Transcribe Video to Text

Upload an audio or video file and get the text back. Files are forwarded to the configured speech-to-text provider and never stored.

File transcription is not switched on yet, so you cannot upload a file here for now. Transcripts from YouTube videos work today and need no file.

Upload a video and get its spoken content as text. This is the video counterpart to the audio transcriber: the audio track is pulled out and recognised, and the words come back as a transcript.

It is the right page when you have a video file rather than a link — a recording of your own, a downloaded talk, a screen capture — and you need the words out of it.

Frequently asked questions

Can I paste a YouTube link instead?
Use the YouTube pages for that. They read the video's existing captions, which is far faster than recognising audio. This page is for video files you have on disk.
How long will it take?
Roughly proportional to the length of the recording, since the audio has to be listened to. A ten-minute video takes appreciably longer than a one-minute clip.
Will the transcript have timestamps?
Where the speech-to-text provider returns timing information, yes. That lets you line the text up against the video afterwards.
Does the picture matter at all?
No. Only the audio is used. A video of a silent demonstration would produce an empty transcript.
Is the file kept?
No. It is processed for recognition and not retained by this site.