Skip to main content
Behind every Summary sits the transcript: the conversation word for word, labeled by speaker, timestamped, with the audio a tap away. The Summary is for living with, and the transcript is for the moments you need exactly what was said. Open it from the Summary ▾ menu at the top of a note.
A note on its transcript view, with speaker turns, timestamps, and playback

Who can see it

The transcript is yours. In a team space, other members see a note’s Summary, not its transcript. It only leaves your hands if you share the note by link and turn the transcript on. See Who sees what.

Reading a transcript

Each turn shows who spoke and when. Gobi labels each voice Speaker 1, Speaker 2, and so on, until you name them by adding attendees. Name a speaker once, and all of their turns follow. Timestamps run from the start of the voice note, so a moment in the transcript is a moment you can jump to.

Playback

The audio is kept with the note. Tap play at the bottom of the note, or tap a moment in the transcript to hear it. Skip back for the sentence you want to hear twice. Reading tells you what was said, and hearing it again carries the tone.

When to reach for it

Honestly, less often than you’d expect. The Summary carries the meaning, and Ask anything answers most “what did they say” questions. The transcript earns its keep in the exact moments:
  • The precise quote. When “roughly what she said” isn’t enough: a number, a commitment, the wording of an offer.
  • The disputed moment. When memories differ, the transcript settles it quietly.
  • The detail the Summary judged small. Summaries choose what matters, and the transcript keeps what happened. Sometimes a passing remark turns out to matter later, and it’s still here.

Honest edges

Real conversations are messy, and transcripts inherit that. Noisy rooms, crosstalk, and people who never say their names make speaker labels less certain, so a turn may occasionally land on the wrong speaker. The fixes are ordinary: correct the attendees, and when it matters, tap play. The audio is the ground truth the text stands on.