Captions that land on every word.

Upload a video, run a local transcription, and fine-tune timing with a waveform. No OpenAI API, with MP4 export.

Import or drag your video MP4, MOV or audio file
MEDIUMlocal model
Waveformprecise timing
MP4max quality

Plans

Start free. Upgrade when you need exports and transcription.

Try it

Free

0 EUR

Manual captions, preview, timing editor, and subtitle file export.

  • Manual captions
  • Preview and waveform timing
  • SRT, VTT and JSON export
For creators

Plus

5.99 EUR / month

Automatic transcription, all supported languages, WebM export, and no watermark.

  • Everything in Free
  • Automatic local transcription
  • All supported languages
  • WebM export without watermark

Built for short-form

Not just fast captions. Captions with timing control.

01Automatic transcription

A local Whisper workflow for spoken video.

02Word by word

One phrase at the right time, like modern Reels and Shorts.

03Manual fine-tuning

Preview a word, shift by 20 ms, and snap to audio.

Workflow

1Upload video
2Transcribe locally
3Tune the waveform
4Download MP4

Models stay with you.

The repo contains code. The model ggml-medium.bin lives on your machine or server, so uploads do not need to go to a third-party AI API.