Feature · Speaker identification
Knows who said what.
Recorder doesn’t just hear words — it identifies voices. Every line of the transcript names its speaker, so conversations stay crystal clear long after everyone’s left the room.
- Speaker A So where did we land on the launch date?
- Speaker B Marketing wants the 14th, but engineering needs one more week.
- Speaker A Then let’s lock the 21st and tell the team today.
- Speaker B Done — I’ll send the note this afternoon.
Why speaker identification changes everything
A transcript without speakers is a wall of text. You can read it, but you can’t use it: who agreed to the deadline? Which quote belongs to the interviewee? Who raised the objection? Record and Transcribe answers those questions on every memo, so the transcript arrives already structured as a conversation rather than a monologue.
New to the idea? Speaker diarization explains the technique itself. For the practical side, how to transcribe audio with multiple speakers covers microphone placement and what to expect from a real conversation, and how to label speakers in a transcript covers the naming conventions and how to fix labels that came back wrong.
Where it earns its keep
- Interviews — quotes stay attributable. You’ll never wonder which answer came from which participant.
- Meetings — decisions and owners are visible in the text. Pair it with Pro summaries and the action items name their people.
- Lectures & seminars — the professor’s thread stays separate from questions in the room.
No setup, no profiles
There is nothing to configure. The separation happens from the audio itself as part of automatic transcription, whether you recorded on iPhone or from your Apple Watch. Record the conversation; read it back as one.
Frequently asked questions
Does Record and Transcribe identify speakers automatically?
Yes. Every recording is separated by voice as part of transcription, so each line of the transcript arrives already attributed to whoever said it. There is nothing to switch on, no voice profiles to train, and nothing to tag by hand.
Do I need to set up voice profiles first?
No. The engine separates voices from the recording itself. Start recording a conversation and the transcript comes back already labelled by speaker.
How many speakers can it handle?
It is designed for real-world conversations — meetings, interviews, calls with several participants. Distinct voices and reasonable audio quality give the cleanest separation.
Does Apple’s Voice Memos app label speakers?
Apple’s built-in Voice Memos offers transcripts on recent iPhones, but the transcript is one continuous block of text without speaker labels. Speaker-labelled transcripts are the core of Record and Transcribe.
Every voice, on the record.
Free to start — 3 transcriptions included, no card needed. Apple Watch app comes with it.