How to Transcribe Audio to Text in Word

Kevin Stratvert
16 May 202308:37

TLDRIn this tutorial, Kevin demonstrates how to transcribe audio to text within Microsoft Word using the 'Transcribe' feature. He explains the process of uploading audio, recording directly in Word, and converting it into text. The tutorial covers language selection, editing speaker names, and customizing the transcript's appearance. A Microsoft 365 subscription is required, and the transcript can be saved to OneDrive for backup. Kevin also highlights additional features like playback speed adjustment and text synchronization with audio, as well as editing and inserting specific transcript sections into the Word document.

Takeaways

  • 😀 Microsoft Word allows you to transcribe audio to text directly within the application.
  • 🔊 You can upload an existing audio file or record directly in Word to generate a transcript.
  • ✍️ The transcribed text can be edited, and speaker names can be modified for clarity.
  • 📑 A Microsoft 365 subscription is required to use the transcription feature in Word.
  • 👤 The 'dictate' feature provides a real-time transcript of spoken words, while 'transcribe' processes pre-recorded audio.
  • 🌐 Over 80 languages are supported for transcription, making it versatile for various users.
  • 📹 Supported formats for audio and video uploads include MP4, from which audio is extracted for transcription.
  • ⏺️ The 'transcribe' feature allows you to pause and resume recording within Word.
  • 📈 The playback speed of the audio can be adjusted, and the text highlights as it plays for easy synchronization.
  • 📝 Specific sections of the transcript can be edited or added directly to the Word document.
  • 🔗 A link to the original recording is provided in the Word document for reference and review.
  • 📚 The transcription feature is also available in other Microsoft 365 apps and OneDrive.
  • 🌐 An alternative free option, Whisper AI, is mentioned for generating transcripts without a Microsoft subscription.

Q & A

  • What are the two main ways to transcribe audio in Microsoft Word?

    -You can upload an existing audio file or record audio directly in Word and get a transcript.

  • What is required to use the transcription feature in Microsoft Word?

    -You need a Microsoft 365 subscription.

  • How can you modify a transcript in Microsoft Word?

    -You can change the speaker names, edit the text, and decide how you want the transcript to look.

  • What formats of audio and video files are supported for transcription in Word?

    -Supported formats include MP4, among others.

  • Where are the transcribed files saved in Microsoft Word?

    -They are saved in a new folder called 'transcribed files' in OneDrive.

  • What feature allows you to navigate through a transcript in Word?

    -You can click on timestamps to jump to specific points in the audio.

  • How can you edit the transcript in Microsoft Word?

    -You can use the pen icon to edit text and change speaker names.

  • What are the options for adding a transcript to a Word document?

    -You can add just the text, text with speakers, text with timestamps, or both speakers and timestamps.

  • What happens when you start a new transcription in the same Word document?

    -It will delete the existing transcription on the right-hand side, but the text and link to the recording will remain in the document.

  • What other Microsoft 365 apps support the transcription feature?

    -OneDrive and Word on the Web also support the transcription feature.

Outlines

00:00

😀 Converting Speech to Text in Microsoft Word

Kevin introduces the process of converting audio to text using Microsoft Word. He explains that users can upload an existing audio file or record directly in Word and then obtain a transcript. The transcript can be modified, including speaker names, and the appearance of the transcript can be customized. A Microsoft 365 subscription is required for this feature, and a link is provided to support the channel. The 'dictate' and 'transcribe' options are explained, with 'dictate' offering real-time transcription and 'transcribe' allowing the conversion of existing audio or new recordings into text. The process of choosing a language, uploading audio, and starting a recording is demonstrated. The ability to pause and resume recording, and the subsequent transcription and saving of the audio file to OneDrive is also covered.

05:06

📑 Editing and Incorporating the Transcription into Word Document

The video continues with Kevin demonstrating how to edit the transcript within Word. He shows how to change the speaker's name from 'speaker one' to 'Kevin' and correct any errors in the text, such as fixing a URL. The functionality to add specific sections of the talk to the document is discussed, along with the options to add the entire transcript with various levels of detail, including just the text, text with speaker names, or text with both speaker names and timestamps. The process of linking the recording and transcript to the Word document is shown, including the ability to start a new transcription and the limitation of one transcript per document. Kevin also mentions the transcribe feature in other Microsoft 365 apps like OneDrive and Word on the Web. He concludes by suggesting an alternative free transcription service, Whisper AI, for those without Microsoft Word or a subscription.

