Microsoft is adding audio transcription to Word

Microsoft is adding automatic audio transcription to Word, starting with Word for the Web, for Microsoft 365 users.

wordtranscription.jpg

Credit: Microsoft

Microsoft is adding a new transcription feature to Word, starting with Word for the Web. The Transcribe in Word feature will allow users to record conversations directly in Word and have them transcribed automatically. Users also can upload pre-recorded audio files or videos, and automatically get a searchable, editable transcription from within Word with this feature enabled.

Microsoft is touting the new transcription feature as helping users stay focused in the moment -- similar to its latest "prosumer" positioning for its Surface devices and other productivity software and services.

Transcribe in Word is available in Word for the web (the Web-based version of Word; not the native Word app) for all Microsoft 365 subscribers and is supported in the new Microsoft Edge or Chrome browsers, officials said in a blog post on Aug. 25. Right now, transcribing audio into US English is the only language supported. Currently, there also is a five hour limit of transcription time per month for uploaded recordings and there is a file size limit of 200MB.  (Note: Microsoft has clarified its post to note that audio recorded within Word is actually unlimited.)

Transcribe in Office mobile will be coming by the end of the year, officials said.

Microsoft is also announcing new dictation features for Word. Via voice commands, users can add, format, edit, and organize text. To use the Dictate with voice commands capability in Word for the Web and Office Mobile (for free), users just need to be signed into their Microsoft accounts. Officials said that voice commands will be available for Microsoft 365 subscribers in Word desktop and Word for Mac apps toward the end of the year.

(A list of the dictation commands available in Microsoft Office apps is here.)

In somewhat related news, Microsoft also announced general availability today, Aug. 25, of its Immersive Reader service. Immersive Reader is an Azure Cognitive Service designed to help users, especially students, read and comprehend text. Transcribe in Word uses another Azure Cognitive Service, Speech to Text, to automatically transcribe conversations