FluentView evidence
Voice plus optional gaze

Voice names the intent. Gaze clarifies the target.

Fluent combines voice and gaze only when the combination makes the request clearer.

Read the short answer
Short answer

How does Fluent combine voice and gaze?

Voice or text expresses the requested outcome. Optional gaze supplies recent target context for references such as "that file" or "this button." Fluent resolves a stable fixation locally to a semantic Windows accessibility element and sends structured target metadata with the submitted command. Looking never clicks, selects, or runs an action by itself.

Voice and gaze solve different parts of the request

Voice is good at expressing intent: open, summarize, draft, move, compare, or prepare. Voice is weaker when the target is spatial and the user naturally says "that" instead of reading a long label. Gaze is useful for indicating attention, but it is a poor consent signal because people look at things without intending to activate them.

Fluent assigns each signal a narrower job. Voice or text carries intent. A recent stable gaze fixation can name a semantic target. A separate action path decides what to do, and consequential behavior should pause at an explicit approval boundary.

What happens to gaze data

Eye control is off by default and can be paused independently. When enabled, WebGazer estimates gaze in the renderer. Stable fixations enter a short in-memory buffer. Fluent resolves a fixation locally against the Windows accessibility tree before a command is submitted.

The planner can receive a structured attention target containing fields such as the accessible name, role, process, bounds, fixation duration, and timestamp. Raw gaze samples are not persisted or included in agent input. WebGazer calibration data may remain in local browser storage.

  • Camera and gaze permission are optional.
  • Raw samples stay in a short in-memory buffer.
  • Target resolution happens locally against a semantic accessibility element.
  • Structured target metadata is attached only when a command is submitted.
  • Coordinates are not treated as a click instruction.

What happens when the target is stale or unclear

A deictic request such as "click that" needs a recent reliable target. If Fluent cannot resolve one, the intended behavior is to ask the user to look again or clarify the target. The automation agent is instructed to observe the interface and use semantic controls rather than click a raw gaze coordinate.

The published research record is candid that gaze onboarding, quality, multi-display behavior, and recovery states still need product-grade work. That makes gaze appropriate for preview evaluation, not a dependable baseline. Voice and text must continue to work when gaze is unavailable.

Why multimodal input is worth testing

Research has long explored combining language with pointing because the modalities carry complementary information. Richard Bolt demonstrated voice plus pointing in the 1980 Put-That-There system. Later studies examined how multimodal input can reduce recognition ambiguity and support correction.

Those studies motivate the product hypothesis. They do not prove that Fluent is effective. Fluent must run its own accessibility-led task studies with the installed Windows product and publish the protocol, failures, and results.

Direct answers

Questions people ask before trying Fluent.

Does looking at a control click it?
No. Fluent does not treat gaze as activation. Gaze can contribute target context only when a voice or typed command is submitted.
Is an eye tracker required?
No. Voice and text are the baseline. The preview gaze path uses a camera-based WebGazer surface and must be explicitly enabled.
Are raw gaze coordinates sent to the planner?
The documented contract says raw gaze samples are not included in agent input. A locally resolved semantic target may be included with a submitted command.
Is Fluent gaze control ready for everyday use?
No. The research scorecard lists onboarding, quality, multi-display, stale-target, and recovery work that must pass before a public release claim.
Check the record

Sources and product disclosures.

  1. Fluent privacy and safety disclosureCurrent gaze behavior and stored-data contract.
  2. Put-That-ThereRichard Bolt, ACM SIGGRAPH, 1980.
  3. Multimodal text entry studyKristensson and Vertanen, Interspeech 2011.
  4. Fluent research methodGaze readiness and recovery gates.
Written and maintained byJason Matthew Suhari

Creator of Fluent. Product claims are reviewed against the current implementation and published limits.

GitHub profile
Inspect before you trust

Judge Fluent by the evidence.

Read the method, inspect the limits, and evaluate the current preview against published thresholds.

Read the research method