I always like finding new ways to apply artificial intelligence (AI) tools to my day-to-day productivity tasks. Last year, I showed how I used generative AI to rescue some bad audio and otherwise tweak a short how-to video. I used Photoshop’s Generative Fill, Adobe Podcast, and what was then a new background replacement feature in Final Cut Pro.
This time, I’m using an AI gimbal to help the camera follow my movements, Apple’s Voice Memos AI transcription feature in MacOS Sequoia to transcribe an unscripted video, and ChatGPT to suggest titles, tags, and a description for an unboxing video.
Also: How to use Photoshop’s Generative Fill AI tool to easily transform your boring photos
Let’s start with the project. I do videos for my YouTube channel as often as I can, but my primary work product is writing. So I try to find ways to optimize my limited non-writing time for my various YouTube projects.
The video I worked on most recently was the unboxing of a multi-filament 3D printer. The Anycubic Kobra 3 Combo<!–> can print using up to four colors at once. Unboxing videos have always been popular with my viewers, so I wanted to get the video done quickly.
1. Automatic camera: Hohem iSteady v3 gimbal
The challenge with unboxing is that it’s often hard to know what to film because I never know what’s inside the box until I open it. The best way to be sure I get good film is to place a bunch of cameras all around my work area, and then just do my unboxing thing.
Also: How to download YouTube videos for free – 2 ways
The problem is, I often move around the workshop while unboxing. In previous videos, I’d often wind up with shots where I’m out of frame, or coming in and out of frame. I tried some auto-follow gimbals in the past, but they always got confused unless I was facing the gimbal directly at all times.
Not this time.
I picked up the Hohem iSteady v3 gimbal<!–> on sale at Amazon for $100. (It’s usually $129.) I watched a few reviews of this gimbal, and began to realize that gimbal AI has come a long way in the past year. This gimbal has a whole bunch of app-assisted features, but what I liked most is that it has an “AI module” that orients the gimbal properly, regardless of whether you’re running an app, or even what you’re using for a camera.
Also: My 9 must-have gadgets for creating quality YouTube videos
Even if you don’t have the app installed, the gimbal responds to a few simple hand gestures. I have yet to install the app and I’ve made a great video with amazing tracking of my movement.
–>
The setup is super easy. Charge it via USB C, then pull out the little built-in tripod legs and insert your camera. I used my old iPhone SE in the little clamp. Long pressing the power button turns it on. It will auto-calibrate, setting your phone to film in portrait mode.
To switch to landscape mode, you simply point both your thumbs to the left. Then, give it the OK sign and it will track you as you walk around.
Also: NASA has a problem, and it’s offering up to $3 million if you have a solution
This gimbal completely solved my out-of-frame problem right out of the box because the onboard machine learning in the AI module tracked me perfectly. It tracked me correctly when I moved behind a workbench and behind the big box I was unboxing. It tracked me when I walked toward the camera and when I turned around and walked away. The only time it lost track of me was when I walked completely out of the room, and all I had to do to get its attention again was hold my hand up in the OK sign.
In addition to the phone in the gimbal, I used a second iPhone pointed down from a high vantage point. I also used two iPads that were filming from their front-facing cameras so I could watch what was on-frame while filming. Yes, the front-facing cameras are a little lower in resolution, but it’s worth the trade-off to have a built-in monitor at all times.
2. Transcribing audio: MacOS Voice Memos
This video was entirely off the cuff, so I didn’t have a pre-written script I could feed into YouTube for closed captions. I also didn’t have a script to give to ChatGPT to help me with SEO and tag suggestions.
Instead, I just recorded my commentary into the DJI Mic 2<!–>, which was connected via Bluetooth to one of my iPads. After recording into all four iOS devices, I transferred the video into Final Cut Pro and used the multicam feature to match up the timing of all four camera angles. That allowed me to easily switch between angles during editing by simply typing 1, 2, 3, or 4, corresponding to whichever camera I wanted to show footage from at that point in the film.
