Google Docs audio to text
Google Docs audio to text: upload the voice typing recording and get the text with a timecode on every line. Free $0, 3 files a day.
The file of the voice typing recording is the whole input, and the engine reads it in one pass. The whole recording comes back as one document. The free plan is $0 with 3 files a day, and one file may be 30 minutes.
How to get Google Docs audio to text
- 1
Turn on the microphone
The microphone of the computer is switched on, and the microphone box appears on the screen of the document.
- 2
Send the file to the engine
Drop the file of the voice typing recording on the widget above, set the language and switch the speaker split on when more than one person talks.
- 3
Read the text, fix a name
The text comes back one segment per line, with the start and the end time of every piece. A wrong name is fixed in the editor.
- 4
Export and send it on
Take TXT for a plain text, SRT or VTT when the voice typing recording has to become a subtitled video, and DOCX for a review on Pro.
What comes back from the engine
- TXT
One segment per line, the way a person wrote it down. It is the format to paste into a ticket, a chat or a document.
- TXT, CSV
The start and the end time of every segment, and the speakers named separately when you ask for it.
- SRT, VTT
SRT and VTT with the time of every line, so the recording can carry its own subtitles.
- Markdown, DOCX
The transcript is edited through the API and exported as Markdown for a wiki, or as DOCX for a review.
What Google Docs keeps, and what it gives
- Where the file is
Voice typing runs in the browser: when you turn on voice typing or captions, your web browser controls the speech-to-text service, decides how your speech is processed and sends the text to Google Docs or Google Slides.
- What the file is
The text goes into a Google Docs document, and the voice typing of Slides writes into the speaker notes of the slides.
- Length of one file
up to 30 minutes on the free plan, no minute limit on Pro
- Free plan
$0: 3 files a day, up to 30 minutes per file, no card
What the recording does not give you
Google Docs gives you the file, and the engine gives you the text with the time in it. The hard part of the recording is over once the file is on the disk; the text is a minute of waiting. Our own engine reads the voice typing recording and keeps every timestamp, which is what makes the text quotable later.
Tips
Name the file of the voice typing recording after the meeting, not after the day.
Google Docs gives the file, but the name of the file is yours to choose.
Check the length of the voice typing recording before the upload: 30 minutes is the limit of one file.
Over 30 minutes on the free plan a file has to be cut before sending; Pro has no minute limit.
Set the language of the voice typing recording yourself when you know it, or leave it on automatic detection.
Questions about Google Docs audio to text
What do I need to know about Google Docs audio to text?
The file of the voice typing recording is the input, and the engine reads it as it is: no conversion, no link, and no account.
Do I need an account for Google Docs audio to text?
Bring the voice typing recording to your disk and upload it here; our own engine returns the text with the time of every line.
What comes back after Google Docs audio to text?
Our own engine reads the voice typing recording and keeps the time of every segment, so the work ends with a document.
Is a link enough for Google Docs audio to text?
Send the voice typing recording to the widget and the text comes back as a document, with the speakers on request.
Which file do I need for Google Docs audio to text?
There is one step before the engine: the file of the voice typing recording has to be on your own disk.
Related pages
- How to transcribe audio in Google DocsHow to transcribe audio in Google Docs: where Google Docs keeps the file, and what the engine does with it.
- How to transcribe a podcastHow to transcribe a podcast: the steps of the platform, and what comes back from the engine.
- Audacity audio to textAudacity audio to text: the file of Audacity, the limits of it and the price of the service.
- Transcribe audio to textWhat one recording file gives to the engine, and what the text of it looks like.
Sources
- SType & edit with your voice - Google Docs Editors Help (read 2026-10-25)support.google.com · checked
- TTranscription service page (read 2026-10-25)transcrib.si · checked
- TPricing page (read 2026-10-25)transcrib.si · checked
Reading: 4 minutesUpdated Transcribsi editorial team
Drop a recording — the text arrives in a minute
Speakers by name, a time on every line, export to TXT, SRT, VTT, CSV and Markdown.