Voice searching is all the rage on Android devices (and your Chrome desktop with this nifty extension) and at the same time we’re being promised new forms of software interactions stemming from the advancements in the natural language processing science. Our operating systems have basic speech-to-text capabilities, but it doesn’t work that great and we rarely use the feature in everyday computing. With Chrome 11, Google is taking a different approach, leveraging their vast computing power to deliver cloud-drive speech-to-text to HTML5 web apps, explains a blog post:
Fresh from the work that we’ve been doing with the HTML Speech Incubator Group, we’ve added support for the HTML5 speech input API. With this API, developers can give web apps the ability to transcribe your voice to text. When a web page uses this feature, you simply click on an icon and then speak into your computer’s microphone. The recorded audio is sent to speech servers for transcription, after which the text is typed out for you.
How does it work?
We’ve tried this out by switching to the Chrome beta channel and the feature works as advertised, with remarkable accuracy you’d come to expect from Google. The latest beta of Chrome 11 also includes 3D CSS acceleration, smartphone app screens, seen below, and other goodies.