Voiceprints: recognizing people across meetings

A voiceprint is a voice signature Daisy can use to recognize the same person across different meetings, so you do not have to label them every time. Voiceprints are created and stored entirely on your machine.

Enroll a voiceprint while labeling

When you label a speaker in the transcript tab:

1. Click a speaker chip to open the Label speaker dialog.
2. Enter the person's Name (and optionally Email).
3. Tick Save voiceprint for future meetings. This stores an encrypted voice embedding so Daisy can recognize this person automatically.
4. Optionally tick Also check past meetings for this person to scan your older recordings for unlabeled speakers that match and label them too.
5. Click Save.

The past-meeting scan can take a few minutes if you have many recordings.

Manage voiceprints

Go to Settings and open the Voiceprints section. You will see a table of enrolled people showing each person's name, email, number of Sessions, and number of voice Samples (more samples make matching more robust).

• Rename updates a person's name and email.
• Delete removes the voiceprint, so future meetings will no longer auto-label that person.
• Rematch all sessions re-scans every recording for known voiceprints and back-fills speaker labels.

Good to know

• Voiceprints are biometric data. Only enroll people you have permission to identify.
• They are stored encrypted in your vault, and the audio sample never leaves your machine. You can delete any voiceprint at any time.
• Matching is not perfect, so review labels Daisy applies automatically.