Microsoft Word can now transcribe lectures and voice commands

Microsoft Word is the most important application in the software giant’s Office suite. A word processing software that will be 40 years old next year since its premiere. Two new features are announced aim to improve user productivity. Both are powered by the Azure Cognitive Services artificial intelligence platform.

Microsoft has announced two new features that are surely appreciated by journalists and students. Microsoft Word for web now allows automatic transcription of a conversation recorded with the microphone and audio already present on the device. There are improvements to the dictation function of Microsoft Word that now supports voice commands thanks to a series of compatible commands. The features are only available for subscribers of Microsoft 365.

Transcription

The first one is the Transcribe function in MS Word. A tool that will allow us to record conversations directly in MS Word thanks to automatic transcription. Functionality that allows to detect and differentiate the speaking of different people fluently and accurately.

Once the transcript has been generated, the user can revisit parts of the recording, reproducing the audio with time stamps. And if necessary, making the appropriate corrections. In the same way that we can record a conversation in real-time. We can also load existing file (mp3, .wav, .m4a, or .mp4) to obtain the Word transcription.

The feature takes advantage of the artificial intelligence of the Azure Cognitive Services platform which makes it possible to recognize different voices. Registration begins when the user clicks the button in the sidebar within MS Word. It is also possible to upload an audio or video file (mp3, .wav, .m4a, or .mp4) already present on the computer. But in this case, there are limits of duration (five hours per month) and length (200 MB).

At the end of the conversation, the transcription is shown with separate blocks for each speaker. You can hear the final result and edit the text. The user can insert the entire transcript into the document or individual parts.

Transcription in MS Word only supports the English language, although Microsoft is expected to add other languages in the future. Also to extend it to other platforms such as desktop versions and those for Android and iOS mobiles that will be available at the end of the year.

Dictation: Voice command

Another voice command feature present in Microsoft 365 is Dictation. This feature is present both on desktop and mobile and in transition between devices. It allows you to add, format, edit, and organize your text.

Microsoft has also improved the Dictation functionality. You can use voice commands to format text, such as bolding a sentence, starting a bulleted list, or inserting emojis. Voice dictation is available for free in MS 365 for web, iOS, and Android if a Microsoft account is used. It will also arrive in Word for Windows and macOS by the end of the year, but only for Microsoft 365 subscribers.

The second feature Dictation also comes from the AI services provided by Azure. It consists of the addition of voice commands to control certain functions of the application such as starting a list or putting a sentence in bold. Microsoft says that the user will be able to speak naturally and Word will recognize everything they say.

Microsoft’s goal with these new features is clear: to convert a greater number of users into Microsoft 365 subscribers. Keep in mind that a subscription to specialized services such as Grammarly or the Otter may cost more than the entire subscription to the Microsoft suite.

Leave a Reply