Live transcription

Transcription turns the interviewer's audio into text you can read while they are still talking.

A rolling caption of the live audio.

How it works

Once a session starts, the transcription panel shows a rolling caption of what is being said. It is genuinely useful in two situations: when you miss a word, and when the question is long enough that by the end you have forgotten the start.

Audio sources

ModeWhat it captures
SystemAudio playing on your machine — the interviewer's voice. The default.
MicrophoneYour own input.
System + MicrophoneBoth, as separate tracks, so the two sides stay distinguishable.

On macOS, system audio is captured through ScreenCaptureKit. On Windows it uses native output loopback. Change the source from the audio device menu in the interview control bar.

Sending a question to the assistant

  • ⌘⌥. — append the latest transcript chunk to your draft without sending it.
  • ⌘⌥↵ — send the draft, plus any attached screenshots, to the assistant.
  • ⌘⌥, — clear the draft text without removing attached screenshots.

The two-step append-then-send exists so you can stack several sentences — or a transcript line plus a screenshot — into one question.

If detection feels off

Interviewers speak at very different paces. If the app is cutting questions early or lumping two together, adjust the pause interval in settings — a longer interval suits someone who thinks out loud, a shorter one suits rapid back-and-forth.

Test audio before the interview
Transcription depends on permissions and on the right device being selected. Run a self-meeting and confirm the caption is moving before you rely on it.