Features

Vizir features

Vizir is an AI interview assistant that hears the conversation on two channels, transcribes speech in real time, and on a hotkey serves up a hint or a ready-made solution — on an overlay that stays hidden from screen recording and browser screen sharing. Below is exactly what the app can do, and how it looks.

The panel

Four windows — and what you can do from each

The panel switches from the keyboard. Each window handles its own job — from the live dialogue to a line-by-line code walkthrough. Here's how it looks and what it does.

Tab 1 · Transcript

A live dialogue on two channels

Hears both the interviewer (audio from Zoom, Meet, or the browser) and you through the mic — as two tracks, natively, with no virtual audio drivers. Lines are split into "Interviewer / You", by time, in Russian and English. Speaker echo is filtered out.

What you can do from here
  • ⌥↩generate a hint or solution from the whole conversation
  • ⌥1⌥4switch to any tab
  • ⌥↑⌥↓scroll the transcript
Tab 2 · Hint

What to say out loud right now

A short answer to the interviewer's last question, in the context of the conversation. Not paragraphs of theory — what people actually say out loud, in a couple of seconds.

What you can do from here
  • ⌥Eexplain a selection — the breakdown goes to "Explanation"
  • ⌥Vcopy the hint
  • ⌥↑⌥↓move through the answer line by line
Tab 3 · Solution

Ready-made code with a walkthrough and complexity

The problem came as text or an image: screenshot ⌥C or the selection ⌥⇧C, then ⌥↩. Returns code with line numbers, a walkthrough of the approach, and complexity analysis. A vision model reads the image — you can attach several frames.

What you can do from here
  • ⌥C⌥⇧Cscreenshot the prompt · grab selected text
  • ⌥↑⌥↓move through the lines — read it out without losing your place
  • ⌥E⌥Vexplain the selected lines · copy
Tab 4 · Explanation

A breakdown of what you've already said

When they ask you to clarify your own answer: select a passage in "Hint" or "Solution", press ⌥E — and a breakdown of exactly that part appears here, continuing your train of thought instead of starting over.

What you can do from here
  • ⌥Efrom "Hint" or "Solution" — fill this tab
  • ⌥Vcopy the breakdown
One shared context

All four windows remember the same thing

The problem statement, the last solution it produced, and the tail of the conversation are shared across every tab. So "why this way?" and "what's the complexity?" are answered against what it already produced, not from scratch in the abstract. Vizir only sees your code if you show it with a screenshot (⌥C) or a selection (⌥⇧C).

Controls

Everything from the keyboard

No mouse needed. Generating, tabs, screenshots, moving and resizing the window — it's all on hotkeys, so your hands never leave the keyboard during the interview.

⌥↩

Generate a hint or a solution from the current context.

⌥1 ⌥2 ⌥3 ⌥4

Switch tabs: Transcript, Hint, Solution, Explanation.

⌥C

Task snapshot — capture the problem statement or a diagram for the vision model (you can stack several).

⌥⇧C

Grab the selected text — the problem statement or a code snippet, for example.

⌥\

Hide or show the overlay with a single key.

⌥W ⌥A ⌥S ⌥D

Move the overlay window up, left, down and right.

⌥+ ⌥−

Make the window bigger or smaller.

⌥↑ ⌥↓ ⌥← ⌥→

Navigate line by line through the answer and scroll the content of the active tab.

Try it on your next interview

Download Vizir, sign up and get 7 days free. No card required.