Mindmap

Keywords

💡Transcribe

Transcribe refers to the process of converting spoken language into written text. In the context of the video, it is the main function demonstrated, showing how to use Microsoft Word to turn audio files into text documents. The script mentions, 'You can take audio, say me speaking, and then convert that into text, all from within Microsoft Word,' illustrating the core functionality being discussed.

💡Microsoft 365 subscription

A Microsoft 365 subscription is a service provided by Microsoft that gives users access to a suite of applications and services. The video script mentions this as a requirement for using the transcription feature in Word, emphasizing that 'To do this though, you will need a Microsoft 365 subscription.'

💡Dictate

Dictate is a feature within Microsoft Word that provides a real-time transcription of spoken words. The video script explains the difference between 'dictate' and 'transcribe,' stating, 'With the dictate, this will give you a real-time transcript of everything that you're saying.'

💡Transcribe pane

The Transcribe pane is the user interface element in Microsoft Word that appears when the 'Transcribe' option is selected. It is where users can manage the transcription process. The script describes it as 'This opens the transcribe pane over on the right-hand side,' indicating its location and function within the software.

💡Language selection

Language selection is the option within the Transcribe pane that allows users to choose the language of the audio they want to transcribe. The video mentions that 'here you have a dropdown list where you can choose your language,' highlighting the software's multilingual capabilities.

💡Upload existing audio

Upload existing audio is an option in the Transcribe pane that allows users to select and transcribe audio files that were recorded outside of Microsoft Word. The script provides an example: 'You can upload existing audio. Maybe you recorded some audio externally, and now you want to bring that into Word.'

💡Recording

Recording in this context refers to capturing audio directly within Microsoft Word for later transcription. The video script includes a step where the narrator says, 'You can use Microsoft Word to record your audio, and then at the very end, it'll transcribe it,' demonstrating the process.

💡OneDrive

OneDrive is Microsoft's cloud storage service, which is used in the video to store and manage the transcribed files. The script mentions, 'It'll now take that audio file and upload it to OneDrive,' showing how the transcription process integrates with cloud storage.

💡Playback controls

Playback controls are the tools within the transcription interface that allow users to play, pause, and adjust the speed of the audio being transcribed. The script describes a feature: 'I have my playback controls and one of my favorite features. I can adjust the playback speed,' which relates to the user's ability to control the audio playback.

💡Edit transcript

Edit transcript is the ability to modify the text generated by the transcription process. The video script explains how to do this: 'This allows me to edit the transcript. When I click on this, here I could change the speaker,' indicating the level of customization available to users.

💡Add to document

Add to document refers to the feature that lets users incorporate the transcribed text into their Word document. The script describes this process: 'I can add just this specific section of my talk to the document,' showing how the transcribed text can be seamlessly integrated into the user's work.

Highlights

Microsoft Word allows you to convert audio to text.

You can upload existing audio files or record directly in Word.

The transcription feature requires a Microsoft 365 subscription.

You can modify speaker names and edit the transcribed text.

Transcribe feature supports over 80 different languages.

You can upload audio in MP4 format and it will transcribe the audio.

Recording can be paused and resumed within Word.

Transcribed audio is saved and uploaded to OneDrive for backup.

Playback controls allow you to adjust the speed and synchronize text with audio.

Timestamps are provided for each section of the transcribed text.

You can edit the transcript to correct speaker names and text.

The URL in the transcript can be corrected directly within Word.

Transcribed sections can be added to the Word document with timestamps and speaker information.

The transcript can be added to the Word document in different formats: text only, with speakers, with timestamps, or both.

A link to the original recording is provided in the Word document for easy access.

The transcribe pane can be closed and reopened from the voice category in Word.

Only one transcript can be attached per Word document.

Transcription functionality is also available in OneDrive and Word on the Web.

Whisper AI is an alternative for free transcription without a Microsoft 365 subscription.