How to Make Amazing Videos with Claude and HyperFrames
A HyperFrames builder who has only edited for six months walks through the editing vocabulary, the prompts, and the reference tricks that get Claude to cut launch videos, talking-head episodes and shorts.
Posted
yesterday
Duration
Format
Interview
educational
Views
7.5K
114 likes
57 · 43
Big Idea
The argument in one line.
AI video editing now works mostly in one shot, and the quality comes from vocabulary and context: name the edits the model already knows, describe the story and energy, and hand it references instead of frame-by-frame instructions.
Who This Is For
Read if. Skip if.
READ IF YOU ARE…
You record talking-head or screen-share videos and still clean up filler words, pauses and retakes by hand on a timeline.
You ship software features and need short launch videos without hiring a motion designer for every release.
You already use Claude Code or a similar agent and want to know which editing words get better results on the first pass.
You keep seeing the same hook effects on Instagram and TikTok and want a practical way to recreate one in your own brand.
SKIP IF…
You are a professional editor looking for advanced craft technique; this is a vocabulary-and-workflow primer for non-editors.
You want a tool-neutral comparison; a large share of the demo happens inside the guest's own HyperFrames desktop app.
TL;DR
The full version, fast.
Frontier models can now edit video close to one shot, but only if you speak their language and give them context. Learn a short vocabulary: rough cut, filler words, pauses, retakes, jump cuts and punch-ins for cleanup; zoom-ins, B-roll, speaker cards and whip pans for hooks. Combine every cleanup request into one prompt, use an accurate local transcription model like Parakeet so cuts land on real word boundaries, and specify music volume because models cannot hear. For launch videos, describe the story in four parts (hook, context, payoff, brand), ask for a storyboard of stills before a full build, and lean on references, brand kits and frame annotations to steer revisions.
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.
Raw takes versus the finished cut, and the cleanup terms to use in a prompt: rough cut, filler words, pauses, repeats, retakes, jump cuts and punch-ins.
06:14 – 08:40
02 · Parakeet for accurate cuts
Why bad transcription timestamps clip words, and the free local Parakeet model that fixes it. Includes the Wispr Flow sponsor read.
08:40 – 13:37
03 · Hooks: zooms, B-roll, transitions, music
Push-ins, cut-ins and easing curves, B-roll and speaker cards, cut versus whip pan, and how to ask for music without it drowning the voice.
13:37 – 18:41
04 · Demo: launch video from three screenshots
The background-removal launch film, the short story prompt behind it, and asking for a storyboard of stills before a full build.
18:41 – 20:39
05 · Launch videos in four parts
Keep feature launches between 30 seconds and a minute and change, structured as hook, context, payoff and brand.
20:39 – 23:28
06 · AI avatars and brand kits
Claude used HeyGen to generate a grid of fake creators, including the guest's own avatar unprompted, and brand kits pulled from a website keep colors consistent.
23:28 – 29:25
07 · AI edit of a raw YouTube episode
A 20:30 raw episode cut to 18:11 plus a table-of-contents intro reel built from two reference screenshots, and why YouTube needs fewer effects than social.
29:25 – 36:57
08 · Copying any video's style
Upload a five-second reference, let the agent reverse engineer it, then restyle. Plus AI-generated split-screen B-roll and the moments library of launch-video sections.
36:57 – 41:41
09 · Draw feedback on the frame, plus final tips
Annotating frames to queue revisions instead of typing timestamps, a blur-PII skill, segmenting long videos, saving workflows as skills, and where to find HyperFrames.
Atomic Insights
Lines worth screenshotting.
Using editing terms the model already knows, like filler words, retakes and jump cuts, gets a cleaner first cut and wastes fewer tokens.
Put every cleanup request in one prompt: remove filler words, trim pauses to a quarter second, drop repeated phrases and retakes.
A weak transcription model gives the agent bad timestamps, so tight pause trimming chops off half of a word.
Parakeet, a free local transcription model of roughly a gigabyte, lands the right gap between words about 98% of the time in the guest's use.
Models cannot hear, so added music often comes back too loud; tell it to sit at about 10% of the A-roll volume.
A zoom-in at the very start of a video is one of the cheapest, strongest hook moves you can ask an agent for.
You do not need to choose between a cut and a whip pan; list the transitions you like and let the model pick placement.
The guest's launch video started from three screenshots and a short story prompt, with almost no editing jargon.
Asking for a storyboard of still frames before a full render catches problems early, because full video builds are slow.
A feature launch video works in four parts: an engaging hook, how it works in the product, the payoff for the user, then the brand.
Saying 'use my brand' without supplying colors and fonts gets invented colors nine times out of ten.
A 20 minute 30 second raw recording became an 18 minute 11 second episode after one AI cleanup pass.
Energy words like 'high paced' or 'refined, professional, sleek' steer an agent's motion graphics better than technical specs.
To copy a hook style, upload a few seconds of the reference clip, let the agent reverse engineer it, then change font and color.
Splitting anything over 15 to 20 minutes into segments avoids reprocessing the whole video for one late edit.
Once an AI editing workflow works, ask the agent to save the steps as a skill so you never rebuild it.
Takeaway
Vocabulary and context decide AI edit quality
WHAT TO LEARN
Agents already know how to edit; your job is to name the edits, describe the story and energy, supply references and brand, and review stills before paying for a full render.
