Everyone’s Using AI to Write Resumes—Here’s a Tool That Lets You Speak Yours | HackerNoon

I’m building a new free tool for ResumeMaker.Online, and I think this one is more robust and has more potential than any of the other free tools I’ve made so far.

That’s why I thought it would be a good idea to share the process as I go.

The idea is simple: I want to help people create short, 30-second video resumes.

Not to replace their CVs, but to stand out a bit.

Here’s he issue that I see today: everyone’s using AI and have perfectly written resumes, which is great … but it means everyone kind of blends in.

So, what if you could just add a short video? It could make your application way more memorable. You can attach it to your resume, or post it on LinkedIn.

Now, obviously, not everyone is comfortable with this:

• People aren’t video editors.
• Most webcam recordings look terrible.
• And a lot of us are shy or not great at speaking on camera.

That is why I need to make it as easy as possible for someone to hit record.

I know there are also concerns around bias, like in some countries, you’re not even supposed to add a photo to your CV… so the idea of a video might sound like a terrible idea.

But again, this isn’t a replacement for a traditional resume. It is just a complement. A way to show a bit of personality, if you want to.

Anyways… 5-day challenge. That’s the plan.

📅 DAY 1: The First Steps

Today I started with the basics. I reused some code I already had to let users upload their resume, either a PDF or a Word doc, extract the text, and pass it to ChatGPT.

You can also paste a job post to make the script more personalized, and pick the language too.

The AI then generates a short, 30-second video script based on your resume.

The prompt is designed to sound casual and real, like you’re just talking to someone. And of course, you can tweak the script however you like.

I also added the webcam preview, the option to choose the video aspect ratio (widescreen, square, or vertical), and you can already hit record and download the video.

It’s a small first step, but it’s working.

Tomorrow, I’ll tackle a key part of the recording process: the teleprompter.

Day 1, done ✅
Let’s see how far I can take it.

📅 DAY 2: The Teleprompter

I knew that just generating a script and letting users record themselves on webcam wasn’t enough.

I wanted to build a tool that actually makes it comfortable and extremely easy for people to record themselves.

First, I added a simple teleprompter with auto-scrolling text. That was the obvious move.

But then I thought… what if I could actually recognize the words you’re saying while you speak?

The teleprompter could scroll at your pace, and highlight exactly where you are.

I started by checking word by word, but it felt a bit clunky and unreliable.

Tiny pronunciation differences would throw it off, especially if you’re not speaking in your native language (like me).

If a feature like this only half-works, it’s worse than not having it at all. It needs to be reliable, otherwise, it adds an extra level of frustration: sometimes when you mess up as part of the normal process, but even worse when you were doing everything right and the teleprompter lagged, forcing you to start over.

So I scrapped the word-by-word detection and switched to sentence detection, and that made all the difference.

There’s a bit of wizardry going on under the hood, and now it feels way more stable and reliable.

The cherry on top is that the recording stops soon after it detects the last sentence. So you don’t get that awkward pause where you reach for the mouse to click stop. It just ends on its own, nice and smooth.

I also made it so that clicking anywhere or pressing any key will stop the recording too, just in case you want a bit more control.

For example, you could be holding the mouse and simply click to stop it without breaking your pose, since any click will end the recording.

One limitation: the speech recognition part only works on Android and desktop (both Windows and Mac). It doesn’t work on iOS, or at least I still can’t get it to work.

If you’re on iPhone or iPad, it’ll default to auto-scroll, which is still available for everyone.

All sounds good, right? But the truth is, none of this matters if the teleprompter still makes you look like you’re just reading off the screen.

You’re supposed to show your human side (or at least fake it elegantly) not read like a robot.

So here’s what I did: I placed the teleprompter at the top of the screen, centered right above the webcam.

That way, when you’re r**eading, it actually looks like you’re making eye contact (**especially if you step back a little from the device).

I also kept the text narrow so you’re not scanning side to side, which would make it obvious you’re reading.

And of course, you’re not supposed to stare at the words the whole time.

