Take Command: Control This AI Browser with Your Voice
Comet’s Upgraded Voice Mode Lets You Browse Without Moving Your Mouse
Imagine a browsing experience where your voice navigates the web effortlessly, leaving your hands free for other tasks. Comet, the innovative browser from Perplexity, has introduced an enhanced voice mode that eliminates the need for a mouse. This exciting upgrade allows desktop users to control their browsing entirely through speech, while iOS users can expect the feature to arrive shortly. Get ready to explore a whole new way to browse, where simply talking is all it takes.
A Seamless Hands-Free Experience
With the updated voice mode, users can open websites, scroll through pages, and follow links—all with their voice. For desktop users, you can activate this feature by pressing Shift + Alt + V or Shift + Option + V on Mac. And soon, iOS users will be able to experience Comet as potentially the first mobile browser you never have to physically touch.
This feature is powered by OpenAI’s latest real-time model, emphasizing hands-free control beyond just voice search. CEO Aravind Srinivas recently announced this rollout via social media, highlighting the collaborative efforts of OpenAI’s multimodal team.
Built on OpenAI’s Cutting-Edge Technology
The voice mode operates using OpenAI’s gpt-realtime-1.5 model, which is engineered for low-latency interactions. Srinivas applauded OpenAI, noting that tool-call stability has improved by over 25%. This enhancement ensures that your commands are executed accurately, reducing frustrating misfires. Not to mention, the updated voices now feature improved pacing, perfect for extended listening sessions.
“We’re rolling out an upgraded voice mode on Comet. It’s the first time you can fully control the browser hands-free,” Srinivas shared. He encouraged users to pre-order for iOS, where this feature will be available soon.
The Importance of Full Voice Control
While many browsers treat voice input as a mere gimmick, Comet is taking it seriously. Imagine asking your browser to not only fetch your search results but also to perform tasks like “scroll down,” “open the third link,” or even “summarize this page.” The aim is for your voice to navigate throughout your entire browsing session—no keyboard necessary.
This shift aligns perfectly with the ongoing trend toward ambient computing, suggesting that the web can be more efficient when it’s conversational. Currently, this feature is live for desktop users, ushering in a new era of browser interactions.
Comet also stands out for its privacy approach. The browser processes voice commands locally when possible, ensuring that your click history isn’t stored in the cloud by default. This means you’re not subjected to ad tracking profiles based on your browsing activity.
What to Look For in the Coming Days
As of today, desktop users can experiment with this groundbreaking voice mode. For iOS users, the rollout is expected around March 11, according to App Store pre-order listings. The true test will lie in how natural the controls feel in real-world applications, beyond just demonstrations.
Perplexity has big plans ahead for Comet. The Comet Assistant will learn your preferences, helping you shop, order food, or find flights tailored to your habits. Additional features like a password manager and cross-device synchronization are also on the way. While Android users are still waiting for some of these updates, the voice upgrade marks just the first step for iOS users.
Embrace the future of browsing and unleash the power of your voice with Comet. Your hands-free journey into the digital world is just beginning. Don’t miss out—explore these cutting-edge features and transform the way you navigate the web!
