Skip to main content
  1. Home
  2. Computing
  3. News

I turned my face into a game controller, and you can too

Add as a preferred source on Google

At Google I/O, AI was a theme throughout the event, but another game-changing assistive technology was announced that lets your face control a computer instead of using a mouse. Google’s Project GameFace literally turns your face into a game controller. If even the best mouse or trackball is prving difficult or impossible, this free app can significantly improve your computing experience.

Alan Truly tries Project Gameface while watching Lance Carr.
Alan Truly tries Project GameFace while watching Lance Carr. Image used with permission by copyright holder

Google’s blog post describes how Project GameFace was inspired by the plight of video game streamer Lance Carr, who has muscular dystrophy. A fire led to the loss of Carr’s expensive head-tracking mouse, which had allowed him to keep gaming.

Recommended Videos

Google worked with Carr to develop Project GameFace, a solution that uses a standard webcam and works on any Windows PC. You can download the app from the GitHub project or fork, and customize it for your own particular needs if you know Python.

I installed and tried it. My built-in webcam worked for pointer control, but was too blown out by a nearby window to detect my eyebrows and mouth well. I hooked up an Insta360 Link, which includes face-tracking technology to pan and tilt as I move around. The two technologies blended seamlessly and everything worked great after some fine-tuning.

The cursor speed was much too fast, so I dropped from the default setting of 40 to 15 vertically and 20 horizontally. With these adjustments, I could move my mouse pointer to any point on my screen simply by turning and tilting my head. This isn’t eye-tracking. It seems to follow my nose.

Google's Project Gameface has adjustments for cursor speed.
Google’s Project GameFace has adjustments for cursor speed. Image used with permission by copyright holder

The app recognizes six face gestures: open mouth, mouth left and right, raise left and right eyebrow, and lower right eyebrow. It’s unclear why Lower left eyebrow isn’t an option. These gesture settings, combined with head movement for directional control, make it relatively easy to bind keys and mouse clicks, allowing you to play a game or control a computer with only your face.

There’s plenty of room for improvement here. Ideally, groups of gesture bindings and cursor speeds should be saved for each app so you don’t have to find a single configuration that works for everything. It would also be more convenient to require a confirmation click, with a countdown to revert, after adjusting cursor speed. It took me a few minutes to tame my wild mouse pointer when I first switched on face tracking.

Overall, Project GameFace is a wonderful adaptation that should make life much easier for many people who could otherwise struggle to navigate a computer or play a game. More tech companies should be taking advantage of gesture control enabled by a webcam.

Alan Truly
Alan Truly is a Writer at Digital Trends, covering computers, laptops, hardware, software, and accessories that stand out as…
AI image generators have escaped nightmare fingers and entered the fake premium era
Meta Muse, Gemini, and ChatGPT can now make clean, usable images. They also keep making reality look like a product render with feelings.
Terminal, Railway, Train

I expected this comparison to be uglier. Meta Muse, Gemini Nano Banana 2, and ChatGPT Images 2.0 sounded like a perfect setup for plastic faces, mangled hands, fake products, and posters written in haunted alphabet soup. Instead, they were mostly competent, which somehow made the whole thing more suspicious.

These aren’t identical tools wearing different logos. Meta pitches Muse Image as a social image model living inside Meta AI and its apps. Google frames Nano Banana 2 around speed, editing, and Gemini’s broader knowledge. OpenAI sells ChatGPT Images 2.0 on text rendering, visual control, and stronger prompt handling. Different ambitions, same polished little showroom.

Read more
DuckDuckGo’s browser now blocks the YouTube ads everyone hates
DuckDuckGo adds a Brave-like YouTube ad blocking feature
Text, Aircraft, Airplane

DuckDuckGo has spent the past few months gaining fresh attention as more users look for alternatives to Google’s increasingly AI-heavy Search experience. Now, the privacy-focused company is adding a feature that could make its browser even more tempting for everyday use. DuckDuckGo says its browser can now block most video ads, including those on YouTube, when a video is playing inside the browser.

What’s happening?

Read more
ChatGPT Live could make talking to AI feel straight out of the movies
We might finally get the AI sidekick sci-fi movies promised
Elderly women using ChatGPT live on a smartphone

AI voice assistants have been chasing the sci-fi dream for years, but they still have a hard time holding a conversation with humans. Most voice systems still need clear turns, clean pauses, and a few seconds before they respond. OpenAI is now rolling out GPT-Live, a new voice model for ChatGPT Voice that is designed to make those exchanges feel faster and less scripted.

The main upgrade is what OpenAI calls a full-duplex architecture. In simpler terms, GPT-Live can listen and speak at the same time. It continuously processes what the user is saying while also generating its own response, allowing it to decide when to talk, when to pause, when to keep listening, and when to use a tool.

Read more