Free tool

Video to Text

Send an MP4, MOV, WebM or MKV and get the words back. Up to 90 minutes, free. We read the audio track — you get text, not a video.

Looked after by Clack, a typewriter with a sheet of paper in it.

We show the transcript here and email you the text, SRT and VTT, so you still have them tomorrow.

Free. No account. 2 files a day per person, up to 90 minutes each.

Ninety, because across 96 transcripts we measured the median episode was 47.3 minutes and 96% were 90 minutes or under.

How to get text out of a video

  1. 1Check the size firstOver 600MB, export the audio on its own — same transcript, a fraction of the upload.
  2. 2Drop in the fileMP4, MOV, WebM or MKV, up to 90 minutes. Only the audio is read.
  3. 3Say where to send itTranscript on screen, and TXT, SRT and VTT in your inbox.
  4. 4Import the subtitlesSRT for Premiere, Resolve and Final Cut. VTT for web players and YouTube.

Questions

Does it read the words on screen?
No. This transcribes what is said, not what is written. Text in the picture — slides, lower thirds, captions already burned in — is not read at all. That is optical character recognition, a different job entirely.
Which video formats work?
MP4, MOV, WebM and MKV, up to 600MB and 90 minutes. Only the audio track is transcribed; you get text back, never a video.
My export is bigger than the limit. What now?
Pull the audio out and send that instead. A 90-minute 1080p export can be several gigabytes, while its audio as an MP3 is under 90MB — the same words, a fraction of the upload. There is a one-line command for it further down this page, and any editor can do it with an audio-only export.
Does the whole video have to upload?
Yes, if you send a video. We cannot read the audio track out of a file we do not have. That is the practical argument for extracting the audio first: it is usually ten to fifty times less to upload, and the transcript is identical.
Can it burn the subtitles onto my video?
No. You get an SRT and a VTT to import into your editor or upload alongside the video. Burning styled captions into a video is what Slice’s paid captioning tool does, and it is a genuinely different job from this one.
What about a video with several people talking?
You will get everything they said, as continuous text, without labels saying who said it. Speaker labels are a paid feature. For an interview you are publishing, that distinction matters, so it is worth knowing before you start rather than after.
Is a screen recording fine?
Yes, as long as somebody is talking. A silent screen recording comes back with the honest message that we could not hear any speech, rather than an empty file and no explanation.
How this compares to Otter, Rev and the rest

We read the free tiers of six other transcription tools off their own pricing pages and put them in one table — longest free file, whether they label speakers, whether you need an account, and what happens when the free part runs out. It includes where we lose, because a comparison that does not is an advertisement.

The size problem, and the fix

Video files are enormous next to what is actually being transcribed. A 90-minute talking-head export at 1080p is commonly 3–6GB. The audio inside it — the only part any transcriber reads — is under 90MB as an MP3. You are uploading fifty times more than the job needs.

So the limit here is 600MB, and the honest advice is to pull the audio out first. Every editor can do it: in Premiere it is File → Export → Media with the format set to MP3; in Resolve it is the Deliver page with “Audio only”; in Final Cut it is Share → Export File with Audio Only. If you have ffmpeg, it is one line:

ffmpeg -i your-video.mp4 -vn -b:a 128k audio.mp3

-vn means “no video”. The result transcribes exactly the same as the original file, because it contains exactly the same speech.

What we read, and what we do not

Only the audio track. Anything written on screen — slides, names in a lower third, captions somebody has already burned in — is invisible to this. If what you need is the text in the picture rather than the words in the room, this is the wrong tool and no amount of trying will make it the right one.

After you have the transcript

The SRT and VTT that come back are ready to import. If your editor wants a format neither of those is, the subtitle converter handles that in your browser without uploading anything. If you want captions actually burned onto the video, styled and animated, that is Slice’s paid captioning tool rather than this one — and it is a different job, not a bigger version of this one.

More Free Tools

Shorts by Slice

From the team behind these free tools

One video. A week of posts.

Upload an episode and get back the moments worth posting, cut and captioned.

  • Reads the whole episode, then picks the excerpts worth posting
  • Captions burned in and framed vertical, ready to post
  • Seven days free, no card
Try Shorts by Slice