01Video editing 101
Name cleanup jobs in standard terms, filler words, pauses, repeats, retakes, jump cuts, and combine them into one prompt with examples.
Give pause trimming a concrete target, like a quarter second, so the model has a measurable rule instead of a vague request.
02Parakeet for accurate cuts
Use an accurate local transcription model such as Parakeet, because tight cuts depend entirely on precise word timestamps.
03Hooks: zooms, B-roll, transitions, music
Open with a zoom-in, since a push-in or cut-in at the start leads the eye and pulls the viewer into the frame.
List the transitions you like and let the model choose placement rather than deciding where every whip pan goes.
State music volume explicitly, around 10% of the voice, because the model cannot hear the mix it produces.
04Demo: launch video from three screenshots
Describe the storyline and goal in plain words; heavy editing jargon and exact timings are no longer needed for good launch videos.
Ask for a storyboard of still frames first so you can catch wrong directions before a slow full build.
You still need the idea; the model fills in execution but cannot invent the story you want to tell.
05Launch videos in four parts
Structure feature launches as hook, how it works, payoff, brand, and keep them between 30 seconds and about a minute.
06AI avatars and brand kits
Supply real brand colors and fonts or a brand kit, because 'my brand' alone produces invented styling.
Generated avatars and B-roll replace hours of sourcing example footage when the clip only needs to illustrate an idea.
07AI edit of a raw YouTube episode
Expect a cleanup pass to shrink raw footage; a 20:30 recording became 18:11 with no content lost.
Keep YouTube effects restrained and let the speaker carry it; social short-form can run busier to stop the scroll.
Describe the energy you want, fast and chaotic or sleek and professional, since models translate mood words well.
08Copying any video's style
Copy a style by uploading a few seconds of reference, letting the agent reverse engineer it, then changing font and color.
Experienced editors can reverse engineer their own past work into reusable code references for consistent output.
09Draw feedback on the frame, plus final tips
Mark revisions directly on the frame and batch them, instead of typing timestamps while watching.
Split long videos into 15 to 20 minute segments so a late change does not reprocess the whole file.
When a workflow works, have the agent save its steps as a skill so the next video starts from it.
Glossary
Terms worth knowing.
Rough cut
The first cleanup pass on raw footage that removes mistakes, retakes and dead air so the recording follows the intended storyline before any effects are added.
Filler words
Verbal padding such as 'um', 'uh' and 'you know' that editors remove to tighten speech.
Jump cut
A cut inside the same shot where time is removed, so the speaker's head appears to jump slightly between positions.
Punch-in
Moving a clip recorded later to an earlier point, or cutting to a tighter frame, to add context or hide a jump cut without re-recording.
A-roll
The primary footage, usually the person speaking to camera, that carries the story.
B-roll
Supporting footage or graphics shown over or between the A-roll to illustrate what the speaker is describing.
Push-in
A zoom where the frame appears to move gradually closer to the subject, as opposed to a cut-in that jumps to a tighter frame instantly.
Whip pan
A transition where one scene rapidly slides out of frame in one direction while the next scene slides in, with motion blur.
Easing curve
The speed profile of an animation; most creators use one that starts slow, accelerates, then smooths out at the end.
Speaker card
An on-screen overlay introducing the speaker and their credentials, often used early in a video to establish authority.
Parakeet
A free NVIDIA speech-to-text model that runs locally and returns precise word timestamps, useful when an agent trims pauses to fractions of a second.
Brand kit
A saved set of colors, fonts and logos an editing agent applies so every generated video stays visually consistent.
Storyboard
A sequence of still frames previewing each scene of a planned video, reviewed before the full animation is rendered.
“I came with three screenshots. It came up with so much of this on its own.”
concrete before-and-after claim in one breath→ TikTok hook↗ Tweet quote
27:43
“That's the dream of a content creator. You can just yap to the camera and then Claude will add all the screenshots and everything for you.”
states the whole promise of AI editing→ IG reel cold open↗ Tweet quote
21:42
“None of these people are real except for you in the middle there. Or even you is not real.”
surprise reveal over a visual grid→ TikTok hook↗ Tweet quote
09:08
“I can't understate how powerful a zoom-in is at the beginning of the video.”
single actionable tip, no setup→ newsletter pull-quote↗ Tweet quote
12:57
“Models still struggle with audio. They can't hear anything.”
counterintuitive limitation with a simple fix→ IG reel cold open↗ Tweet quote
16:11
“The biggest bummer for people still today with editing with AI is that you probably do still need your idea.”
honest caveat that cuts through hype→ newsletter pull-quote↗ Tweet quote
The Script
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.
17px
metaphoranalogystory
I came with three screenshots. It came up with so much of this on its own. None of these people are real except for you in the middle there.
Or even you is not real. That's my avatar as well. Yeah, and I didn't even ask for myself to be in there.
That was actually Claude's discretion. You just upload a reference, so I uploaded this five seconds, and then I described in the prompt just what I wanted to change. You can just draw on what you want to change, leave the note, and then they'll cue.
I think that's the dream of a content creator. You can just yap to the camera, and then Cloud will add all the screenshots and everything for you.
All right. Hey, everyone. Today, I'm really excited to welcome back Jake from Hyperframes.
Jake has only been editing videos for six months, but to me, he's the go -to expert on how to use AI to edit videos. Today, we're going to walk through video editing 101 and also how to edit product launch videos, talking head YouTube videos, and also short form videos. So welcome, Jake.
