Audio to Word: Convert a Recording to a Word Document
Transcribe audio and download it as an editable DOCX file
No account? The first 30 minutes of any file are free. Create a free account for premium on your first file.
Convert audio to a Word document: upload the recording, check the transcript, and download a DOCX with speaker names, timestamps and the summary when you want them. It opens in Microsoft Word, Google Docs and Pages.
Why convert audio to Word here
Word preselected
Files you start on this page open the export with Word already chosen, so the download is one click once the transcript is ready.
Speakers and timestamps
Every line keeps its time in the recording. Before you download, choose whether the document shows speaker names, timestamps and the summary, and whether lines are grouped into paragraphs.
Edit before you export
Correct names and words in the transcript editor, then download. Click any line to hear that moment.
Every other format too
The same transcript exports to TXT, Word, PDF, SRT, VTT, CSV and JSON. Paid plans, the Weekly Pass and your first file can also translate it.
How it works
Upload your audio file
Every common audio format is accepted, and video files work too.
Get the transcript
Speech is transcribed with timestamps, and with speaker labels on the premium engine. Check it in the editor.
Download Word
Word (DOCX) comes with your first file, the Weekly Pass or a paid plan.
Audio to Word: what you get
Audio to Word in three steps
- Upload your audio file. The spoken language is detected for you, or pick it from the list.
- Wait for the transcript. Progress shows on the page.
- Open Export. Files started on this page open with Word selected. Set the options and download your Word document (DOCX).
What is a DOCX file?
A DOCX file opens in Microsoft Word, Google Docs, Pages and LibreOffice, so the transcript is ready to edit, comment on and share like any other document.
- Interview and research transcripts you will quote from
- Meeting notes to edit and send around
- Lecture transcripts to annotate as study notes
What the Word document looks like
The document opens with a Transcript heading, then the summary when your file has one and you keep it on, then the conversation, each block headed by its timestamp and speaker name. A short details block at the end gives the duration, the number of speakers and the word count.
Turn on paragraph grouping and consecutive lines from the same speaker are merged into readable paragraphs. Turn off timestamps and speakers and you get clean prose for an article or report.
Export a transcript to Word or Google DocsInterview transcription
What it costs
| You have | What you get |
|---|---|
| No account | The first 30 minutes of any file transcribed, readable on screen |
| A free account | TXT download on every file; your first file, up to 60 minutes, downloads in every format |
| Weekly Pass | $9.99 for 20 hours over 7 days, every export format |
| Pro | $14.99/month or $99.99/year, full-length files and every export format |
Audio to Word vs typing it out by hand
Why upload-and-go beats manual transcription every time.
| Capability | CATT | Manual transcription |
|---|---|---|
| Time to first draft | Minutes per file | 8 to 10 hours per audio hour |
| Accuracy | 99% on clear audio | Depends on the typist |
| Speaker detection | Automatic | Tagged by hand |
| Languages | 99+ supported | Whatever you speak |
| Exports | TXT, DOCX, PDF, SRT, VTT, JSON | Whatever you build by hand |
| Cost | Free for the first 30 minutes | Your time, every time |
Weighing transcription services instead? Read the full CATT vs Otter.ai comparison
Simple pricing
Free for files up to 30 minutes, no card needed. Paid plans start at $14.99.
Cancel anytime. See all plans
Frequently asked questions
Upload your audio file on this page. When the transcript is ready, open Export, where Word is already selected for files started here, and download. Before you download, choose whether the document shows speaker names, timestamps and the summary, and whether lines are grouped into paragraphs.
The transcript is free to start: the first 30 minutes of any file are transcribed with no signup. Downloading this format needs your first file on a free account, the Weekly Pass ($9.99 for 20 hours over 7 days), a minutes top-up or a paid plan (Pro is $14.99/month, or $99.99/year). The first file on a free account, up to 60 minutes and given once, downloads in every format.
Every common audio format is accepted, and video files work too. Accepted formats include MP3, WAV, M4A, FLAC, AAC, OGG, OPUS, WMA and more.
Yes. Open the transcript in the editor, correct names and words, rename speakers, then export. Automatic transcripts can miss words in noisy audio or with unusual names, so a quick check before you publish is worth it.
The spoken language is detected automatically, or you can pick it before you start for the most reliable result. English, Spanish, French, German, Portuguese, Japanese, Arabic, Hindi and many more are supported.
Yes. One transcript exports to every format: TXT, Word (DOCX), PDF, SRT, VTT, CSV and JSON. Formats other than TXT come with the first file, the Weekly Pass or a paid plan.
Yes. Upload the DOCX to Google Drive and open it with Google Docs, or use File, then Open, inside Docs.
Related tools
Interview Transcription
Upload the full interview or focus group, even 2 or 3 hours. Get each speaker labeled, with timestamps.
Meeting Transcription
Upload the whole meeting, even a 3-hour one. Get every word, who said what, and a summary.
Audio Summarizer
Get AI-powered summaries of any audio file
Audio to TXT
Transcribe a recording and download it as a plain text file