What is Speaker labels?
The names or tags in a transcript that show who said each line. The technical name is speaker diarization.
Speaker labels show who said what in a transcript, like “Priya:” or “Speaker 2:”. Working out where one voice stops and another starts is called speaker diarization. Without it, a transcript is one long wall of words.
How it’s done
- By voice. The software groups similar-sounding stretches of audio. It’s harder with crosstalk, similar voices or one shared microphone.
- By channel. If your microphone and your computer’s sound are recorded separately, everything from your mic is you and everything from the computer is everyone else. Simple and reliable.
- By name. Some tools use a calendar invite or a meeting bot’s view of the call to put names on voices.
In Fetch
Fetch records your microphone as Me and your computer’s sound as Them, so you can always tell your lines apart. It also learns voices over time: tell it once who a speaker is, and it fixes their lines and recognizes them next time, on your computer. See Record your first meeting and speech-to-text models.
Questions people ask
Why does my transcript say Speaker 1 and Speaker 2?
The software can tell voices apart but doesn't know their names. Some tools let you name a speaker once and remember them next time.
Still scratching your head?
Send us a note and a real person will get back to you.