Video to text, upload a file
No link needed. Drop a video or an audio file straight from your device and the spoken words come back as text you can copy, or save as TXT, SRT or VTT subtitles.
Drop a video or audio file here
or click to browse · MP4, MOV, WEBM, MP3, M4A, WAV · up to 2GB
See the transcript flow, step by step
A walkthrough of speech turning into clean, timed text.
10%
What you get
- Plain text transcript
- Timestamped lines you can jump through
- Subtitle file, .srt or .vtt
Why people use it
Files stream straight to your device. We keep no copy of the video or the link.
No sign up, no email, no tracking pixel. Paste a link and save the file.
Every tool on the site is free to use, with no daily download cap.
We pick the highest stream the source offers, up to 4K where it exists.
One paste, one click. No queues, no waiting rooms, no forced ads between steps.
Runs in any modern browser on phone, tablet and desktop. Nothing to install.
How to turn a file into text
Drag a file onto the box, or click it and pick one from your device. The name and size appear once it is loaded, then press Get transcript.
The audio is read by speech recognition and the text comes back split into short lines with a timing on each one. Nothing is saved on our side, the file is read once and dropped.
What you can upload
Video files, MP4, MOV, WEBM and MKV, and audio files, MP3, M4A, WAV, OGG and AAC. Screen recordings, voice notes, lecture captures and podcast episodes all work.
Files up to 2GB work. Anything large is decoded in your own browser, downmixed to speech quality audio and sent in parts, so a long recording is transcribed piece by piece and stitched back together with the right timings.
Upload or paste a link
Use this page for anything already on your device, and for private files you would never want to publish anywhere just to get a transcript.
For something already online, the video transcript generator takes the link directly, and for YouTube it pulls the creator's own captions instead of guessing at the audio.
How accurate is it
Clear speech in a quiet room reads back very closely. Heavy background music, several people talking over each other and thick accents all lower the accuracy, so read the text once before you publish it.
Timings are spread across the length of the file rather than measured word by word, so treat them as close rather than frame accurate and nudge them in your editor if you are cutting subtitles.
Questions people ask
What file size can I upload?
Up to 2GB. Larger files are split into audio parts inside your browser before they are sent, so long recordings still go through.
Which formats work?
MP4, MOV, WEBM and MKV for video, MP3, M4A, WAV, OGG and AAC for audio.
Do you keep my file?
No. The upload is read once to produce the text and nothing is written to our storage. Close the tab and it is gone.
Can I get subtitles out of it?
Yes. Save the result as SRT for a video editor or VTT for a web player, and both carry a timing on every line.
Does it handle other languages?
Yes. The language is detected from the audio, so you do not have to set anything before uploading.