Audio Transcriptor
Start
Try it without an account

Generate subtitles for your video

Upload the video and get an SRT or a VTT with the timings already in place. Correct anything before downloading.

Drag your file here

MP3, WAV, M4A, MP4, MOV… up to 10 GB

  • SRT and VTT, timings included
  • Speakers marked, useful for interviews
  • Fix the text before downloading
  • MP4
  • MOV
  • MKV
  • WEBM
  • MP3
  • WAV
  • M4A

What this tool does

Subtitling by hand is the slowest job in video: you play, pause, type, and then spend as long again nudging the timings. This does the first pass in about three minutes an hour and leaves you the part that actually needs a person — checking a name, fixing a term.

What comes out isn't a raw text dump: the lines are cut where they should be cut, the timings match the audio to the millisecond and, if there's more than one voice, each line knows who said it.

What we handle that others don't

  • Timings to the millisecond, taken from the audio itself and not estimated.
  • Lines cut at a readable length instead of dumped as one long paragraph.
  • Speaker names in front of the line when the recording has several voices.
  • More than 90 languages, and a translated subtitle track if you ask for one.

How it works

  1. 1

    Upload the video or the audio

    MP4, MOV, MKV, WEBM, MP3, WAV or M4A, up to 10 GB.

  2. 2

    Check the timing

    Play it back with the text alongside and correct whatever needs it.

  3. 3

    Download the subtitles

    SRT for editors and platforms; VTT for a browser player.

What people use it for

Social video

Most people watch on mute. Subtitles are the difference between watched and scrolled past.

Accessibility

Subtitles are what makes a video usable for someone who can't hear it.

Courses

A subtitled lesson is a searchable lesson, and it's also the transcript.

In detail

How many characters fit on a line

The rule everyone follows is two lines of around forty characters, held on screen long enough to read without rushing: between one and seven seconds, and never less than one. It isn't our rule — it's what settled in television and film over decades, and players assume it's being followed.

The segments come out cut on that basis, not on loose sentences. If you edit the text afterwards to fix a name, the cut stays put: what changes is what's read, not where each subtitle enters and leaves.

SRT or VTT, depending on where they're going

SRT for anything that's an editing program, a desktop player or a platform's upload form. VTT for a video embedded in your own site, because it's the only one the browser's player understands.

Both download from the same screen without transcribing again, so there's nothing to decide up front. If you end up needing the other, grab it; and if you need to move between them later, the converters are there and work without an account.

Questions

And if what you have is the video?

Upload it and you'll get the transcript with timestamps, the speakers separated by name and a summary with the key points. You can start without an account.

Transcribe my recordingSee prices

Related tools

Worth reading