Skip to content

Video to text converter

Turn what's said in a video or audio file into a transcript, for free: in paragraphs with their times, to copy or download. It's transcribed on your device, so nothing is uploaded.

MP4, MOV, WebM, MP3 or WAV, or drop one on the player. It's transcribed on your device: nothing is uploaded.

An example: 8 seconds of IMPAULSIVE

Settings

Free, with nothing to sign up for. The speech model is a one-time download of about 76 MB; after that it's kept in your browser.

How to transcribe a video to text

  1. Choose your video or audio file, or drop it on the player. Pick a part if you only need some of it.
  2. Pick the language, or leave it to detect, and press Transcribe.
  3. Read it through: click a paragraph's time to hear that part, then copy the transcript or download it.

What to do with a transcript

Show notes and posts. A podcast episode or a video, written down, is the start of its description, a blog post or a newsletter. Quotes are easier to find in text than by scrubbing through the video.

Chapters. A new topic is easier to spot in a transcript than by ear. The YouTube timestamp generator transcribes the same way and lets you start a chapter at any line, then checks the list against YouTube's rules.

Captions. The same transcript, cut into timed lines, is a captions file. Make one with the auto caption generator, or download the SRT here.

Clips. The lines people would share are the moments worth clipping. That's how clips get chosen: read how to repurpose a long video and how to clip a podcast.

Private, because it stays on your device

Most transcription sites upload your file to their servers. This one doesn't: the speech recognition model, OpenAI's Whisper, runs in your browser, so interviews, meetings and unreleased episodes stay on your computer. The model is downloaded the first time, about 76 MB, and your browser keeps it for next time.

Questions

How do I convert a video to text?

Choose the video (or an MP3 or WAV), pick the language or let it detect it, and press Transcribe. The transcript comes back in paragraphs, with the time each one starts; copy it, or download it as a text file, an SRT or a VTT.

Is it really free? Is my video uploaded?

It's free, with nothing to sign up for, and nothing is uploaded: the speech recognition model (OpenAI's Whisper) runs in your browser. It's downloaded once, about 76 MB, and kept there for next time.

Can it transcribe audio files, like a podcast MP3?

Yes: MP3, M4A and WAV files work as well as MP4, MOV and WebM videos.

How long can the video be?

Up to 30 minutes at a time; for a longer one, pick each part in turn. On a computer's processor it takes about half as long as the part plays, and much less where the browser can use the graphics card.

How accurate is the transcript?

Close to word for word for clear speech in a quiet room, in English and the other big languages. Strong accents, crosstalk, names and numbers are where to check it. Click a paragraph's time to hear that part again.

Which languages does it work in?

About 100, the languages Whisper was trained on. It detects the language by itself, but picking it helps with short clips and mixed languages.

From transcript to clips

Paste a YouTube link and Clyper reads the whole video, finds the moments worth posting and makes them vertical clips with captions: up to 30 per video.

or upload a video

Guides

More free tools