Voice typing in Chrome is about to feel much more natural
AS Photography / Pexels
Google is quietly making voice dictation in Chrome feel a lot more natural. With the latest Chrome 151 Beta, the company is introducing a new capability that allows the browser’s speech recognition engine to automatically infer punctuation based on the way people speak, eliminating the need to explicitly say commands like “comma” or “full stop.”
The update may sound minor at first glance, but it addresses one of the biggest frustrations with voice typing: speaking naturally often produces text that lacks punctuation unless users consciously dictate every punctuation mark. By teaching Chrome to understand pauses, rhythm, and speech patterns, Google is taking another step toward making conversations with computers feel more human.
Chrome wants to understand how you speak, not just what you say
The new feature arrives through the Web Speech API in Chrome 151 Beta. Google has added a new unspokenPunctuation boolean attribute to the SpeechRecognition interface. When enabled, the speech recognition engine automatically inserts punctuation based on pauses, intonation, and prosody instead of requiring users to say punctuation commands aloud.
In practical terms, that means users can dictate an email, document, or message in a more natural conversational style while Chrome determines where commas, periods, and other punctuation marks belong.
The improvement is particularly useful for longer dictation sessions where repeatedly saying “comma,” “period,” or “question mark” interrupts the natural flow of speech. It could also make browser-based transcription tools, note-taking applications, accessibility software, and AI-powered writing assistants feel significantly smoother.
Developers stand to benefit as well
Because the feature is part of Chrome’s Web Speech API, web applications that rely on speech recognition can implement the functionality without having to build their own punctuation models.
Google says the feature works by analyzing speech pauses and prosody rather than relying solely on spoken words, bringing browser-based speech recognition closer to how humans naturally communicate.
The addition also reflects a broader trend across Google’s software ecosystem. As Gemini and AI-powered language models become increasingly integrated into products like Chrome, Android, and Workspace, the company is placing greater emphasis on understanding natural human conversation instead of requiring users to adapt their speech for machines.
Chrome 151 Beta already includes the feature for developers to test, though broader availability will depend on the browser’s stable release schedule. As with many experimental APIs, developers will ultimately determine how widely it’s adopted across web applications.
While automatic punctuation won’t transform voice typing overnight, it’s the kind of quality-of-life improvement users are likely to notice every time they dictate a message or transcribe a conversation. Sometimes the biggest upgrades aren’t flashy new AI features but small changes that make technology better at understanding how people already communicate.
Moinak Pal is has been working in the technology sector covering both consumer centric tech and automotive technology for the…
AI security cameras may soon recognize your walk before they recognize your face
A new AI gait system tracks body motion through skeletal keypoints, aiming at long-range identity checks where face scans and fingerprints fall short.
Security cameras are built to look for faces. New research suggests they may soon have another target, the small habits buried in the way someone walks.
A paper published in the International Journal of Reasoning-based Intelligent Systems describes SKDMap-Net as a gait recognition system designed to identify people from walking video, even when the camera doesn’t get a clean look at their face. Instead of relying on a close-up scan, it studies how a body moves from frame to frame.
Read more
A 20-second 3D printer breakthrough comes with exactly the kind of catch science loves
The process can create complex microstructures far faster than some laser-based methods, but full 3D control is still a work in progress.
A 3D printer that can make a structure in about 20 seconds sounds like a lab claim wearing a cape. The clever bit is real. The catch arrives before anyone starts dreaming about instant replacement parts.
University of Utah researchers have demonstrated a holographic 3D printing technique that hardens tiny structures in one exposure instead of building them layer by layer. That one-shot approach could avoid the weak, leaky seams that stacked printing can leave behind. For now, though, this is a tool for microstructures, not a shortcut to printing whatever object pops into your head.
Read more
Amazon is full of copycats and shady brands. This Chrome extension lets you avoid them.
Shopping on Amazon used to be simple. You searched for a product, compared a few familiar brands, and checked out. These days, it often feels like you’re scrolling through an endless parade of names that look like someone leaned on a keyboard before hitting publish. That’s exactly the problem Knockoff is trying to solve.
Created by developer Josh Pigford, the Chrome extension doesn’t promise to expose counterfeit products or magically tell you what’s good. Instead, it tackles something arguably more annoying: the flood of unfamiliar, mass-produced brands that dominate Amazon search results.
Read more