Step-by-step
-
1
Drop an audio or video file onto the import bar, or click it to browse. For several clips at once, use New Batch.
-
2
Choose an accuracy — Fast, Balanced, or Accurate — and press Start analysis. The first run downloads a verified speech model; after that everything runs locally.
-
3
Play the preview and correct any word the model got wrong. Edit a word inline, delete it, add a missing one, or use search and replace.
-
4
When the captions look right, export. Choose a folder and the app writes a word-level .srt for the clip. You can also burn the styled captions into an MP4 instead.
-
5
You choose where output goes. Exports ask for a folder and write your .srt files or captioned videos there. The app keeps its own settings and downloaded models in your Windows user folder, and it references your original media in place rather than copying it.