Speaker recognition in MacWhisper: how to assign, rename and merge speakers

By · Published

MacWhisper recognizes speakers automatically when you transcribe with a model that supports it: the local models that run on its WhisperKit engine, marked with a green Speaker Recognition badge, or the cloud providers ElevenLabs and Deepgram. The transcript is grouped as Speaker 1, Speaker 2 and so on, and you rename, merge or reassign them in the sidebar. It arrived in MacWhisper 12, and MacWhisper's pricing page lists speaker recognition under Pro.

I built YapToText, a different Mac app for dictation and file transcription, so read what I say about MacWhisper with that in mind. Every fact about MacWhisper here comes from its own help center, read on October 10, 2026.

Download YapToText on the Mac App StoreThis app is completely free. You don't have to make an account. There are no subscriptions, no difficult downloads, and nothing is locked. Made for Apple silicon Macs. Source on GitHub.

This guide in other languages: العربية, Čeština, Dansk, Deutsch, Ελληνικά, Español, Suomi, Français, עברית, हिन्दी, Magyar, Bahasa Indonesia, Italiano, 日本語, 한국어, Norsk, Nederlands, Polski, Português, Română, Русский, Slovenčina, Svenska, ไทย, Türkçe, Українська, Tiếng Việt, 简体中文, 繁體中文

Turn it on

  1. Choose a model with the green Speaker Recognition badge. Those are the local models on the WhisperKit engine.
  2. Transcribe the file as usual.
  3. When it finishes, the transcript is grouped by speaker, with default names.

If you do not see speakers, the model is the usual reason. The MacWhisper troubleshooting page has the checks.

Rename, merge and reassign

  • Rename a speaker. Click the name in the sidebar, type the new one, and press Return.
  • Merge two speakers. When one person was split in two, right-click the speaker name in the transcript or the sidebar and choose Merge Speaker To.
  • Reuse names. As you type a name, suggestions from the speakers saved in settings appear. Command Return picks one.
  • Change a color. Click the color palette icon in the sidebar.
  • Reassign a segment. Hover over the segment and press that speaker's number key: 1, 2, 3 and so on.

Where it does not apply

  • Dictation. MacWhisper's dictation assumes one speaker, so there is no speaker recognition there.
  • Transcribe Podcast. Each imported track is meant to be one speaker already.
  • Models without the badge. Other engines do not group by speaker.

For meetings, MacWhisper can record Zoom, Teams, Webex and other meeting apps and identify speakers afterwards. Its help center marks Automatic Meeting Recording as a beta feature and recommends manual recording for critical meetings.

Getting cleaner speaker splits

Speaker recognition groups voices by how they sound, so it does best when people do not talk over each other and each voice is clearly recorded. Expect to merge a speaker or fix a few segments on most real recordings. The number keys make that quick: hover, press, move on.

What YapToText does instead

YapToText does not identify speakers. It transcribes an audio or video file into one continuous transcript, and it has no timestamps or subtitle export either. If you need a transcript labeled by who spoke, MacWhisper is the better tool for that job.

YapToText is built for the other half of the work: dictating into any app with one key, with cleanup that runs on the Mac, free and with no account. The MacWhisper alternative page compares the two, and the interview transcription guide covers recording and transcribing a two-person conversation.

Download YapToText on the Mac App StoreThis app is completely free. You don't have to make an account. There are no subscriptions, no difficult downloads, and nothing is locked. Made for Apple silicon Macs. Source on GitHub.

The short version

  • Needs. A WhisperKit model with the green badge, or ElevenLabs or Deepgram.
  • Rename. Click the name in the sidebar.
  • Merge. Right-click, Merge Speaker To.
  • Reassign. Hover a segment and press the speaker's number.
  • Not for. Dictation or Transcribe Podcast.

If MacWhisper changes how this works, open an issue on GitHub. Every one gets read.

Download YapToText on the Mac App StoreThis app is completely free. You don't have to make an account. There are no subscriptions, no difficult downloads, and nothing is locked. Made for Apple silicon Macs. Source on GitHub.

About the author. Ryleigh Newman is a developer whose hands make typing difficult and who dictates every day with YapToText, the app this site describes. Facts about other apps come from their own sites, with the date they were read. More about the project.

Sources

Questions

Does MacWhisper identify speakers?

Yes, since MacWhisper 12, with local WhisperKit models that carry the Speaker Recognition badge, and with the cloud providers ElevenLabs and Deepgram.

How do I assign speakers in MacWhisper?

Transcribe with a supported model, then rename speakers in the sidebar. To move a segment, hover over it and press the speaker's number key.

How do I merge speakers in MacWhisper?

Right-click the speaker name in the transcript or the sidebar and choose Merge Speaker To.

Why is MacWhisper not showing speakers?

Most often the selected model does not support it. Pick a WhisperKit model with the green Speaker Recognition badge.

Is speaker recognition free in MacWhisper?

MacWhisper's pricing page lists speaker recognition under Pro.