Rescroll

YouTube Shorts to text, timed to the word.

Drop in a Short and get its transcript with a timestamp on every line, ready to copy, or download captions cut into short lines for a vertical frame. Free, private, and nothing is uploaded.

  • 100% free
  • No sign-up
  • 99 languages
  • Timestamps, SRT and VTT
  • Files stay on your device

Loading the tool…

It runs in your browser. Nothing is uploaded.

How it works

How to convert video to text, free, in three steps.

  1. 1

    Drop in your video or audio

    MP4, MOV, WebM, MP3, M4A or WAV, from a phone, a camera, a screen recorder or a podcast mic. It opens in your browser; nothing is uploaded.

  2. 2

    Transcribe it

    The language is worked out from the first thing said, or pick it yourself. The first time, the speech model downloads once and stays in your browser for next time.

  3. 3

    Edit, copy or download

    Read the transcript line by line with timestamps, fix any word, then copy it or download it as plain text, SRT or WebVTT captions.

Why this one

Free, with nothing held back, and nothing uploaded.

Every word timed

Each line shows when it starts; click the time and the video plays from there. Captions are timed to the word, not spread evenly over a sentence.

Captions ready to upload

SRT and VTT files cut the way subtitle editors cut them: two lines of up to 42 characters for widescreen video, one short line at a time for vertical video.

99 languages, detected for you

It runs Whisper, OpenAI's open speech-recognition model, which knows 99 languages. It works out which one is spoken, or you choose it.

Private by design

The model runs on your own graphics card or processor, in the browser. Your video is never uploaded, so it's fine for unreleased videos, client calls and anything else you'd rather keep to yourself.

Your file is opened and processed by your own browser. It is never sent to a server, so it stays private, and there’s no upload to wait for.

How to get the transcript of a YouTube Short

YouTube shows a transcript for videos that have captions: on a computer, open the video's description and click Show transcript. When a Short has no captions, or you want the transcript as a file with timestamps, or captions to upload, transcribe the video itself.

For your own Shorts, download the video from YouTube Studio (Content, then the menu next to the video, then Download) and drop it here. It's transcribed on your device and comes back as timed lines, with captions in short lines that fit a vertical frame, ready to edit and upload.

To study someone else's Shorts, use YouTube's transcript where there is one, or Rescroll: paste the link and it transcribes the Short and reads its on-screen text, so you can ask what the hook is and why it works.

Rescroll

Only have the link? Need the words on screen too?

This converter transcribes a file you have. Rescroll goes further: paste a TikTok, Instagram Reel or YouTube link and it gets the transcript and reads the text on screen, then lets you ask anything about the video.

  • Transcripts straight from a link
  • On-screen text read too
  • Chat with every video you save

Questions

The video to text converter: your questions, answered.

How do I get the transcript of a YouTube Short?

If the Short has captions, open it on a computer and click Show transcript in its description. For a transcript you can download with timestamps, or captions to upload, drop the video file here and press Transcribe.

How do I add captions to my YouTube Short?

Transcribe the Short here and download the SRT. In YouTube Studio, open Subtitles, choose the Short, add a language if asked, then under Subtitles click Add, choose Upload file and With timing, and select the SRT. YouTube accepts SRT and WebVTT files.

Can I turn a YouTube Short into text without downloading it?

This tool needs the video file. Without it, use YouTube's own Show transcript where the Short has captions, or paste the link into Rescroll, which transcribes it and reads the text on screen.

How accurate is the transcription?

It uses Whisper, OpenAI's open speech-recognition model: the base version by default, and the larger small version when you choose High accuracy. On clear speech in widely spoken languages it gets nearly every word; strong accents, people talking over each other, music under the voice and unusual names are where it slips. Read it through and fix what's wrong: the captions update with your edits.

Which languages can it transcribe?

99, from English, Spanish, Portuguese, Hindi and Arabic to Welsh and Swahili: every language Whisper was trained on. It detects the language from the first speech in the file; if it guesses wrong, pick the language and transcribe again. It's most accurate in widely spoken languages; for others, choose High accuracy.

Does it read the text on screen?

No. It transcribes what's said. Text that only appears on screen, like a hook in big letters, captions burned into a TikTok or a slide, isn't in the sound, so a speech model can't hear it. Rescroll reads both: paste a TikTok, Reel or YouTube link and it transcribes the speech and reads the on-screen text, frame by frame.

Why does it download a model the first time?

Because the transcription happens on your device, the speech model has to be on your device too. The first time, your browser downloads it from Hugging Face, usually 110 to 140 MB with the speech engine (about 280 to 350 MB for High accuracy; the page shows the exact size for your device first), and keeps it, so the next file starts in seconds. Only the model is downloaded: your video isn't sent anywhere.

Which browsers does it work in?

Current Chrome, Edge, Safari and Firefox. In Chrome and Edge on a computer the speech model runs on your graphics card (WebGPU), the fast way; where a browser can't do that, it runs on your processor instead and takes longer. On a recent laptop, with the model already downloaded, a 37-second clip took about 4 seconds on the graphics card and about 10 on the processor.

How big a file can it handle?

There's no file-size limit of ours: a video of several gigabytes is fine, because only its sound is kept, and long recordings are transcribed in pieces that fill in as they go. What grows is the time: a 10-minute recording took about 40 seconds on a recent laptop's graphics card. On a phone, keep to shorter files: an hour of sound takes about 230 MB of memory.

Can I edit the transcript?

Yes. Click any line and type: fix a name, take out a filler word, rewrite a sentence. The text you copy and the TXT, SRT and VTT files you download all use your edits, and edited captions keep the timing of the line they're in.

Can I put the captions into the video itself?

Yes, with the free caption generator on this site: it transcribes the video the same way, then burns the captions into an MP4, word by word, in a look you choose. It can also burn in an SRT or VTT file you made here.

Is this video to text converter really free?

Yes. There's no price, no trial, no account and no limit on how many files you do. The video to text converter runs on your own device, in your browser, so it costs us nothing to run and we don't charge for it.

Is my video or audio uploaded anywhere?

No. The file is opened and processed by your browser, on your device, and never sent to a server: not to us, not to anyone. You can check: watch the Network tab of your browser's developer tools while it works, and you'll see the file is never sent anywhere.