A meeting transcript is only useful if you can tell who said what. Speaker identification in a transcript is what makes that possible: ThinkScribe separates voices automatically, labels them Speaker 1, Speaker 2 and so on, and, once you name a voice, remembers it. The next recording with the same person comes out already labeled. This guide shows how to name, enroll, correct and merge speakers on Mac and iPhone.
How speaker identification works in a transcript
Every recording with more than one voice goes through two steps on your device after transcription (you see "Identifying speakers..."): the audio is split into turns by voice, and each turn is compared with the voices you have already named. A known voice gets its name; an unknown one gets a generic label. The number of speakers is detected automatically, and your recordings and voices are never sent to us.
The settings live under Settings > Speaker Identification on iPhone, and under Settings > AI & Models on Mac. On a Mac, and on iPhones and iPads with 8 GB of memory, ThinkScribe also downloads a better speaker model once, which helps with harder recordings. There is nothing to set: until it is ready, the standard model is used.
What a voice fingerprint actually is
The word fingerprint is doing real work here, and it explains most of the results you will see.
Any system that recognizes voices turns a stretch of speech into a list of numbers, usually a few hundred of them. The list describes the voice rather than the words: pitch, timbre, the resonance of the vocal tract, speaking rhythm. Two samples of the same person saying entirely different sentences sit close together; two different people sit further apart. The numbers mean nothing to a human reader; they describe a voice, not what was said.
Naming a voice stores that list under a name. In a later recording, each stretch of speech becomes a new list and is compared with the stored ones, giving a similarity score. Clear the threshold and the name is applied; fall short and the voice is treated as someone new.
That threshold is a trade-off no setting escapes. Loose, and a colleague with a similar voice inherits your name. Tight, and you become a new speaker on the morning you have a cold. This is why correcting a label matters more than it looks: the correction is the only information the system gets about where the line was wrong. How speaker diarization and speaker recognition work covers the whole pipeline.
How to name a speaker in a transcript
The easiest way to teach ThinkScribe is to name people as you read.
- Open a transcript that shows Speaker 1, Speaker 2 and so on.
- Tap a line to hear who is talking, so you are sure which label is which.
- On iPhone or iPad, touch and hold the speaker badge and choose Rename Speaker.... On Mac, use Rename Speaker... on the speaker badge.
- Type the person's name, or pick them from Known Speakers if you have named them before.
- Confirm. Every line with that label is updated, and the voice is saved.
From now on, saved voices are recognized automatically across new recordings. When ThinkScribe is not quite sure, it shows Possible matches so you can Confirm or Reject the name.
Enroll someone on purpose
If you want a colleague or a client recognized before their first meeting, enroll them with a clean sample.
- On iPhone, open Settings > Speaker Identification > Manage Known Speakers. On Mac, open Settings > AI & Models and click Manage... next to Known Speakers.
- Choose Add Speaker.
- Enter the name, then either record them speaking on their own for 20 to 30 seconds, or import a recording where only they are talking. A voice message they sent you works well.
- Save the new speaker.
Longer, cleaner samples produce better recognition. A sample with two voices or with music in the background will confuse the profile.
Why one person is sometimes split into two speakers
This is the most common complaint about any speaker-labeling system, and the causes are nearly always in the audio rather than the software.
- Short turns. A one-word answer is less than half a second of speech, not enough for a stable fingerprint. Short interjections attach themselves to whoever was speaking around them, or become a speaker of their own.
- Crosstalk. When two people talk at once, the segment holds both voices and its fingerprint lands between them. Nobody matches it well, so it becomes someone new.
- A changed voice. A cold, a hoarse morning, shouting over noise or plain tiredness shifts the numbers enough to miss the threshold.
- A different microphone. A headset, a laptop microphone and a phone on the table capture the same voice very differently, so someone who joins the second half of a meeting on another device often arrives as a new speaker.
- Distance and room. Moving away from the microphone mixes more of the room into the voice, so a person who starts at the table and ends up pacing can split in two.
- Phone and call audio. Calls are compressed, noise-suppressed and narrow in bandwidth, which strips out detail the fingerprint relies on.
The reverse failure, two people sharing one label, has the same roots: similar voices, a distant microphone, or too little speech from the quieter person.
What to do when a label is wrong
Fix labels while you still remember the meeting, and start with the earliest confident example of a voice rather than one in the middle of a crosstalk.
- One person, two labels in a transcript: use Rename Speaker... on the second label and pick the same person from Known Speakers.
- One person, two saved voices: open Known Speakers (Manage Known Speakers on iPhone, Manage... on Mac) and use Merge to combine them.
- Two people, one label: enroll the second person with a clean sample using Add Speaker, so future recordings have two distinct voices to match against.
- Wrong name on a known voice: rename the badge to the right person. When ThinkScribe offers Possible matches, Reject the wrong ones so it learns where the line is.
- A voice you no longer want saved: Delete it from Known Speakers.
Interviews, panels, lectures and calls
The recording situation decides how much work is left for you afterwards, and the four common ones behave very differently.
An interview is the easy case: two voices taking turns, close to the microphone. Enroll yourself, let the guest be labeled automatically, and rename them once afterwards. Consistent labels matter most for interview transcripts in research, where the attribution ends up in the analysis.
A panel is the hard case: five or six voices, frequent interruptions, often one microphone for the room. Expect more speakers than there are people, expect the quietest participant to be merged into someone else, and plan a pass of merging and renaming. A round of introductions at the start helps a great deal, because it gives every voice a clean, uninterrupted sample early on.
A lecture sits between the two. One voice dominates and is recognized easily, and questions from the room arrive as separate speakers, which makes them easy to find even when the questioners are never named.
A phone or video call is limited by its audio rather than by the number of people. Compression and noise suppression remove detail, and some call apps mix every remote participant into one channel, which no software can undo. For a one-to-one call recorded with both Microphone and System audio on the Mac, your side and the call side come from distinct sources, which gives separation a head start.
For in-person meetings, put the phone flat in the middle of the table so every voice comes through, and interview transcription for journalists shows how named speakers make quotes quick to check.
Speaker labels while you record
On the Mac, and on iPhones with 8 GB of memory, you can turn on live speaker labels so names appear as you record. They are off by default. On every device, the full transcript and its speaker labels are made after you stop.
Known speakers sync between devices
If Sync Across Devices is on, speaker profiles travel with your transcripts through your own iCloud account, provided by Apple. Name a client on your iPhone after a coffee meeting, and the recording of tomorrow's video call on your Mac is labeled with their name. The sync guide explains what is included.
Frequently asked questions
Does speaker identification work offline?
Yes. Speaker labels are made on your iPhone, iPad or Mac and work offline. Saved voices are kept in ThinkScribe on your device, and in your own iCloud account only if you turn on sync. They are never sent to us.
How many speakers can it tell apart?
ThinkScribe detects the number of speakers automatically, so you do not have to tell it in advance. Recognition is most reliable with a handful of regular voices close to the microphone. In large panels, rare or distant voices may stay generic or merge into someone else until you rename them.
How do I remove a saved voice?
Open Known Speakers (Settings > Speaker Identification > Manage Known Speakers on iPhone, Settings > AI & Models > Known Speakers > Manage... on Mac) and delete the voice. The same list lets you rename and merge voices.
Are voice profiles recordings?
A voice profile is a compact numerical description of a voice that ThinkScribe compares against new recordings, as explained above. It is what lets a saved voice be recognized again, and it is never sent to us.
