AI-powered vs. voice-based camera tracking

Overview 

Room OS supports two tracking modes:

• Voice-based tracking

• AI camera tracking

Both keep the right person in view. They work in different ways, which affects setup, behaviour, and how natural the experience feels.

Pleneo RoomVision and RoomVision XL use AI camera tracking.

—————————————————————————————————————————

How each works 

Voice-based tracking

Voice-based tracking follows the person who is speaking. The microphones identify where the active speaker is, and RoomHub switches the camera to the view set for that location.

In practice:

• Tracking is location-based

• Camera views are set in advance

• The camera switches cleanly between them

Pleneo makes this simple with a guided setup and built-in checks. No extra processors or scripting required.

AI camera tracking

AI camera tracking works by sight rather than sound. The camera recognises people in the room and follows them in real time, keeping everyone naturally framed as they move or take turns speaking.

• No presets

• No zone mapping

• No calibration

The movement is smooth and continuous, more like a human camera operator than a system that only reacts to triggers.

—————————————————————————————————————————

Setup and configuration 

Voice-based tracking

Set up per location, in two steps:

• Speak from the location you want to track

• Set the camera view for that location

Setup is predictable and repeatable, even across many rooms.

AI camera tracking

Simpler. Connect a Pleneo PTZ camera, and tracking starts right away. People are recognised automatically, and framing adjusts on its own, with nothing to configure.

—————————————————————————————————————————

Performance and experience 

Voice-based tracking:

• Works in defined zones

• Switches between set views

• Predictable and repeatable across rooms

AI camera tracking:

• Follows people by sight

• Works even in noisy rooms

• Moves smoothly and continuously

AI camera tracking adapts on its own to a single presenter, a panel, or a group discussion, with no reconfiguration.

The two work together. AI camera tracking handles auto-framing and presenter tracking automatically, so there's nothing to set up. If you also want the camera to favour specific seats, you can add voice-based tracking on top.

—————————————————————————————————————————

Why AI camera tracking is the default

AI camera tracking is simpler to deploy, needs no calibration, and follows people rather than sound:

• Tracks people, not sound direction

• Adapts automatically to multiple speakers

• Smooth, lifelike camera movement

• Simple, hands-off setup

That's why Pleneo RoomVision and RoomVision XL use AI camera tracking by default. For rooms that prefer sound-based control, RoomHub still offers voice-based tracking with guided setup.

—————————————————————————————————————————

In summary

Both modes keep the right person in view:

• Voice-based tracking is structured and predictable

• AI camera tracking is fluid and natural

Pleneo RoomVision and RoomVision XL use AI camera tracking for a natural, hands-free experience.