Voice commands and live captions are ready for prime time
Voice typing tools reliant on speech-to-text algorithms have long been a convenient way to create larger text documents quickly, especially if you’re a slow typist, or you're seeking a hands-free experience. Specialized voice typing tools are aplenty, but Google Docs and Slides include one for the average user. The company recently updated the feature to allow editing Slides speaker notes and Docs files using your voice, along with a live caption-generation tool for your presentations.
Google explains that its popular cloud-based Workspace utilities have been updated to minimize errors and lost audio in the transcription process. If you have a microphone set up, open Google Docs and select Voice Typing from the Tools drop-down menu. Click the microphone to dictate, and click it again when you’re done. With the latest update, you can follow up with voice commands like “select paragraph,” “italics,” and “go to the end of the line,” much like you would instruct a human typist to make edits to a body of text.
Voice typing and commands are also now available for the speaker notes section in Slides. Interestingly, Google’s support documentation for voice typing still says you cannot use voice commands for editing your speaker notes. That aside, Slides users can enjoy one more new feature designed as an accessibility aid in presentations. If you’re using Chrome to deliver a Slides presentation, you turn on live captions. It will transcribe everything you say into text seen underneath your slides, just like Live Captions and transcription on YouTube.
Once you start presenting, you can switch captions on using the Toggle captions option under Captions preferences in the three-dot menu. Remember that Google’s method does not punctuate the live captions in Slides, and the feature may not work well in a noisy environment. If you plan to use this feature on a video conference, we suggest consulting other participants because Slides captions could overlap with independent live transcription/translation features on Google Meet and other video conferencing utilities.
Besides these improvements, Google is expanding the availability of its speech-to-text utility to most major browsers. The above improvements will be available to anyone with a Gmail account, including Business customers, starting January 9. However, the feature could show up later for some, since Google expects the rollout to complete on February 21.
Chandraveer is a mechanical design engineer with a passion for all things Android including devices, launchers, theming, apps, and photography. When he isn’t typing away on his mechanical keyboard’s heavy linear switches, he enjoys discovering new music, improving his keyboard, and rowing through his hatchback’s gears on twisty roads.
About Post Author