Hey, Peter. Thanks so much for having me. Why don't we start with this?
I'm like a total new year when it comes to video editing. Can you walk us through some video editing concepts and terms and what they might look like so that we can all get educated? Video creation, it's a super wide net.
So... There's tons of different types. There's launch videos, which is what I've worked on primarily for the last few months.
I'm actually just now really getting into the weeds of editing something like this, which is a podcast where we've recorded this and then we need to do some kind of cleanup later. And I want to try and visualize a couple of these things here today. When we finish recording this video, we're going to have something called the raw video or the raw takes, which is going to be maybe slightly longer than what the finished video will look like.
And so in the case of using AI, it makes it a lot easier to get to this kind of shortened version that's a little bit more polished there's a couple terms that are worth knowing and i'm sure peter's going to be able to to share this out in some form later so that we have a visual reference as well For me, I use Hyperframes as my editor.
There's plenty of other editors out there. Hyperframes is HTML based, so it's a pretty native way for agents to edit. So I find a lot of these techniques to work pretty much one shot if you ask for them.
So there's in terms of like cleaning up recordings before you put anything crazy on the screen, there's something called the rough cut, which you can ask your agent for. This is basically where we take out a lot of the mistakes that might have happened during recording and get back to that consistent storyline that you wanted when you...
started recording. The way that I would do a rough cut is I would say, let's remove things like filler words, which are all the things that I'll probably say right now on this podcast I would normally want to remove to get to the meat of what I'm trying to talk about. The same thing, I'm probably gonna stop and think about something before I say it, which would be considered a pause.
It's probably pretty self -explanatory, but it's important to use language that both you and the LLM will recognize because that'll help you get to results faster, not waste tokens. We all know that AI is expensive. Editing definitely isn't outside of that.
So there's different things that you can ask to be removed because models can do transcription, which is basically taking the audio and understanding what was spoken from that. It can find filler words. It can find the pauses because it'll take timestamps.
It can find moments where I say something twice. It can also find things where I might start saying something and then I'll realize that I might have blundered and I say it again. All of these can be found.
The key is that if you really want to maybe guarantee that you're going to get closer to that cut. down that you want that first go is if you use these types of terms which is hey I think I had a lot of filler words here's an example I might have said I want to remove ums I think there was a moment where I was pausing a lot I would like to cut all the pauses to around let's say a quarter of a second or less.
And it goes down the list in the same way, right? I might have been repeating words. I want to get rid of those.
I know that I did a retake around here. Basically, I think this is true with all things AI, but it's also especially true with video editing. Getting as much context.
into your prompt, into wherever you're asking things to be edited is the key to increasing quality and getting closer to what you're wanting. So the biggest thing you can do is try and explain as much as possible. And this is just to finish it, the jump cut and the punching.
So jump cut is like all of a sudden you like jump cut to saying something else and a punching tries to hide some of that stuff, right? Yeah. So same kind of thing.
If I The way the LLM will probably do it is if I say if two times, it'll cut out one of those ifs and then move to whatever the next item is. And so that will just, to the viewer, they might notice it just because it will appear as a slight.
oh my head might have moved from here to here because in between that the time has been taken out and then the same thing here if you want to move something that you said later to earlier in the video that would be the same idea where you're punching in this clip that would add additional context for the viewer at the right time in the video so these are all ways to use your footage that might have happened later without having to fully re -record something Got it.
And basically you have individual prompts here, but usually what I do is I just combine all this stuff. You do one prompt, right? Just like remove all the filler words, repeat phrases, jump cuts, use punchings.
Yeah. Yep. Yeah.
And this only happened really in the past, basically with Opus 5 .5, maybe with Astra and Gemini 4. So really only the past few months, right? It was able to kind of...
get to this level. And for this, for the main video, I had to look at the timeline and look at the transcript and cut stuff out. And it just took forever, man.
So, so I think this is a massive time saver. Yeah. And you also had a tip that you told me because some of the transcription models aren't as good.
Like can you share that tip? I think you use Parakeet or something. Yeah, so I use Parakeet, which is a locally hosted model.
I think it's about a gigabyte in size. So it's big as local models are, but it's worth it. So basically all of these tools, no matter what you use, either if they're operated from MCP, which would be the kind of older generation tools, that's how AI interacts with them or us.
They normally... have some kind of transcription software. For hyperframes, we have a smaller size local transcription model.
And the thing is, sometimes it misses on the exact timestamp. It's a bit hard for LLMs to figure out exactly when something's set down to the millisecond, but it's key for, let's say, Instagram or TikTok -based editing where it really, really matters that you're super... concise and that the pacing is really high and so you might ask to be like okay cut down the the pauses in between sentences to a quarter of a second with a bad transcription model the llm will think okay cool and then it might be operating on some bad time stamps and then you'll have like half your word cut off or things like that that are awkward so parakeet for me works 98 % of the time to getting the right amount of time in between words or whatever the case you need.
It just allows the LLM to get really good timestamps, which is everything for these types of, let's say recording cleanup. Awesome. Yeah.
We can link the Parakeet model. It's free in the video description. This episode is brought to you by Whisperflow.
Whisperflow saves me at least three hours a week. and is one of my favorite AI apps by far. It's just so much faster to dictate to AI using your voice than to type.
You just talk naturally and it outputs clean, ready -to -send text. Whisperflow even removes filler words and formats your sentences for you. I use Whisperflow for everything including drafting newsletter posts, writing product specs, replying on Slack, and more.
