SmoothCutDownload

On-device captions

Captions from your voice, without sending it anywhere.

Most videos are watched with the sound off, and most caption tools upload your audio to make them. SmoothCut downloads a speech model once and does the work on your machine.

  • Word-timed subtitles from your voice
  • The model runs on your computer
  • Works offline after one download
  • The language is detected automatically

How it works

On-device captions, step by step

  1. 01

    Download a model once

    Pick a speech model -- the recommended one is about 75 MB -- and it is saved on your computer. From then on, captions are one button.

  2. 02

    Nothing leaves your machine

    The audio is transcribed locally. There is no upload, no queue and no per-minute charge, and it works on a plane.

  3. 03

    The transcript does more than captions

    The same transcript is how SmoothCut finds filler words and abandoned takes, so they can be cut for you.

On-device captions: questions

Do captions need an internet connection?

Only for the first download of the speech model. After that they are generated offline.

Is my audio sent to a server?

No. Transcription runs on your own computer.

Which languages are supported?

The speech model detects the spoken language automatically. You can choose a larger model than the recommended one for more accuracy, at the cost of a bigger download.

Record better videos, faster.

Free to record, edit and preview. Pay once when you are ready to export.

macOS and Windows · No account needed