Open Letterly (opens in a new tab)

Can Letterly separate speakers?

Yes. Letterly can split a transcript by who said what, so an interview or a meeting reads as a dialogue instead of one block of text.

Turn it on

During a recording — tap the Multi-speaker button on the recording screen. The transcript is split by speaker as soon as it is ready.

After a recording — open the note, tap the ⋯ menu, and choose Add speaker roles. Letterly processes the audio again and splits the transcript by speaker.

To split a note that was recorded without Multi-speaker, open the note, tap ⋯, and choose Add speaker roles.

What the transcript looks like

Each turn in the conversation gets its own label — Speaker 1, Speaker 2, and so on. Letterly separates the voices, but it does not know who the people are, so the labels stay generic.

Get better separation

  • Place the device where it can hear everyone, not next to one person.
  • Ask people not to talk over each other — overlapping speech is the hardest case to split.
  • Avoid heavy background noise: cafés, air conditioning, speakerphone echo.

Voices that sound very similar, or moments when several people speak at once, may end up under the same label.

Was this helpful?