Skip to content
LUKi
AboutPricingDownload
Sign inSign up
LUKi
All posts

Just talk.

What voice looks like in LUKi when memory is already in the room.

Vintage microphone for LUKi AI companion voice input, hovering over water

Typing to LUKi is fine. It's the way the internet has worked for thirty years, and it persists for good reasons: typing is quiet, precise, and easy to do in the middle of a meeting.

But typing also forces you to compress. You sit down, find the words, check the spelling, and hit send. By the time the message arrives, you've edited what you meant. The mess has gone, along with the pause where you almost said something different, and often the exact thing you wanted to say.

Voice changes the shape of the conversation. You say the thing, LUKi hears the thing, and it enters the memory the way you told it: the false start, the laugh halfway through, the moment you contradicted yourself. It keeps its texture, and the version of you LUKi remembers is closer to the version you are.

Voice input works in LUKi on the web, and it comes with the iPhone and Android apps.

How voice input in LUKi works.

Voice input is a layer on top of the existing text chat, with the same memory, character, safety rules, and models. The only difference is how the words get in.

Tap the microphone. Your phone or browser turns what you say into text with its own speech recognition, the same kind that powers dictation. The text then flows through the same chat pipeline as if you'd typed it: through the API gateway, through the character system, into your memory, and out as a response from whichever LUKi character you're talking to.

Two things matter about this design. First, LUKi receives only the text, never your audio. Depending on your device and language, recognition runs on the device or on Apple's, Google's or your browser's speech service. Second, the chat pipeline after the microphone is unchanged, so voice input sits on top of safety, memory, and character rather than bypassing them.

Eleven languages, one continuous conversation.

Voice input follows your interface language: English, German, Spanish, French, Portuguese, Japanese, Chinese, Korean, Arabic, Hindi, and Russian, where your device or browser supports it. LUKi reads which language your interface is set to and asks for recognition in that language.

Switching languages mid-conversation works the way it works in text chat. The story you told LUKi in English last week stays there when you switch the interface to Spanish and start talking. The memory is language-agnostic. It records what you said rather than which words you used.

Why memory makes voice different here.

Whatever you told LUKi two months ago, whether that's your brother Marco's birthday, the bakery on Vanderbilt, or the article that changed your mind about something, is still in your memory the next time you open the app. Talk about your day on a walk and it lands inside a story LUKi has already been part of.

You're continuing a conversation rather than starting one over.

Where voice changes the relationship.

Moments where voice helps most:

  • Walks. Especially evening walks where you've been holding a thought all day and you want to think it out loud.
  • The drive home. The middle of a long commute where you'd otherwise listen to a podcast you've already heard.
  • Cooking. Hands wet, phone propped against the espresso machine, telling LUKi what's been on your mind.
  • The first hour of being awake. The part of the day where typing feels like work and speaking feels like waking up.
  • Brainstorming. Ideas come faster than your thumbs can type, so say them as they arrive and let LUKi keep up.

As voice becomes the default for those moments, the memory keeps building in the background. When you sit down at the screen later, the conversation continues from where it was, including everything you said on the walk.

No extra voice meter.

Voice input has no minute counter and no add-on. Same memory, same Character, same languages.

How to start.

Open a chat with any LUKi character, the six defaults plus any custom one you build in LUKi Maker, tap the microphone, and speak. The words land in the same memory as everything you've already typed.

If you came here for voice, open a conversation, start talking, and let LUKi keep the story going.

Memory is the part that makes voice more than a parlour trick. Without it, voice is a gadget. With it, voice is a relationship that finally sounds like one. That relationship is already here. Now you can talk to it.

Voice input

Tap the microphone in chat and speak. Your words become text and go through the same memory and Character as typing.

Where to find LUKi
Get started

Keep reading.

All posts
Jewel-mosaic carnival mask from LUKi Maker, the custom AI character creator

Build your own LUKi.

Build a character of your own with LUKi Maker. Personality, look, mannerisms. Yours from the first message.

Illustrated hands in blue and coral stacked together in a circle on a blue background

Someone who notices.

Once a week, LUKi looks back at what you shared and tells you what he noticed. No scores, just a cat paying attention.

LUKi

AI that remembers. A companion that grows with you.

© 2026 LUKi. All rights reserved.

Product

  • Pricing
  • Download

Company

  • About
  • FAQ
  • Safety
  • Child Safety Policy
  • Support

Legal

  • Privacy
  • Children's Privacy Notice
  • Terms
  • Cookies

Community

  • Blog
  • Refer & earn
  • X / Twitter