How to Transcribe Audio to Text in Microsoft Word

Converting Speech to Text with Microsoft Word

Typing out minutes from a recorded meeting, transcribing an interview, or capturing lecture notes manually is a tedious and time-consuming process. Thankfully, if you have a Microsoft 365 subscription, Microsoft Word includes a powerful, built-in AI transcription tool that can convert both live speech and pre-recorded audio files into text with remarkable accuracy.

The “Transcribe” feature not only generates the text but also automatically separates different speakers and adds timestamps. This feature is currently available in Word for the Web, Word for Windows, and Word for Mac.

Here is exactly how to transcribe audio to text in Microsoft Word, whether you are recording live or uploading an existing file.

Method 1: Upload a Pre-Recorded Audio File

If you already have a recording saved on your computer (such as an MP3 from a voice recorder app, an MP4 from a Zoom meeting, or a WAV file), you can upload it directly into Word. Microsoft currently allows you to upload up to 300 minutes of audio per month for transcription.

1. Open Microsoft Word (either the desktop application or Word for the Web).
2. Ensure you are signed in to your Microsoft 365 account.
3. Go to the Home tab on the top ribbon.
4. Look for the Dictate button (it has a small microphone icon). Click the small down arrow next to it to open a drop-down menu.
5. Select Transcribe. A new panel will open on the right side of the screen.
6. Click the Upload audio button.
7. Browse your computer for the audio file and select it. Supported formats include .wav, .mp4, .m4a, and .mp3.

Depending on the length of the recording and your internet connection speed, the upload and transcription process may take a few minutes. Leave the window open until it finishes. Once completed, the full transcript will appear in the right-hand panel, broken down by “Speaker 1”, “Speaker 2”, and so on.

Method 2: Record and Transcribe Live Audio

If you are about to start a meeting or a lecture, you can use Word to record and transcribe the conversation in real-time. There is currently no monthly time limit when you record live audio directly within Word.

1. Open Microsoft Word and create a new blank document.
2. Go to the Home tab on the ribbon.
3. Click the down arrow next to the Dictate button and select Transcribe.
4. In the right-hand panel, click Start recording. (If your browser or computer asks for permission to use the microphone, click Allow).
5. Leave the Transcribe pane open while the conversation takes place. You can even type notes into the Word document while it is recording.
6. When the meeting is over, click Save and transcribe now in the right-hand panel.

How to Edit and Insert the Transcript

No automated transcription is perfect. Before adding the text to your main document, you may want to correct names, fix industry-specific jargon, or identify the speakers properly.

• Renaming Speakers: In the Transcribe pane, hover over a speaker’s name (e.g., Speaker 1). Click the pencil icon. Type the person’s real name, check the box that says “Change all Speaker 1,” and click the checkmark to save.
• Editing Text: Hover over any block of text in the transcript and click the pencil icon to fix typos manually.
• Adding to the Document: At the bottom of the Transcribe pane, click the Add to document button. A menu will appear asking how you want it formatted. You can choose to add just the text, text with speakers, text with timestamps, or text with both speakers and timestamps.

The entire transcript will then be pasted directly into your Word document, ready for you to save, format, or share with your team.