It works on Mac, Windows, iPhone, and Android across all of your favorite apps. Try it free at whisperflow .com and use my code peterwhisperflow.
So that's the main video, like getting rid of the repeat phrases and all that kind of crap. What about the intro? The intro is trying to hook the viewer, right?
I think you have some more stuff down here. Yeah. So intro hook.
are normally the main terms you're going to hear i think the biggest thing is if you're trying to get into this game of creating video you're going to hear all of these buzzwords and they a lot of them mean the same thing intro and hook are generally the same thing and normally what you want to do in these if you're editing existing footage i'll go into it with motion graphics as well but you'd want probably your most engaging piece to come from that.
And so when you're editing existing footage, normally that takes the shape of a couple effects. And so those can either be motion graphics or those can be things that are done to the footage itself to make it a little bit more engaging. One that's probably super familiar to people, at least from visually understanding, is zoom -ins.
I can't understate how powerful a zoom -in is at the beginning of the video. It just leads your eye somewhere and kind of wraps you into the world.
And there's tons of different ways to do that. You can ask an LLM right now to just add a zoom in in the beginning, and it'll probably look pretty good. There's different types of zoom in.
So there's push ins where you start further away and then the camera kind of appears to come in closer like this and then there's pull back there's cut in where we don't actually see the zooming happening it just jumps from one position in frame to another and all of these are controlled by a certain speed most creators you'll see are using a curve that looks something like the one on the right here where we start slow kind of ramp up and then smooth out towards the end Then the next types of things you can add to a intro or hook is B -roll.
So this right now that we're hovering on is all A -roll, but this would be an example of B -roll, which is something that you might be talking about later in the video. It might be something that's just for the purpose of being visually engaging. It might be maybe a table of contents for a more tutorial style thing.
If you're somebody like Peter that has a big audience, you might put your overlay explaining, hey, here's the reason you listen to me because I've got a big audience. I've got a long history, right?
Like there's certain pedigree that's normally used for these speaker cards, things like that. So these are a couple examples of other types of techniques that people use. So transition in this case is pretty broad, but the one that's shown here is just a cut.
where there's no effect being done to the footage in scene A from the footage to scene B. We just straight drop in. The second one on the right is called a whip pan, where it appears that the scene A would go out to the left and then scene B enters to the left.
You can do this in any direction. It's just another example of more visually engaging ways to hook in viewers. Nice.
these are examples as well other kinds of transitions and and maybe you can just like maybe we can just like because i don't actually know when to whip pad versus cut so maybe maybe we can just like mention all the transition names or like a bunch of them and be like hey cloud use your best judgment too exactly yeah yeah honestly yeah i i it is rare that i'm deciding what exactly needs to happen at when.
It's more, hey, I like these effects, right? When I see another creator use, let's say, the whip pan, I like it. I think visually, it's just a really engaging type of effect.
Leave it up to Claude. It's going to make the choice for you and it'll probably be pretty solid. Got it.
Awesome, dude. And then you can also ask it to add music. Do you have to use Suno or you can just randomly add music by itself?
Yeah, so... So this one's super new to me and I'm still experimenting with it, but Opus can make its own music too. So it can use MIDI and create its own tracks.
You can point it at different types of libraries to create its own music. If you just ask, hey, don't use a generative model, make your own music. There's, you can, if you have local files on your desktop, which I do, I just drop it in chat.
I'm like, hey, please add this music. One thing. That kind of goes back to the idea with transcription as well.
Models still struggle with audio. They can't hear. anything and so often if you just say put the music in it might come back super loud against what you're talking about and against your voiceover so i normally just say keep it low you know keep it at 10 of the volume of my a -roll there's all sorts of ways to describe this but just being a little bit clear normally helps again turns with editing take a little while it's not the fastest thing ever so if you kind of have an idea that something might happen or you kind of have an idea of what you want It's better to just list it all out before sending the agent off on some kind of task.
Awesome. Yeah, this is awesome. And of course, asking it to cut the transitions to the beat of the music will take it to another level, right?
That's kind of... Exactly. Yeah.
Dude, so do you want to show us a finished video that you made? Should we start the product launch one or should we start with something else? So this is something we launched.
last week which is a feature inside of our desktop app hyperframes desktop app that allows people to remove background on video and images what i'm really going to actually be going over is more of okay how did i actually make this video right there's the meta idea of we have this feature how do we describe it to people and so i came up with this All right.
That's pretty great. So that's pretty good. So yeah, that's how you made this.
Yeah. So let me open up. In our case, I made it in our desktop app.
You can also use our tool natively within Cloud Code app or ChatGPT, anything. I'm just going to show our app because that's where I made it. But the creation flow is largely the same thing.
This just made it easier for me to edit later. Basically, I came with three screenshots. That's what I came with when I wanted to start this video.
So one screenshot I had was of our actual studio because I knew I wanted to share it later. I came with the images I wanted to use in Hook. And then I sat down and I wrote this prompt.
And kind of core to what I was going over earlier, it's the same idea with motion graphics videos as well. As much context as you can feed is ideal. So but this isn't it isn't that much.
And the key is that I'm not actually using really much editing jargon at all, which goes back to that idea that like Opus and these newer models, they're going to make a lot of these choices themselves. And you'll be amazed once you get started by what they choose to do by themselves. What I'm really going over in this is the storyline that I wanted.