Also: I was a Final Cut Pro diehard until DaVinci Resolve won me over with these 3 features
To get an audio file suitable for transcription, all you have to do is open the completed video file produced by Final Cut in QuickTime Player. Under the File menu, select Export As > Audio. You’re not given a choice of formats, so you’re stuck with m4a. Fortunately, this will work for our purposes.
Next, open the Voice Memos app in Sequoia. This won’t work on earlier versions of MacOS. There’s no import option in Voice Memos, but if you drag and drop your m4a audio file onto the list of recordings, you’ll briefly see a green plus sign and it will be accepted into the list of clips. Note that Voce Memos places your clip chronologically based on when it was recorded, not based on when you insert it into Voice memos.
Once it’s imported, click the very tiny gray transcribe icon.
Wait a minute and it will generate a transcript.
Let’s be clear. This is a poor transcription. It got my name wrong, it got the product names wrong, and it didn’t have any concept of paragraphs or line breaks. It doesn’t seem to use any sort of custom on-device dictionary culled from the millions of words I’ve typed on the Mac it’s running on.
It’s nothing like what would come from the commercial Rev.com–>
service, but at two bucks a minute for human transcription, this little video would have cost over $20. Using this Apple Voice Memos hack was free (although you do get what you pay for). I’m not knocking Rev.com. I use the service anytime that quality is important for client work.
Also: I improved my iPhone’s battery life by changing these 11 settings
But for my little box opening? It just wasn’t worth the cost.
To get the text out of Voice memos, hit the Edit button and copy. You’ll need to paste it into your text editor of choice and save it for later. Take a brief moment to make some edits. You’ll want to search and paste on your name and product names, so at least they’re correct in the transcript.
3. AI and YouTube Studio: ChatGPT
We’re going to use this transcript for a few things on YouTube Studio. First, once your video is uploaded, go into YouTube Studio and click the Subtitles tab. If your video has been in the system for a while, YouTube is likely to have generated automatic captions, as shown with my video.
But above the Automatic Captions entry, there’s usually a series of three dots where you can enter your own “English (video language)” transcript. Mine’s complete here, but you would click on the arrow and upload your somewhat corrected text file from earlier.
YouTube uses this to help produce closed captions, comparing what you upload with what it creates internally. I’ve also heard from other YouTubers that having a full set of uploaded captions gets you a bit more SEO juice because YouTube has more insight into what your video is about, and the algorithm is reputed to maximize exposure based on that.
Also: I’m a ChatGPT power user – and this new feature instantly made me more productive
Next up are three easy-to-write components of the video listing: the headline, the description, and the tags. As a writer, this is the easiest part of the whole project for me, but as an AI researcher, here’s another opportunity to see what we can get an LLM like ChatGPT to do for us.
I was pleasantly surprised. The AI wouldn’t directly “watch” my video, but ChatGPT Plus–>
did ingest my transcript. I gave it the prompt:
Read the following and then wait for additional instructions.
Then I gave it this prompt:
This is a transcript from a YouTube video. Please give me 10 high-impact possible YouTube video titles.
It returned the following 10 video titles:
- Unboxing the Anycubic Kobra 3 Combo: 4-Color 3D Printing Made Easy
- Multi-filament Magic: Inside the Anycubic Kobra 3 Combo
- First Look at the Anycubic Kobra 3 Combo – 4-Color 3D Printing Unboxed!
