CLIP WORKROOM / CAPTIONS & CUTS

Make every word land.

Cut audio or video by editing its words, trim it, and burn styled captions into the picture. Your file stays on this device; only its sound goes to Whisper, and only when you ask for a transcript.

Open audio or videoChoose from library ↗Try a sample

Edit by text

Transcribe, then delete words to cut them from the sound and the picture.

Spoken language

Only the sound, as 16 kHz mono, goes to Cloudflare's Whisper (open weights) and it is not stored. Cutting, playback and export happen on this device.

Captions & trim

Start · secondsEnd · secondsImport SRT or VTTCaption timingCaption colorText size

Captioned clips play through in real time, up to two minutes. Keep this tab visible while recording. Sound is included when the source has an audio track. Edit by text works on the whole file.