Tobii Eye Gaze Technology: What It Is and What It Means for Webcam Audio

The short answer

Tobii is best known for eye tracking: hardware and software that estimate where a person is looking on a screen and turn that gaze into input. It is used for gaming, research and, through Tobii's assistive-technology line sold under the Tobii Dynavox name, for communication devices that let people with limited speech or movement select words and phrases with their eyes. For anyone concerned with webcam audio, the key point is that an eye tracker is an input device for gaze, not a microphone. Eye gaze can replace a mouse or a keyboard, but it does not capture speech. Spoken audio in a call or recording still comes from a webcam microphone, a headset or another audio input you choose separately.

No product specifications, prices or test results were supplied for this guide, so it covers how the technology works in general terms and what that means in practice. Check details for any specific model with the manufacturer.

How Tobii-style eye tracking works

Dedicated eye trackers of the kind Tobii is known for generally use near-infrared light and specialized image sensors. The light creates reflections on the surface of the eye, and software compares those reflections with the position of the pupil to estimate the direction of gaze. A short calibration, in which the user looks at points on the screen, maps those estimates to screen positions for that person.

Once calibrated, gaze can drive different kinds of interaction:

• Dwell selection: looking at an on-screen target for a set time activates it, which works like a click.
• Gaze-assisted pointing: the cursor or focus moves toward where the user is looking, sometimes combined with a key press or switch.
• Communication software: on assistive devices, gaze selects letters, symbols or phrases, which the device then speaks aloud with synthesized speech.
• Awareness features: some consumer software uses gaze or presence to adjust what is on screen.

How an eye tracker differs from a webcam

Both devices contain a camera, which is why they are easy to confuse. Their jobs are different. A webcam captures a visible-light image of you for video and usually includes a built-in microphone. A dedicated eye tracker uses its sensors to measure eye position and generally does not produce a video feed for a call or supply audio. Software-only eye tracking that runs on an ordinary webcam also exists. It is a separate approach from dedicated infrared hardware and is typically more sensitive to lighting and head movement, though how well any particular product performs is not established here.

Aspect | Webcam | Dedicated eye tracker

Main purpose | Video image for calls and recording | Estimating where the user is looking

Typical light used | Visible light | Near-infrared

Appears in a call app as | Camera and, often, a microphone | Usually neither; it acts as an input device

Captures speech | Yes, if it has a built-in microphone | No

Typical placement | Top of the display | Commonly below the display, facing the user

What this means for capturing speech

Adding an eye tracker does not change your audio chain. In a conferencing app's audio settings, the input device (the microphone the app listens to) remains whatever you select: the webcam's built-in microphone, a USB microphone or a headset. If the eye tracker is installed alongside a webcam, both devices can be used at once. The webcam provides picture and sound, and the tracker provides gaze input.

There are a few practical considerations:

• Placement: a webcam at the top of the screen and an eye tracker at the bottom can usually coexist. Keep the tracker's view of your eyes clear, and don't let the webcam or its cable block it.
• Infrared overlap: some webcams use infrared for face sign-in. The evidence available here does not show whether that interferes with a given eye tracker. If tracking becomes unreliable, test with the webcam's infrared features disabled.
• Microphone distance: a person who relies on eye gaze may sit in a fixed position or use a mounted setup. A webcam microphone's pickup depends on distance and room noise, so check the voice level with a short test recording rather than assuming the default placement works.

Eye gaze communication and video calls

For someone using an eye gaze communication device, the voice in a call is often synthesized speech rather than speech picked up by a microphone. There are two broad ways that voice reaches other participants:

• Acoustic pickup: the device speaks through its own speaker, and a nearby microphone, such as the webcam's, captures it. This is simple, but the result depends on volume, distance and room noise. A call app's noise suppression or echo cancellation may also reduce or clip sound it treats as background or speaker output.
• Direct routing: the communication software sends its audio straight into the computer or call as an input source, with no room microphone in between. Whether this is supported depends on the specific device, software and operating system, and the supplied evidence does not confirm it for any Tobii product.

If the user also speaks, even partly, a microphone is still needed for their natural voice. In that case, check that the call app's noise suppression is not cutting off quiet or intermittent speech.

Next steps

• Decide whether you need eye gaze for computer control, for communication, or for both. This determines whether a consumer tracker or an assistive device is the relevant category.
• Confirm with the manufacturer or an assistive-technology specialist that the device is compatible with your operating system and call software.
• If synthesized speech must be heard in calls, ask whether the device can route audio directly to the computer.
• In your call app's audio settings, select the microphone deliberately and make a test call or recording to check level and clarity.

What this guide could not confirm

No model-specific specifications, accuracy figures, prices, compatibility lists or independent test results were available for this guide. Statements about how eye tracking works and how it relates to audio input reflect general, widely documented principles, not measurements of any particular Tobii product. Confirm audio routing, interference with infrared webcams and software support for your exact setup before relying on it.