And I will say, and this has come up before, the biggest bummer, I think, for people still today with editing with AI is that you probably do still need your idea, right? You probably still need to know a rough storyline that you want to convey. And so in the case of this video, when we were creating the background removal feature, one of the engineers on my team had actually shared.
this hook sequence basically with me in Slack and was like, look, we have background removal and it works and showed this image with the background removed. And I was like, okay, that was super cool. I want to use it in the video.
So I came to create my launch video with the same asset that he had shared, dropped it in, and then loosely in the chat described what I want. which is literally not that much information, right? It came up with so much of this on its own.
And then the rest of it, I just wanted to explain kind of the, now it's just a prompt away, like the idea of just normal. how people do the more marketing -y type things in these videos where it's just like, oh, it's a prompt away, right? Things like that.
But it wasn't like, okay, now we're going to cut into this and it's going to be 35 seconds and all of the very specific things that could have happened. I actually don't really feel like you need to prompt like that anymore. It's more about get out what you're thinking and you'll get something back.
And the last thing is I normally ask for a storyboard. In this case, in this tool, we actually have this as a thing you can select. So I had that selected.
And so the LM goes off and it makes something like this if you ask for it. Otherwise, it'll probably go build the full video, which takes a long time. I prefer just because motion graphics, I have a certain standard I want to get to.
I prefer to look at still frames of what's going to happen over the video instead of kind of working on the fully built thing. But basically going back to that full video that we saw. You can see all of the pieces that actually ended up making it to the finished film.
But this allowed me to edit things first. So you can see I didn't end up having this exact look. So I asked for more things later when I got the first build back.
I normally just use this as a rule of thumb where I don't need it to be perfect. But if I can kind of see what I want, then I'm good to let it build. But it allows you to catch some of the things that might be issues a lot faster.
And generally speaking for product launch videos, I think you've made the most of these, right? So just as a high level, do you have any quick guidelines for making these? Like, you know, they're usually like 30, 45 seconds long.
They just tell a story, maybe like bring the problem or show a solution. Yeah. In our case, the...
Mainly what we're doing with product launch videos is it's some feature, which is a subset of our larger product. I'm not often doing like, here's this new company. I have to explain the founder story and all the things that you might see for when people announce a round or something like that.
Often what people really need is, hey, I just. made this tool in our case our engineers go crazy all the time so i'm getting pinged at 5 p .m being like hey we just finished this do you think we could talk about it tomorrow right so it's it's some smaller scope item that is useful to something or some subset of users and then within these videos you want to be concise they don't need to know a ton of things So you try and get somewhere.
I, or generally I try and get somewhere in like 30 to a minute and change 30 seconds to a minute and change. And I start with some kind of engaging hook in the case who is in this case, who is that kind of basketball thing. But in general, this is the hook is probably your most creative thing.
And I'll get into different ways to add context in just a second, but the hook is your most engaging thing. Then you kind of want to lead to how to use it in the product generally. And then what the payoff is going to be for the end user.
And then maybe you need some kind of follow -up information about if it costs money or something like that, or just like, Hey, we're Hyperframes again, by the way, right? Just reminding people of the brand. So I normally think about it in four sections, hook, kind of like the context building, the, maybe the call to action or the output, and then coming back around to like, Hey.
here's our brand got it and a couple of quick questions so i think the avatars are actually not generated by claude you're using hey gen right to make that yeah people yeah yeah so i don't like being on camera i also don't have access to a ton of creators so i being a hey gen employee being someone that's been around hey gen way before i started doing this hyperframe stuff I've gotten super comfortable with just using avatars to generate assets that I need in videos.
In this case, like we'll see later in this video, right? We have this crazy grid wall of video examples. I could have pulled these from online.
I'm lazy. And I just asked Claude to use HeyGen to generate different characters and then have them speak a couple clips in this way. I could get the idea that I wanted to get across more easily and without me doing any kind of research work on Instagram and TikTok and pulling videos and all the things.
So none of these people are real except for you in the middle there. Is that right? Exactly.
Even you is not real, right? Is it like an avatar? No.
Yeah. That's my avatar as well. Yeah.
And I didn't even ask for myself to be in there. That was actually Claude's discretion. If you have footage, you can use it.
You would just drop it in. In this case. I really didn't want to source it.
I have access to these models. Why not use them? It sped up my workflow and made my night easier.
And you didn't actually go to heygen .com or whatever, right? You just used the MCP and just talked to Cloud to do it? Yeah, so in our desktop app, we actually have...
a direct connection to generative models. In the case you were using it in the cloud desktop app or let's say Codex or anything like that, you would have to connect via CLI or MCP. And that's true for any of these other generative features.
You can use image gen, audio generation like Suno. All of these require some kind of outside connector to generate. Okay.
And the other question I had was, how do you make sure that the brand is consistent across these different videos? Do you have a scale with color and font and stuff like that? Yeah, so we have a feature now that allows you to create a brand kit just from your website.
In this case, I already had brand kits, let's say the HeyGen one, where I can edit all of these items myself, but the agent just pulls them down from your website, or you can upload them if let's say you have a PDF with all of the information or a folder. Got it. This helps so much.
You do need to add it in. If you just say my brand, probably nine times out of 10, you're going to get some crazy colors and an imagined surface. So it does matter to add the context.
For us, we built this natively. You just have to be more specific if you use it outside of our app. Okay.
