creator wants you to go next.
AFFILIATECommission earned if you click.
OTHER LINKSAlso linked in the description.
Visual structure at a glance.
