Why does "voice as in input" matter?
Spoken interaction reduces friction in situations where touch or typing is inefficient. This is a type of no interface system, which during multi-tasking can be used for delegating low-risk or reversible tasks. It requires low cognition, and enables multi-tasking PRO Max.

This was the up until now..

Nowadays, we're seeing voice being added to our day-to-day applications, not just standalone devices like Echo dot.

Why now? Because the technology is finally here. Our fear of getting "uhuh, i didn't quite that" is finally addressed and interpretation has gotten much more advanced.

Let's dive into some examples.

Examples

Perplexity has a voice input mode with a fancyyy visual feedback - reminiscent of the audio visualizer days.

Alexa listens for a wake phrase, "Hey Alexa", and initiates actions like playing music, checking the weather, or controlling your home devices. Users speak their commands, and while Alexa interprets it, the device shows a vibrant blue ring as feedback. The interaction is hands-free and optimized for ambient environments like kitchens or living rooms.

Siri is activated via long press or voice, "Hey Siri". Users can ask general questions like "What’s the weather this week?" or request context-aware actions like "Add hiking to my calendar for 7 AM". The assistant integrates with apps, pulling relevant information and executing tasks while preserving continuity across follow-ups.

Arc enables users to speak during a phone call and have the assistant surface web results live. The AI listens mid-call, processes the query, and presents a summary or options without leaving the interface. This is an embedded voice interaction that functions within a live context, augmenting search with real-time voice input.

AI UX checklist

When designing a voice AI UX, the interface is minimal but needs to consider multiple states in terms of interaction and feedback.

• Ensure reliable wake-word detection or manual trigger

• Show a "connected state" to confirm it's ready to listen.

• Show a listening state to keep the user in the loop with the system's

• Create a response state to ensure the user knows the system understood

• When the user stops talking, what's that moment like?

• Maintain context across follow-up questions or commands

• Show a state when the system is done talking

• Enable fallback when speech is unclear or interrupted

• Design voice responses to be brief and relevant

• The whole interaction should be interruptible, with priority given to the user

The aim when working on a voice interaction is to get into code and a live experience as soon as possible to understand all the interaction states and iron out the nuances.

As a designer, there's not much to the interface, maybe a button and a visualizer, but a lot of designing is needed for the part of the interaction that's invisible.

Voice interfaces are soon going to evolve from simple, reactive tools into proactive, conversational systems. With advancements in memory and context modeling, future assistants will anticipate user needs and suggest helpful actions without being prompted.

Imagine this: your room is connected to a smart voice assistant that says,
"It’s getting quite warm; should I turn on the AC? Also, it’s late; would you like me to dim the lights?"