Yeah, this is awesome. Okay. Awesome.
Yeah. So that's probably launch video. And why don't you show us the other ones now?
I think you actually edited one of my videos, right? One of my talking head stuff? Yeah, I did.
Basically, I might have gotten access to a raw unedited version of one of your episodes. And basically I did. And this was 20 minutes and 30 seconds long.
And then when I finished editing it, it was 18 minutes and 11 seconds. And that comes back to the thing that we were talking about earlier where There were items that were maybe retakes or pauses or things that in the long run weren't necessarily needed.
So the finished output ends up being shorter than the raw footage that comes in. And that came from that initial cut down of the video. That generally, I mean, who knows how much will be cut out?
I've recorded for eight minutes before, and because I was sloppy and didn't have a script and whatever, the finished output of what I actually needed was only a minute, right? You never really know. It just depends on how, let's say, clean you were through the creation process there.
But there are two things I really wanted to do in this example, and we're not going to play the full 18 -minute thing, but I wanted to work on a fun intro reel that I could show off for this episode. And then just going back to this stuff, I wanted to cut out all the things that I might have thought had been pauses, repeated words, retakes, et cetera.
So I ended up creating this intro reel.
Nice. I like listing the use cases because then people actually want to watch you see all 10. So that makes sense.
So that was, and I didn't choose what should be the, where that cut -in should be or anything like that. But it goes back to that idea of if we're going to do a tutorial, most likely you're going to have some kind of table of contents and you're going to introduce that to try and lead people into this video. And so for these effects, i had two examples that peter actually shared with me that he liked and all i did was shared screenshots to the agent of what i was going after and then i said i think i want to do in the case of that that first thing where we showed the apps i just described that right so i had a screenshot of somebody else doing a similar type of hook and then in this case it was just about translating that idea to the contents of this video and then also switching it to the behind the craft colors that that you use for most of your for your videos nice i think one thing with this intro stuff is you want to add some animations and motion graphics but you don't want to overwhelm with the actual person speaking so you have to like do it in their high taste way right you don't want just like add crazy animations all over the place yeah i mean so some some people do i think i definitely agree with you let the a -roll do the work
At the end of the day, you want to learn from the speaker. I don't think we need to go crazy. Some people prefer that look.
But I would say a little goes a long way. And the models seem to be pretty good about this. They seem to be maybe more conservative than...
I normally am. Yeah. Okay.
So basically to make this intro real, you basically just like submitted like some sort of prompt of like, hey, you know, add a table of contents, add a flow of the diagram and so on, right? Exactly. Okay.
Awesome. You know what? I think just real quick on this talking head stuff, you're showing Paul Lipski here.
I actually just talked to him and it's actually kind of incredible how far this thing has advanced. He made a video, I think about Muse Wonder that pretty much other than him talking to the camera, all the other screen sharing and effects were made by Claude. So basically he just kind of shared a link to the MuseWonder blog post and maybe some other assets.
And then Claude made all the text effects and highlighted the right part where he's speaking. And I haven't tried this myself, but it's pretty incredible because I think that's the dream of a content creator. You can just yap to the camera and then Claude will add all the screenshots and everything for you.
No, yeah, exactly. And I think there is a fundamental difference between, let's say, a YouTube video versus these more short form that end up on TikTok and Instagram. Normally, you lean a little bit more towards the a lot of effects or more busy on social media, just because we know it's harder to stop people from just scrolling on to the next video.
Whereas YouTube, the commitment normally comes more from the thumbnail and the other things that. get people to click in. So for those types of videos, again, Claude also now and Astra and Gemini and all of these kind of leading frontier models, they all also seem to have this sense.
It's so crazy. You can probably just give the link to the blog post. You can give maybe a couple other assets if you have them on your computer and a rough description, just even if you just describing the energy is so valuable to the to the agent if you're just like i want this to be high paced i want this to be kind of crazy right or i want this to be refined professional sleek these types of more general i like to say energy type terms work really well for for helping these models get there we added one feature that i'll show just for another way of doing it basically It all comes back to how can I add more context to the agent?
Giving a link to a blog post really helps. The other thing is if you have styles that you really want to emulate, you can either watch them really slowly and try and describe them, which let's say I really liked this creator's effect for a hook or an intro for social media. How I was creating videos in the last...
for four months, five months before for the last couple weeks when we unlocked this new tool internally and we shared it yesterday. If I liked this effect, I would just describe it, right? Which I'm saying that just if you really want to copy someone's effect and then turn it into your own, it's not the simplest thing.
As you can imagine, there's a lot of little nuances in what just happened in this hook, including how the... words enter how there's background removal so that some of the items can be slightly behind the character there's a lot that needs to be described and that's what i would kind of struggle with in previous months now if you scroll x or if you scroll instagram or whatever if your algorithm is remotely involved in this game you'll see people are learning how to recreate certain effects in different ways yesterday we added this as a native capability to if you just upload a reference so i uploaded this five seconds and then i described in the prompt just what i wanted to change right because you can see where we're drawing inspiration from but at the end of the day this feels like a very different scene because there's different font different colors but it's still structurally the same idea and a lot of people when you look on social media or or video sharing platforms.
There is kind of a convergence I would say happening on certain effects and a lot of people want to use those effects. So this gives you the ability to create those or you can just try and describe them, right? There were only probably 10 total things that happened in this hook.
It's more about getting those right. It's easier if you can start with references. May that be screenshots.