I’ll probably add a small tip in the UI to remind people to break the stare from time to time and keep it human and natural.

Day 2, done! ✅
Way more complicated than I thought, but huge progress.

📅 DAY 3: Customization Options

Today was all about another key aspect: allowing users to customize the look and sound without needing any editing software.

I started by letting users add their name androle or email to a video overlay template that sits on top of the video and instantly make it feel more polished.

You can preview exactly how it will look before you hit record:

I’m planning to design at least 10 of them, each with a different vibe (from clean and minimal to bold and colorful).

Some of these templates will be locked unless you upload a resume made with ResumeMaker.Online.

That’s intentional to keep everything connected and bring more users to the main paid product. It’s still extremely generous considering how much you get for free.

I also added background music options. Nothing over the top, just simple tracks to make your video feel more polished.

You can preview them, pick one, and it gets embedded directly into your final recording. I’ll probably add at least 10 tracks here as well.

Yeah, I know it still looks like crap, but this was the point where I actually start to see the potential.

Day 3, done ✅
It’s finally starting to feel like a real, powerful tool!

📅 DAY 4: Making It Look Good

Today was about one thing: making things finally look good.

Up until now, it was all a raw prototype, which is important when you’re trying to move fast and test ideas.

The early days of a project usually come with a lot of excitement and energy, but that momentum fades quickly.

That’s why I try to use those first days to focus entirely on getting the core product to actually work.

For some people (and sometimes for me too), it can be discouraging to work on a product that still looks so rough. But the truth is that you can waste a lot of time making something pretty before it’s actually useful.

Personally, I try to get to a point where the core features are solid.

Once I’m there, it becomes much easier to stick with it and actually finish. I start to see that the product is useful, and I get a little excitement boost.

The hard part is done. Now it’s just about polish. From this point on, it should feel like riding a bike downhill.

First, I designed the video overlay templates. They’re clean, subtle, and work with all kinds of styles and in all video aspect ratios.

I’m really happy with how they turned out.

I also added font pairings options so that your name and role match the visual vibe of the resume template if your resume was made at ResumeMaker.Online:

I designed the UI to keep it minimal, but with a few nice details , like the blurred video background.

I added helpful tips at the bottom of the screen, and improved the teleprompter by highlighting the sentence you’re currently on, while fading the next ones.

With the new UI, the teleprompter isn’t centered at first. But when you hit record, the settings hide automatically. That way, it looks like you’re looking at the camera while reading (just like I explained before).

I also added 10 subtle background tracks to choose from and made sure everything works well on mobile with touch interactions.

This was the longest work day in terms of hours, but also the easiest in terms of flow.

Having a solid foundation made everything else kinda fall into place.

Day 4, done ✅
Tomorrow… launch time!

📅 DAY 5: Logo, Landing Page & Launch

Last day. Let’s wrap it up!

I designed a simple logo, a variation of the one I use at ResumeMaker.Online, to keep the visual connection while giving this tool its own identity.

I also recycled parts of the homepage layout and adapted the design for this new product. The idea is to let it live as a standalone tool.

I created some visuals, and built versions in multiple languages. I also added auto-translate support directly in the tool.

Wrote a couple of quick blog posts related to video resumes but aside from that, it’s just one page , clean copy, strong CTA, no fluff.

So here it is. The tool is ready.

The final flow is super simple:

• Upload your resume

• (Optional) add a job post

• Get your script

• Select your template

• Hit record

• Read with the teleprompter

• Download your video resume

No signups. No logins. No editing required. All in the browser.

I started this knowing it would feel a bit more robust than my usual free tools… and now it really feels like it could be a product of its own.

If you’re job hunting, or just want to try something different to stand out, it’s live: 👉 resumemaker.video

Also, the Product Hunt launch is live today (May 2nd). I would love your support: 👉 https://www.producthunt.com/posts/resumemaker-video

**Day 5, done ✅
**

Now let’s see if people use it. Would love to hear your feedback!

Follow me on X @Fer_Momento to see how things go after launch and to check out my other products: