A speaker tracking camera is a conference camera that automatically finds whoever is talking and frames them, usually by combining a microphone array (to locate the voice) with face or body detection (to frame the person). Remote participants see the active talker in a close-up instead of a small figure in a wide room shot.
How speaker tracking works
- Locate the voice. A mic array measures tiny time differences as sound reaches each microphone and calculates the direction of the talker.
- Match it to a person. Computer vision finds faces and bodies in the image and picks the one in that direction.
- Frame the shot. The camera zooms in, either digitally (cropping a high-resolution sensor) or by physically moving a PTZ lens.
- Hold and switch. Timers stop it from jumping at every cough. It switches when a new person speaks long enough, and may return to a group shot during back-and-forth conversation.
Some systems use a separate wide-angle lens to watch the whole room while the main lens moves, so they can cut to the next talker without searching. Multi-camera systems pick the camera with the best front-facing angle.
Speaker tracking vs other framing modes
| Mode | What it does | Best for |
|---|---|---|
| Auto framing / group framing | Fits everyone in the shot | Most meetings |
| Speaker tracking | Close-up of the active talker | Larger rooms, formal meetings |
| Presenter tracking | Follows one person walking at the front | Training, classrooms |
| Multi-person framing (IntelliFocus, IntelliFrame, Grid) | Separate tiles per person | Remote fairness, gallery views |
See auto-tracking conference cameras and intelligent multi-stream framing.
Why it matters
In medium and large rooms, people at the far end of the table are tiny in a wide shot. Speaker tracking gives remote attendees a view of facial expressions and makes it clear who's talking. It also reduces the need for someone to drive the camera with presets.
It can be distracting in fast conversations, which is why most systems let admins choose between speaker, group and grid modes.
What to look for when buying
- Optical vs digital zoom: Optical PTZ gives sharper close-ups at long distances. Digital works well in small and medium rooms with a high-resolution sensor.
- Switching speed and smoothness: Look for a second "scout" lens or multi-camera support for cut-free transitions.
- Pickup range: The mic array has to hear the talker to find them.
- Platform support: Some framing features only work on certain platforms or modes.
- Control: You should be able to turn tracking off for privacy or presentations.
Catalog products with speaker tracking
| Product | Type | How it tracks |
|---|---|---|
| AVer CAM570 | 4K dual-lens PTZ | Built-in audio tracking: 3 sensor pairs, 10 m, ±60° |
| Yealink MeetingBar A40 | Android video bar | Speaker Tracking, IntelliFocus, Auto Framing |
| Yealink MeetingBar A50 | Android video bar | Speaker Tracking with 10 m pickup |
| Yealink UVC86 | USB PTZ | Speaker and Presenter Tracking |
| Yealink MVC S98 | Multi-camera Teams Rooms kit | Multi-Camera Speaker Tracking, 2-4 cameras |
| Poly Studio X52 | All-in-one bar | DirectorAI speaker framing |
| Logitech Rally AI Camera | 4K camera | RightSight 2 Speaker view |
More picks in best auto-tracking conference cameras.
Not sure which framing mode suits your room? Tell us the room size and seat count and we'll point you to the right camera.
Related guides
- AVer Camera Not Working: Not Detected, Blurry, Not Tracking
- Auto-Tracking Conference Cameras: How They Work
- Choosing a Conference Room Camera for Teams or Zoom
- Video Bar Speaker Wattage: What the Watts Really Mean
- What Is People Counting in Meeting Rooms? How It Works
- Appliance Mode vs USB Mode: Video Bar Modes Explained
Outfitting several rooms, or reselling? Get a volume quote or apply for wholesale pricing →