May that be previous videos. May that be somebody else's Hyperframes project where you have the code to use. All of these are valid paths to getting to what you want.
So basically, the way this is, first you upload the clip and then you... Asked AI to reverse engineer it, and then you added your own tweaks to it, right? Exactly.
Just for what I wanted in my video. And you can do this. with all different types of things.
So this is like a split screen effect to motion graphics on top were generated by hyperframes. We added captions. The other thing too is existing creators, right?
If you're someone that's been editing for a long time, maybe, and you're looking to get into AI editing, this would be really useful because you just want a one -to -one of what you've probably already gotten down to, right? You have your style, you have your colors, you have your... formats, all of these things are dialed down through years of creation.
You now have a library that can be referenceable if you reverse engineer it into code. And so that's another path for the more already creating type of people as well. And I like you showing the split screen view because now you can actually use AI to generate the B -roll footage on the split screen.
Like probably that playing is probably just AI generated. Exactly. Yeah, because before you had to go find all the bureaus and customize it.
It'll take forever. But now you can just like, yeah, generate the stuff. And in like the agent can also probably find real footage to download it and then use it as well.
So all of that, a lot of it, it's just becoming more and more hands off and more and more focusing on what you're trying to convey exactly in that moment. And that's what's making it more fun for me as well, trying to ramp up how much we can share about tools like this online. It's getting easier for even myself to talk about creating with these tools because they're getting so much better.
I think honestly, like the A -roll, the person talking can probably just be AI generated too. Yeah, I mean, it's up to you. Yeah, if you don't want to record, you don't have to.
If you do want to record, do it. It's all kind of the same process at the end of the day. It's just more up to your discretion, which is great.
Awesome. Well, anything else real quick you want to show on the short side? I do want to show one thing just for product launch videos, because I think maybe if people see Hyperframes, they might want a little bit of additional info here.
So we have these things in our desktop app that we call moments. That's an internal term, so I don't believe. Everyone will know that right away, but it's going back to that idea of there's probably four main sections in what you create in a launch video.
So like the hook, proof, the turn, these are all just ways of expressing sections. And what we have here is examples of how people have done this before. And all of these are available to anyone if they use our desktop app.
And all you have to do is add them and then add a little bit of additional information. And I have this article here where I visually just quickly show the three styles of three ways that we use inspirations internally. And so there are three ways that I would ask the agent to use a section for something that I'm creating, which is either make it ours if I'm using a bunch of them.
I would say something like this, each one doing its own thing, serving the purpose of the new story, or I want to take from some of the energy. And you can see these are the actual prompts that went in, which is basically, this is the same idea of just the context that we have launched. And then it's that same get inspired by these.
So it's really lightweight. You add the moments that you like, and then. it'll recreate within your brand context because my brand kit was selected.
Yeah, this makes it easier instead of because I remember you had like a cloud video of the cloud avatar typing stuff. And before I had to go find it in the GitHub, right? Somewhere.
Exactly. Before my agent would have to find it. But now I can.
Exactly. Should we find it? At the end of the day, for us, the desktop app allows us to visualize a lot of the things that have been hidden in some repo or whatever it is, like some X article or something like that.
It just allows, because video creation is so... visual for, I mean, it is, it's so much easier as the end user to have everything available to you to see and then reference when, when you you're ready to start creating. So I just wanted to show that I'll also link this article.
I'm sure with. Can you also show one more thing? Okay.
Let's be real here. Many times the thing can one shot it, but a lot of other times you have to give it feedback. And I honestly haven't tried Hyperfine Studios before.
I'll probably try it right after this, but when I just use cloud. I have to give a feedback, I'll be like, hey, five minutes in, go do this, 10 minutes in, go do that. And it's kind of annoying to type that stuff out in text.
There probably is a way to annotate the stuff, right? In the frame. Yeah.
So that was the other big addition for us. I also have been up until two weeks ago when we had this desktop app internally edited of. the same format which was i watched this whole thing and then i'm trying to frantically leave notes as i go like i'm watching it and typing in cloud chat at the same time and that's difficult right i'm trying to like maybe call back and be like well at this moment i said this to give some kind of additional reference or i do the timestamp if i catch it but at the end of the day it it just was frustrating because yes there are going to be edits maybe Opus doesn't get it right.
Or after watching it, you have a better idea. Half the time I'm creating, I'm like, oh wait, no, this would be sick. I should come up with some other thing.
And that's just part of the creation process for us. We added this ability to, let's say I wanted to change something right here. You can just draw on what you want to change, leave the note, and then they'll cue.
Let's change.
Let's change the text.
oh my god to yellow right it'll queue here and then when i'm ready and i've watched through the whole video um let's do instagram i can just send these off which just feels like to me just it's so much easier to to edit using that type of experience than trying to rattle things off. I still sometimes do it if I have like a 10 second video, but yeah, it just makes it a lot more comfortable as the viewer to make edits.
Yeah. And I guess a few more tips from my side. So one tip is I've built a skill called video blur.
That blurs out all the sensitive information. Cause I'm usually trying to screen shares like clock code or something. And there's some PI stuff in there.
And then, so first I get it to do a video blur pass and it just goes frame by frame and blurs out like emails and names and stuff. That's super helpful. And I think also with longer videos, anything longer than let's say 15, 20 minutes, I like to split it into different segments.
