In this guide, you will find instructions on how to create a voice and face profile in Teams.

(info) Eesti keeles

Creating a voice and face profile gives you the ability to have Teams automatically identify who is speaking and who is currently on camera during meetings.

After creating a voice and face profile, Teams can help you with the following:

For meeting participants:

  • When you create a voice and face profile, Teams automatically recognizes you - both on camera and when you are speaking. Your name appears on screen, in transcripts, and in Copilot responses. The profile is optional, but without it, your name may not appear. It is a good idea to create a voice profile with the microphone you use every day.

For meeting hosts:

  • If participants have profiles, Teams automatically identifies speakers and those in the frame. Names appear on screen, focus shifts to the active speaker, and recordings and transcriptions are more accurate. Copilot can create person-specific summaries. If there are no profiles, these features will work in a limited way.


Voice recognition:

  • Teams automatically recognizes when you’re speaking.
  • Your name appears on the screen as the speaker.
  • Transcription associates what you say with your name.
  • Copilot can answer questions like “What did Martin say?” and create person-specific summaries.

Face recognition:

  • Teams recognizes your face and knows you’re in the room.
  • If there are multiple people in front of one camera in a room, Teams can tell who’s who.
  • Your name may appear at the edge of your video window or on the room camera image.

Display your name on screen

Once your profiles are set up, Teams automatically displays:

  • your name when you’re in the frame
  • your name when you start speaking
  • your performance in transcription and Copilot summaries

Automatic camera focus

If the room uses conference room settings (such as Logitech Rally + microphones):

  • the camera zooms in and focuses on the active speaker
  • when the speaker changes, the focus automatically moves to the new speaker
  • multiple people in the room appear as separate “panels,” as if they were on separate cameras

For the user

  • A voice and face profile is optional, but without it, Teams may not:
    • display your name when you speak or are on camera;
    • link your talk in transcription and Copilot responses.
  • Profiles are saved to your Microsoft account and can be deleted or updated at any time.
  • You can create a voice profile with or without flaps – do it with the microphone you actually use.
  • A premium license is not required for basic features (name display, speaking/in-frame detection).

For the meeting host

  • If participants have profiles created:
    • Teams automatically detects who is speaking and who is in the frame.
    • The speaker’s name appears on the screen and in the transcript.
    • The camera can automatically focus on the active speaker.
    • Copilot can create person-specific summaries and responses (“What did Martin say?”).
  • If participants don’t create profiles, recognition is limited and the name may not appear on the screen.


Creating a voice and face profile

  1. In the Teams desktop app, click the Settings and more button → select Settings from the drop-down menu. 
  2. In the left side tab, select Recognition → in the window that opens, select Create voice profile.
  3. To start creating your voice profile, select your microphone from the list (for example HyperX Cloud II Wireless) and click the Start voice capture button and read the text out loud into your microphone. 
  4. After reading the text our loud, click the End voice capture button.
  5. The voice learning process will start, which will take a few seconds.
  6. Voice profile has successfuly been setup when this window opens. To continue into face recognition, click Get started.
  7. To create a face profile: select your webcam from the list (for example laptop camera, docked monitor camera, or standalone webcam) → click the Start button→ follow the instructions on screen (description of the activity below the video image, example of the activity at the bottom right of the video image).
  8. Voice and face profile has been created successfully. To finish, click the Close button.