Do I have to convert the video to audio first?

No. That's the whole point of this page: we take the audio out on our side. Converting first only wastes your time and a bit of quality.

Is the video uploaded whole?

Yes, and it's stored on European Union servers for as long as your retention says. If you'd rather not upload the picture, extract the audio yourself and use the audio tool instead.

Which containers work?

MP4, MOV, MKV, AVI, WEBM, WMV, FLV and M4V. What matters isn't the container but the audio track inside, and we read the ones any of them carry.

Can I get subtitles instead of plain text?

Yes. The same transcript exports as SRT or VTT with the timings already in place — that's the subtitle generator, same engine.

First 45 seconds free

Turn a video into text

Upload the video as it is. We take the audio out, transcribe it and hand you the text with timestamps and speakers.

MP4, MOV, MKV, AVI, WEBM — no converting first
Timestamps that match the video, frame for frame
Subtitles out the other end, if you want them

MP4
MOV
MKV
AVI
WEBM
WMV
FLV
M4V

Interview — Marta Ribas02:03

Interviewer00:00
Marta, thanks for making the time. I'd like to start at the beginning: how did you end up deciding to rewrite onboarding?
Marta Ribas00:11
It was pretty uncomfortable, honestly. We had an onboarding flow that did reasonably well on activation metrics, but when we sat down to watch the session recordings we saw people completing the steps without understanding what they were setting up.
Interviewer00:34
So, good numbers and poor comprehension. How exactly did you spot it?
Marta Ribas00:41
We transcribed thirty user interviews and looked for language patterns. The word that came up most was «guess». People kept saying «I guess this connects my calendar». That «guess» cost us about six weeks of work, but it was the clearest signal we've ever had.

DOCXPDFSRTVTTCSV

Drag your files here

MP3, WAV, M4A, MP4, MOV… up to 10 GB per file

Options

They apply to every file in this batch

Detect speakers

Split it by voice; otherwise it all goes as one speaker

Generate a summary

Key points, decisions and action items

Translate when it's done

On top of the original transcript

Files 0Estimated cost —

Start without an account: we'll ask for a free one to keep the text.

How it works

1
Drop the video
Any common container, up to 10 GB. Only the audio travels; the picture stays where it is.
2
We transcribe the audio
With speaker separation if there's more than one voice, and timecodes on every line.
3
Take the text or the subtitles
DOCX and PDF to read it; SRT and VTT to put it back under the video.

In detail

You don't have to extract the audio first. Drop the MP4, the MOV or the MKV straight in: we pull the audio track out on our side, and the video itself never gets re-encoded or re-uploaded anywhere else.

That matters more than it sounds. Converting a two-hour recording to MP3 before uploading costs you half an hour and a quality loss you don't need, and it's the step where most people give up.

The audio track is extracted here, so nothing needs converting on your machine.
Timestamps line up with the video: click a line and it plays from there.
Speakers separated, which in an interview is the difference between text and a transcript.
Exports as SRT and VTT, ready for an editor or an HTML5 player.

What people use it for

Courses and lessons

The text becomes the notes, the searchable index and the accessible version.

Recorded calls

Zoom, Meet or Teams recordings come out as an MP4. Drop it in as it is.

Video for social

The subtitles come out of the same pass, and most people watch on mute.

Questions

Start with your own recording