mtools.lol

Auto Caption Video

Transcribe a video's speech and burn styled captions into it, in one step.

How it works

  1. 1Upload a video with speech.
  2. 2Pick a caption style, words per caption and position.
  3. 3Download the captioned video.

Features

  • Speech recognised with open-source Whisper on our server.
  • Bold, word-by-word highlight or boxed styles.
  • 1 to 6 words per caption, timed to the speech.
  • 20 languages, detected automatically.

Frequently asked questions

How accurate are the captions?

Clear speech is transcribed well. Music, crosstalk and strong accents lower accuracy. For full control, make an SRT with Audio Transcription, fix it, then use Burn Subtitles.

How long does it take?

About half the video's length.

Is there a length limit?

Videos up to 10 minutes.

Related tools

Burn Subtitles into VideoHardcode an SRT or VTT subtitle file into a video so the captions always show.Audio TranscriptionTurn speech in audio or video into text, with timestamps or as subtitles.Video CompressorBetaMake a video file smaller while keeping it watchable, with an optional lower resolution.Add Music to VideoPut a song or voice-over on a video: replace its sound or mix the music underneath.