The files of a Zoom meeting are an MP4 video, an M4A audio, a chat text file and CC.VTT subtitles.
Zoom transcription
Zoom transcription: upload the Zoom recording and get the text with a timecode on every line, in TXT, Markdown, SRT, VTT or CSV. Free $0, 3 files a day.
The Zoom recording is the only thing this service needs from Zoom. The export of the Zoom recording keeps the time of every line, so nothing is lost. The export is TXT, Markdown, SRT, VTT or CSV, and the free plan is $0 with 3 files a day.
How to get Zoom transcription
- 1
Take the audio, not the video
A long meeting is easier to send as the M4A audio than as the MP4 video of the same call.
- 2
Read the first lines before you share them
The first minute of the text shows whether the recording was clear. If a name is wrong there, it is wrong in the whole file.
- 3
Keep the export next to the recording
The text of the Zoom recording lands in a file of its own. Keep it next to the recording and the two stay together.
- 4
Take the audio track, not the video
When Zoom gives a video and an audio track, the audio is the smaller file and the one the engine reads.
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 Zoom keeps, and what it gives
up to 30 minutes on the free plan, no minute limit on Pro
$0: 3 files a day, up to 30 minutes per file, no card
What the recording does not give you
Say one word of a decision three weeks later and see whether you can find it in the Zoom recording. Almost every question after a meeting is the same question with another name, and the file answers none of them. Our own engine reads the Zoom recording and keeps the time, so a quotation can point at the minute it was said.
Tips
Take CSV when the text of the Zoom recording has to go into a spreadsheet.
Markdown is the format to keep the text of the Zoom recording in a wiki.
DOCX is the format for a review of the Zoom recording, and it comes with Pro.
The limit of one file is 30 minutes on the free plan, and the Pro plan has no minute limit.
Read the first lines of the text before you send the file of the Zoom recording out.
Questions about Zoom transcription
Which file do I need for Zoom transcription?
For Zoom transcription, one file is enough: the Zoom recording is uploaded to the widget above and the text comes back.
Can I search the text later, after Zoom transcription?
Take the Zoom recording first, then send the file to our own engine: the text comes back one segment per line.
What do I need to know about Zoom transcription?
The engine does not care where the recording came from: Zoom only decides where the file waits for you.
Do I need an account for Zoom transcription?
Give the Zoom recording to the engine as it is, and every line of the text keeps the time of the moment it was said.
What comes back after Zoom transcription?
One upload is enough: the Zoom recording goes to the widget, and the text of it comes back as a document.
Related pages
- Free Zoom transcriptionFree Zoom transcription: the file of Zoom, the limits of it and the price of the service.
- Zoom recording to textZoom recording to text: what Zoom says about the recording, and what the engine adds to it.
- How to get Zoom transcriptHow to get Zoom transcript: the same question about Zoom, with the steps and the free plan.
- Transcribe a Zoom recordingThe file of a Zoom meeting, the formats it comes in and what the engine does with it.
Sources
- SZoom help: the files of a meeting (MP4, M4A, chat, CC.VTT) (read 2026-10-24)support.zoom.com · checked
- TTranscription service page (read 2026-10-25)transcrib.si · checked
- TPricing page (read 2026-10-25)transcrib.si · checked
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.