Video to Word: The Transcript as a DOCX

Upload a video or paste a link, let it transcribe, then export DOCX. You get a Word document with what was said in the video, paragraph by paragraph, with the speaker’s name in front and the timecode if you want it, ready to edit, comment on and share.

MP4, MOV, MKV, WEBM, AVI up to 8 GB or a link · DOCX, PDF and TXT export · 120+ languages

Names, timecodes and paragraphs, set once

interview-cam-a.mov38:12 · 2 speakers
SpeakersMaya OrtizHost
ParagraphsEvery segmentEvery 20 s
ExportDOCXPDFTXT
interview-cam-a.docx is ready

Click or drag & drop to upload your audio or videoTap to upload your audio or video

MP3, MP4, M4A, MOV, MKV, WEBM, AVI, WAV, FLAC, AAC, OGG, OPUS, WMA, WMV

No credit card required · Stored in the EU · Never used for AI training

Videos People Want as a Word File

Interviews on camera
Training and how-to videos
Webinars and talks

A filmed interview becomes a DOCX you can cut into a Q&A, each answer under the interviewee’s name with the timecode to find the shot again.

Interviews on camera

A recorded walkthrough turns into a document the team can edit into a step-by-step guide, without anyone typing from the screen.

Training and how-to videos

The recording of a talk becomes a Word file colleagues can comment on, track changes in and attach to an email.

Webinars and talks

What Goes Into the Word Document

The DOCX is built from the transcript of the video. These are the export settings you choose, checked in the app in November 2026.

Text
Everything said in the video, in order; pictures, slides and on-screen text are not included
Paragraphs
One per segment, or merged into blocks every 5, 10, 15, 20 or 30 seconds
Speaker names
On every paragraph or only when the speaker changes, with the names you set in the editor
Timecodes
In front of each paragraph, like (1:14 - 1:19), or switched off
One speaker only
Export just the lines of one person, for example the guest’s answers in an interview
Language
The original transcript, or a translation of it into one of 50+ languages on paid plans
Microsoft Word’s own Transcribe
Takes .mp4 among video files; MOV from an iPhone, MKV and WEBM screen recordings need converting first
Plans
DOCX and PDF come with the Creator plan; the 30 free minutes export TXT, which Word opens too

Set Up the Word File Before You Export

A few choices decide whether the document reads like an article or a script.

Speakers

Name the speakers first

Rename Speaker 1 and Speaker 2 in the editor once, and every paragraph of the DOCX carries the real name.

Paragraphs

Merge lines for reading

For a document people will read, choose blocks of 15 to 30 seconds. Keep one paragraph per segment when someone will check quotes against the video.

Timecodes

Keep them for editors

A timecode in front of each paragraph lets a video editor find the moment. Switch them off for a clean handout.

Visuals

Add what was only on screen

Steps shown but not spoken, like a menu clicked in a demo, are not in the transcript. Add them in Word while the video plays.

How to Convert a Video to Word

From video to finished document in three steps.

Start Transcribing30 free minutes · No credit card
Upload the video
Check names and words
Export DOCX

Add an MP4, MOV, MKV or WEBM file up to 8 GB, or paste a YouTube, Vimeo or Google Drive link.

Upload the video

Rename the speakers and fix words while the video plays; click any line to jump to it.

Check names and words

Pick DOCX, set paragraphs, speaker names and timecodes, and open the file in Word, Google Docs or Pages.

Export DOCX

Frequently Asked Questions

Video to Word: common questions.

All questions
Word for the web and Word for Microsoft 365 on Windows can transcribe uploaded recordings, including .mp4, up to 300 minutes a month. Use this tool for MOV, MKV or WEBM files, links, longer videos or more languages.
No. The DOCX contains the transcript: the words, speaker names and timecodes. Frames, slides and on-screen text are not added.
Yes, on paid plans. Translate the transcript, then choose the translation as the language when you export DOCX.
Yes. The 30 free minutes export TXT, which you can open or paste into Word; DOCX itself needs the Creator plan.
Yes. With speaker recognition on, the export can include only the lines of the speakers you pick.