So it's also really good at stitching videos together. Cause otherwise, if you want to make a change at like 30 minutes in. to an hour long video, it has to reprocess the whole thing.
We're just going to like, just burn a bunch of tokens. So I actually kind of like spend different segments and edit one by one and then stitch it together or get AI to do it. Yeah.
Yes. Yeah. 100%.
Yeah. We're in a funny time where there's all sorts of things like this, where you have an idea of how it would be faster to be done with AI. Once you nail that, just create a skill or similar.
And all that is, is asking at the end of this session, Hey, let's remember exactly what the steps here are so that I can reference it later for when I'm creating more videos, especially if you're somebody that has a consistent format that you use, you definitely want to save things as a reference. So you don't have to do the same work twice.
Yeah. All right, man. Well, it's crazy times that we live in.
I guess this really democratizes video editing. I think. If you're a professional video editor, you can probably still do a better job, but at least the rest of us can now do enough job.
And I think this is very powerful because I think video is actually the most effective way to communicate something, right? Instead of using slides or text for a lot of things. So yeah, I highly encourage everyone watching this to get Opus to make launch videos for everything or help it edit your videos.
I feel like the ultimate format is a rap battle for everything, like a rap battle video. You know, then people would just love watching it. Didn't you make a rap battle video recently?
Yeah, I made a rap battle of Lauren from Grokbot team versus Tebow from ChatGPT. And I don't think they're actually feuding anymore, but yeah, it was pretty amazing. Yeah, there's so many more things also with AI music and all the things like that, that you can just create kind of whatever you're thinking about and be surprised by what these frontier models are able to do from probably not that much information, right?
I can't imagine that. That was super scripted. So yeah, it is extremely fun.
Yeah. All right, dude. Well, so where can people find you and Hyperframes Studio?
Yeah. So Hyperframes Studio is available to download on hyperframes .dev. Right now it's only for Mac.
And Linux, we are trying so hard to get Windows out. We're hearing everyone talk about it. Hopefully sometime within the next few days, we're waiting on their side.
It's not that the app is built. So we're just waiting to be approved there. Otherwise, you can find our repo, which is also called Hyperframes, and you can use it with any agent.
For me, I'm on X. You can find me at Jake11Moran, M -O -R -A -N. Awesome.
Awesome. Thanks for bringing this tool and showing us your pro tips. I'm really inspired.
I'm gonna definitely do a lot of stuff myself. Thank you so much.
The Hook
The bait, then the rug-pull.
The cold open is a highlight reel of the episode's best claims: a full launch video built from three screenshots, AI avatars Claude added without being asked, and the host's line that the dream is to yap to the camera and let Claude add everything else. Then it slows down and teaches the vocabulary that makes those results repeatable.
Frameworks
Named ideas worth stealing.
02:41list
The cleanup prompt checklist
Remove filler words
Trim pauses to about a quarter second
Drop repeated words and phrases
Cut retakes and blunders
Use jump cuts and punch-ins to hide seams
Name each cleanup job in one combined prompt, with examples, so the model finds and removes everything in a single pass.
Steal forany raw talking-head recording before effects
20:14model
Four-part launch video
Hook
Context: how it works in the product
Payoff for the user
Brand reminder
A 30 to 80 second structure for announcing a single feature, with the hook as the most creative part.
Steal forfeature announcements and changelog videos
34:02list
Three ways to use an inspiration
Make it ours: blend several references into one style
Each one does its own thing for the new story
Borrow only the energy
How to instruct an agent when you hand it reference clips, from close remix to loose inspiration.
Steal forprompting with reference videos
CTA Breakdown
How they asked for the click.
VERBAL ASK
40:52link
“Hyperframes Studio is available to download on hyperframes.dev. Right now it's only for Mac.”
Soft, host-prompted close: download link, open-source repo that works with any agent, and the guest's X handle.
Add Modern Creator as a preferred source and Google shows you more of our breakdowns in Search, Top Stories, and AI Overviews. It only changes what you see, and you can undo it in your Google settings anytime.
Add to Preferred SourcesOpens your Google source preferences with us pre-loaded. Tick the box and you're done.
The VP of Product Engineering and lead PMM at HeyGen walk through the complete workflow for generating polished AI launch videos using HTML, CSS, and JavaScript — at zero cost.
A SaaS instructor takes a host's vibe-coded headshot prototype apart on camera, then rebuilds it inside a pen-tested template with auth, Stripe and a real database.
Replit's head of product engineering walks through three non-coder founders who built real six-figure businesses, then live-demos the four steps that turn a raw prototype into one.
Anthropic's Thariq Shihipar walks Peter Yang through /goal, sub-agent workflows, and a planning habit built entirely around finding out what you don't know before you build.
00:32
01:06
01:49
02:51
03:23
03:54
04:25
04:56
05:28
05:59
07:02
07:33
07:56
08:24
09:07
09:38
10:09
11:12
11:43
12:13
12:45
13:17
13:48
14:47
15:17
15:53
16:24
17:27
17:44
18:29
19:01
20:03
20:34
21:06
21:37
22:08
23:11
23:35
24:13
24:44
25:36
26:18
26:40
27:17
28:04
28:23
28:55
29:26
29:57
30:28
31:31
31:57
32:33
33:05
33:36
33:56
34:25
35:23
35:41
36:15
36:41
37:46
38:12
38:42
39:12
39:47
40:07
41:32
36:07
39:17
36:06
41:48
41:17
28:52