Voice profiles (Mac)

This chapter is for Mac users. Enabling dictation filtering needs the Mac app, and speaker labels are used by Mac system-audio transcription.

A voice profile gives Aria a name for a speaker. An owner profile can also help it select your speech during dictation; a guest supplies labels for system-audio transcripts.

This is a recognition aid, not authentication. Filtering can allow other voices through when it cannot make a confident match.

Enroll

Complete setup, accept the speaker-model download, and keep the background service running. Allow microphone access when asked.

To create an owner profile named alex:

aria speaker enroll alex \
  --role owner

Follow the prompts and provide clear recordings from one speaker. Enrollment asks for five utterances by default and checks that they agree before saving. After it succeeds, run:

aria speaker list

It shows each profile’s name and role.

Use your profile

Enrollment does not turn filtering on. In the Mac app, enable Settings → Dictation → Show Advanced Options → Only type my own voice. It is off by default, and the CLI has no control for this preference.

Filtering needs the speaker model and an owner profile. Without the model, live dictation passes all speech through, but a retry reports no speech. Without an owner profile, or when a sample is inconclusive, speech can pass through. Do not rely on it to keep private background speech out of a recording. Retained originals can contain voices excluded from the delivered text.

Other speakers

To add a guest:

aria speaker enroll partner \
  --role guest

Voice profiles can supply speaker labels in system-audio transcripts. Labels may change as more audio arrives, so the saved transcript may differ from the first labels printed in the terminal.

Replace or remove

To replace alex with new recordings, keep its role explicit:

aria speaker enroll alex \
  --role owner \
  --replace

To remove a profile, use its name from the list:

aria speaker remove partner

Profiles are stored locally and contain a numeric representation of the voice. If enrollment fails, check the speaker-model path with aria doctor and use Troubleshooting.