Captions and transcript

In the Captions module, Generate captions automatically sends only the narration audio for AI transcription and brings back blocks already synced to your speech. Captions follow the language spoken in the video, not the app interface language.

Every block can be fixed: double-click a caption on the stage to edit the text, drag to move it. Style, font, highlight color, background opacity and position apply to all of them.

Exporting captions

At export time, captions can be burned into the video or written to a separate SRT or VTT file to upload alongside it on YouTube.

Cutting filler words

The Transcript screen shows your speech as text with the crutches highlighted: "um", "so", "like", "you know". Pick what to cut using the tags, or click any specific word.

Removal makes micro-cuts: only that word comes out, the rest of the speech stays untouched. The panel shows how many cuts are marked and how much shorter the video gets before you confirm.

Removing silences

In the Audio module, Remove silences analyzes the narration and cuts long pauses, reporting how many seconds came out and how many clips the video was split into. An option smooths the seams with a tiny fade so the cut never clicks.