On Tuesday, Microsoft added the audio transcription feature to the Word for web application, and the Transcribe in Word option will appear in the web version of (Word) for Microsoft 365 subscribers, providing an easy way to automatically transcribe the audio.
Microsoft supports existing audio files, or the ability to record conversations directly inside (Word for the web) and transcribe them automatically. Once the conversation is copied, Microsoft's artificial intelligence separates each speaker and divides the conversation into sections that are easy to operate, modify and insert into a word document. The copy feature also supports audio or video that the user takes elsewhere, with support of up to 200MB of MP3, WAV, M4A, or MP4 files.
It is clear that the processing time will vary greatly if the user uploads a separate audio clip, but with testing the feature in recording meetings, it takes seconds for the transcription process to complete, if the user is recording within (Word) itself.
The audio transcription works by recording any sound from a computer, which means that the user can take advantage of the feature in transcribing meetings, calls, or videos from YouTube. Word can also record audio from a computer's microphone. Microsoft is targeting journalists who transcribe interviews, students who record lectures, and anyone else who needs to transcribe meetings and calls easily.
Microsoft is launching the audio transcription feature initially for the application (Word for the Web), with plans to introduce the same feature to the application (Word) in Android and iOS systems later this year. Also, English is the only language supported at the moment, but due to Microsoft's presence in other languages with regard to transcription support, it is expected that the new feature will expand to include other languages soon.
It is reported that the new feature is only available to Microsoft 365 subscribers, however, there is a maximum of 5 hours per month to download audio from devices, without any way to extend the copy time at the present time, as for the recorded audio inside (Word for the web) there is no limit for copying.