Upload a talking-to-camera recording and get a tighter version with the same message: filler words, false starts, repeated takes and long pauses are removed, the speaker stays framed, and verified word-timed captions are burned in. Free credits on signup.
Filler words such as "um" and "uh", false starts, repeated takes and unnecessary pauses. Cuts are made at sentence boundaries so transitions sound natural, and the content of what you said is preserved.
A single speaker talking to the camera: creator videos, presentations, tutorials, interviews, product explanations and course recordings. Use Auto Clip instead when you want a short highlight rather than a cleaned-up full recording.
Captions are word-timed and added only where the transcription is verified, so nothing is captioned with words that were not clearly said. Choose word-by-word highlighting (default), plain caption lines, or no captions.
Yes. Leave it unset to keep the source framing, or pick 9:16, 1:1 or another ratio: the frame follows the speaker's face, while slides and title cards without a visible face remain fully shown.
Auto detection works for most recordings. Set the language when detection is unreliable — heavy accents, loud background music or very little speech. For Chinese it also selects the caption script: simplified or traditional.
$0.06 per minute of source video ($0.005 per 5 seconds), up to 2 hours per request. Captions, aspect ratio and language add no extra charge. The exact cost is shown before you generate, and new accounts get free credits.