Stack For Designers: Voice To Vision

In partnership with

Global payroll complexity? Here’s the playbook.

Managing global payroll shouldn’t mean juggling vendors and compliance risks. Deel, recognized in the Gartner® Market Guide for Multicountry Payroll Solutions, helps finance teams automate payments, standardize reporting, and stay compliant in 100+ countries. Get key insights from industry experts to future-proof your payroll strategy.

Download the Report

Hey, it’s Kushagra. Welcome to this week’s AtlasMoth drop.

Most apps talk smart.
But now? They talk, hear, see, and vibe.

This week, we’re digging into why multimodal AI hits different from voice to vision, from chill flows to fast replies.
It’s not just cool tech. It’s a new way to build.
One where users don’t tap through menus, they talk, snap, move, and go.

We’re talking tools like Figma, Play, SwiftUI, and the real deal of designing AI that feels right.
Not stiff. Not forced. Just natural.

Let’s break down how the next-gen builders are riding the multimodal wave and what smart UX can learn from it.

💬 Building for people beyond borders? Book a call to explore more

Turn Creative Briefs into Revenue

With Neurons AI, agencies can fast-track everything from creative development to client sign-off.

Neurons AI indicates how campaign assets will perform—before launch—so you can deliver smarter, faster, and with confidence.

Using Neurons AI, Teads helped their client improve brand awareness by 64% and ad recall by 29%.

Get Your Neurons Demo

AI isn’t just text on a screen now. It talks, it hears, it sees, it feels.

That’s what folks call a multimodal word, but a chill idea.

And one designer is deep in it, building cool stuff and learning tons on the way.

What Even Is Multimodal?

Multimodal means apps that let folks talk in more than one way.
Text? Sure.
Voice? Yep.
Touch, moves, pics, sound? All fair game.

Think of tools like ChatGPT. One can type a prompt or just speak it. Snap a pic. Ask a “what’s this?” and boom, context, vibe, reply. It's not stuck in one mode. It gets how real folks want to talk.

That’s the whole point: apps that let users choose how they talk. No force, no stress. Just what feels right in the moment.

Seeking impartial news? Meet 1440.

Every day, 3.5 million readers turn to 1440 for their factual news. We sift through 100+ sources to bring you a complete summary of politics, global events, business, and culture, all in a brief 5-minute email. Enjoy an impartial news experience.

Join for free today!

Why It Matters Right Now

AI isn’t niche anymore. It’s mainstream.
By 2025, over 378 million people are set to use AI, 65 million of them new just that year.

That spike? It’s a sign.
Apps need to vibe with real life. They can’t just be smart, they have to feel smooth, clear, and chill to use. If an app still needs clicks for every step, it’s behind the curve.

One Builder’s Take

Right now, one designer is building an AI mentor app for iOS.

The goal? Let folks talk to AI through voice and chat.

Real talk though: today’s design tools? Kinda mid for this.

So here’s the stack:

• Figma to shape the vibe

• Play to bring it to life (yep, even AI bits)

• SwiftUI to ship it for real

• Bolt to test on all kinds of phones

It’s not just the look. It’s the feel.
Does it flow? Does it make sense? Can users just speak and get help, fast and stress-free?

That’s the kind of app they’re after.

What This Means for Other Designers

Don’t just add AI for hype. That’s not it.
Instead, ask:

• How do folks use the app now?

• Would voice or pics help them do more?

• Are there spots where text feels slow or stiff?

If the answer’s “yeah,” then it’s time to test.
Mock it. Try it. Let real folks vibe with it.
Use real tools. Keep it chill. Let the AI help, not just show off.

The Big Idea

Smart apps are cool. But the best ones?
They care. They make life easy.
They flex in low-key ways that just work.

Multimodal is the next wave.
And the best builders? They’re riding it.