Word-level timestamps, nine caption styles, uppercase pop or subtle sentence case — burned into the video, no SRT juggling.
Open the app to run it — 3 free clips on signup, no card required.
The transcriber produces word-level timestamps — that's what makes karaoke highlighting possible.
Nine templates from BOLD POP to subtle sentence case; adjust size, position and words per line.
Captions are rendered into the pixels — they show up on every platform, no separate subtitle file.
90+ languages via multilingual speech recognition; captions keep the original language and casing rules you choose.
Yes — position and size are sliders in the editor, per clip.
Karaoke word-highlighting is the default; static-line templates are available too (Subtle, Inkbox).