Skip to main content
Product Updates5 min read

Just Talk to Your Tutor: Voice Mode Arrives in Chat

iTutor's tutor now talks. Voice mode lives inside your chat: it greets you, remembers the conversation and the materials you uploaded, answers sentence by sentence so you are never waiting in silence, and switches between twelve languages mid-conversation.

iTutor TeamJuly 14, 2026

Some questions are easier to say than to type. "Wait, go back, why does step six need oxygen?" is a sentence, not a search query. Starting today, you can just say it. Voice mode has arrived inside iTutor chat: tap the Voice button, start talking, and your tutor talks back.

This is not a separate voice page bolted onto the side of the app. It lives inside the same chat you already use, part of the same July update that brought the new Study Plan. Your conversation stays on screen, every spoken exchange lands in the thread as text, and when you end the session you can scroll back and reread everything you covered.

Your chat, out loud

Tap Voice and the message box transforms into the voice dock: your tutor on one side, you on the other, a live waveform between you showing whose turn it is. While the tutor speaks, its words light up one by one in a floating caption, so you can read along with what you hear.

ITUTOR Glycolysis splits one glucose molecule into two pyruvate ITUTOR YOU SPEAKING MUTE PAUSE END 02:41 ENGLISH THE CHAT THREAD STAYS OPEN ABOVE · EVERY TURN IS SAVED AS TEXT
The composer morphs into the voice dock: two mascots on a footlit waveform floor, the tutor's words hanging in the air above them. The floor glows blue while your tutor speaks and mint when the turn is yours.

The two avatars are not decoration, they are the turn signal. When the tutor is speaking, its side glows and the waveform dances to its voice. When it finishes, the light crosses to your side and the mic is yours. Mute, pause, and end are one tap away, and the whole thing works on your phone too.

No awkward silences

The worst part of most voice assistants is the wait: you finish your question, and then you stare at a spinner while the entire answer gets prepared somewhere. Your iTutor tutor speaks the way people do, starting as soon as the first sentence is ready and composing the rest while you listen.

YOU TUTOR you ask your turn sentence 1 sentence 2 sentence 3 speech starts here full answer done YOUR MIC RESTS WHILE THE TUTOR SPEAKS, THEN HANDS BACK TIME
Answers stream sentence by sentence. You hear the beginning of the answer while the rest is still being composed.

The captions follow the same rhythm. Each sentence appears as its audio starts, and fills in word by word as it is spoken. If you are somewhere loud, or you just process text better than sound, you never lose the thread.

It already knows where you left off

Here is what makes this a tutor rather than a talking search box: voice mode is the same brain as your chat. It is grounded in the materials you uploaded, and it continues the exact conversation on your screen. Ask it about the thing you typed yesterday, and it knows. Start a session, and it greets you first.

WHAT THE TUTOR ALREADY HAS bio-notes-ch7.pdf Lecture slides · week 9 YESTERDAY IN THIS CHAT "I still do not get step 6..." THE FIRST THING IT SAYS "Welcome back, Sara. Last time we stopped at step 6 of glycolysis, in your chapter 7 notes. Want to pick it up?" Same conversation, same materials, same tutor. Voice is just a faster way to talk to it.
Voice mode is grounded in your uploads and your conversation history, so the first thing it says is already about you.

And because every voice turn is saved into the thread as text, nothing evaporates when you hang up. The explanation you got while pacing around your room is right there in chat when you sit down to write it up.

Switch languages mid-conversation

Studying in one language and thinking in another? Tap the language chip on the dock and keep talking. The tutor answers in the new language from the next turn, across all twelve languages iTutor supports.

English العربية Français Español Deutsch Português Italiano Nederlands Türkçe Indonesia Melayu اردو TAP THE LANGUAGE CHIP IN THE DOCK · THE TUTOR SWITCHES ON THE NEXT TURN
Twelve languages, including full right-to-left Arabic and Urdu, one tap away during a session.

Voice mode is available on plans that include voice tutoring. Open a subject in chat, and if your plan has voice, you will see the Voice button next to the message box.

More from the July update