English transcription, word by word

Upload a video and AutoCap turns the speech in English into text you can read, correct and download — with the time each word is spoken.

Start free See pricing
your-video.srt
100:00:00,400 --> 00:00:02,150Welcome back to the channel.
200:00:02,300 --> 00:00:04,900Today I'm sharing three quick tips.
300:00:05,050 --> 00:00:06,600Let's get right into it.

What a transcript in English looks like

The same three lines as an SRT file: the words as spoken, with the time each caption starts and ends. Download plain text instead and the timings drop away.

Proofreading a transcript in English

Pick US or UK spelling before you proofread — color or colour, organize or organise — and correct the transcript toward one of them all the way through. Numbers deserve a pass too: most style guides spell out one to nine and use figures from 10 up.

Spoken in
United States, United Kingdom, Ireland, and Malta

How to transcribe a video in English

  1. 01

    Upload your video

    Drop in an MP4 or MOV and tell AutoCap the video is in English. Only the audio leaves your device.

  2. 02

    Let it transcribe

    AutoCap writes out the speech and gives every word its own start and end time.

  3. 03

    Correct the text

    Read along with the video and fix any word in a click. Corrections never use minutes.

  4. 04

    Download

    Save the transcript as plain text, or as an SRT or VTT file with timings, on any paid plan.

What people transcribe

Interviews and podcasts

Turn a recorded conversation into text you can quote, search and share.

Lessons and talks

Give viewers a written version of what was said, with the time each line was spoken.

Social video

Start from the transcript, then style it into captions for TikTok, Reels or Shorts.

Accessibility

A corrected transcript is the base for captions that deaf and hard-of-hearing viewers can rely on.

Good to know before you start

  • AutoCap transcribes video files — MP4 or MOV. Audio-only files aren't supported.
  • Clips can run up to 60 seconds on the free plan and 5 minutes on paid plans.
  • The free plan includes 2 minutes of transcription a month; paid plans start at 60 minutes.
  • Speakers aren't labeled automatically — the transcript is the words, in order, with their timings.

Good to know.

Is it free to transcribe video in English?

Yes, to start. The free plan includes 2 minutes of transcription a month for clips up to 60 seconds. Downloading the transcript as TXT, SRT or VTT comes with the paid plans, from $19 a month.

Can I download the transcript as plain text?

Yes, on any paid plan: a TXT file in paragraphs, ready to quote or paste into a document. SRT and VTT add a timestamp to every caption.

Can I transcribe an audio file?

Not directly: AutoCap works from video files, MP4 or MOV. A recording exported as a video — a still image with the sound — transcribes the same way.

Is my video uploaded?

No. Only the audio is sent for transcription; the video stays on your device.

Can I fix mistakes before I download?

Yes. Every word can be corrected, and lines can be split or merged. Corrections never use transcription minutes.

Other languages

Every language we caption

Try it on the next video you post.

The free plan needs no card. Upload a clip, check the captions yourself, and only upgrade when you want the watermark gone.

Start free See pricing