- Setting Up the Anycubic Kobra 3 Combo: Unboxing and Assembly Guide
- Anycubic Kobra 3 Combo Unboxing – Multi-filament Power in One Box
- Behind the Scenes of 3D Printer Unboxings: Kobra 3 Combo Edition
- Ultimate 3D Printing: Unboxing the Anycubic Kobra 3 Combo
- Multi-color 3D Printing on a Budget? Anycubic Kobra 3 Combo Review
- Unboxing the Future of 3D Printing: Anycubic Kobra 3 Combo
- How the Anycubic Kobra 3 Combo Changes Multi-filament 3D Printing
For some reason, ChatGPT likes capitalizing all the words in these bullet items. It’s a pet peeve of mine, but since I didn’t tell it not to, I can live with the affront to my writer sensibilities, for now. I was fairly impressed that ChatGPT picked up on the focus of my unscripted, poorly transcribed video, but it did quite well.
I did, however, like one of the titles. I settled on “Unboxing the future of 3D printing: Anycubic Kobra 3 Combo. Then I asked it to write a YouTube description. This is normally something I’d crank out, but I wanted to see how the AI performed. I gave it this prompt:
We’re using “Unboxing the future of 3D printing: Anycubic Kobra 3 Combo.” Give me a good YouTube description.
The first result was very short and not particularly compelling. So I told it:
Make it longer
As with the titles, I was fairly impressed. Remember that its only source material was that original transcript. And here’s what it produced:
Welcome to my unboxing of the Anycubic Kobra 3 Combo, a revolutionary 3D printer designed to elevate your multi-color printing projects! In this video, I’ll guide you through every step of the unboxing process, showcasing the 4-color filament switcher and how it comes packaged. From the initial setup to a look at the included components, I’ll highlight the ease of assembly and share insights on the camera setup I use for these types of videos. Whether you’re just diving into the world of 3D printing or you’re an experienced maker, this unboxing will give you an in-depth preview of what to expect from the Kobra 3 Combo.
Stay tuned for upcoming videos where I’ll take you through test prints, advanced settings, and a full review of the printer’s performance. This combo unit is a game-changer for anyone looking to streamline multi-filament prints without sacrificing quality or ease of use.
Don’t forget to like, comment, and subscribe for more content on 3D printing, smart home tech, and everything advanced geekery!
Finally, I asked it for tags. I’ll say here that ChatGPT is no substitute for a commercial tag analysis tool like TubeBuddy. But this set wasn’t too bad, although the self-referential tags with my name and my channel’s name didn’t buy us anything:
Anycubic Kobra 3, Kobra 3 Combo, 3D printing, multi-color 3D printing, 3D printer unboxing, 3D printing setup, 3D printer review, multi-filament 3D printer, Anycubic, Kobra 3 unboxing, color filament switcher, 3D printing tutorial, advanced geekery, 3D printing technology, DIY 3D printing, Kobra 3 setup, Anycubic Kobra 3 review, filament switcher, tech unboxing, 3D printer assembly, smart home tech, maker tech, David Gewirtz
What’s the bottom line, Dave?
Overall, of the three AIs used in this project, I’d give the following grades:
- Hohem iSteady v3 gimbal: A
- MacOS Voice Memos transcription: C
- ChatGPT: B+
All of them did their job well enough. You might find them all helpful unless you’re way beyond needing their help. I will use the gimbal again — that’s huge for me. If I want a transcript, I’ll probably pay Rev.com if it’s a high-leverage project. And, it’s much easier and faster for me to write my own titles and body copy for a YouTube video than it is to convince ChatGPT of what I want.
But if you’re not a professional author who spews words onto pages as regularly as my dog yaps at any noise he hears, tools like ChatGPT may well be very helpful to get you over the hurdle of producing workable supporting text for your YouTube posts.
Here’s how it all came together:
Do you use AI help for your YouTube videos? What AIs do you use? Have you tried AI transcription using Apple’s tech? How do you use ChatGPT? Let us know in the comments below.
You can follow my day-to-day project updates on social media. Be sure to subscribe to my weekly update newsletter, and follow me on Twitter/X at @DavidGewirtz, on Facebook at Facebook.com/DavidGewirtz, on Instagram at Instagram.com/DavidGewirtz, and on YouTube at YouTube.com/DavidGewirtzTV.
Source: Robotics - zdnet.com
