screenkite-clean-cut
screenkite-clean-cut
Remove silence gaps and filler words (um, uh, ah, er, hmm) from a ScreenKite recording in a single pass — one transcript, one dry-run, one cut.
Prerequisites
screenkiteCLI at/usr/local/bin/screenkite-alpha(orscreenkite).ELEVEN_LABS_API_KEY(underscored) in a.envanywhere up from the bundle, or exported in the shell environment.ffmpegon PATH.python3+requests— useuv run --with requeststo avoid install issues.
Phase 1 — Open project
'/usr/local/bin/screenkite-alpha' agent project open \
--path '<absolute-path-to.skbundle>' --json
More from screenkite/awesome-ai-video-editing
use-screenkite-advanced-b-roll
End-to-end pipeline for adding short animated B-roll overlays to a ScreenKite screen recording using the advanced DSL scene layout. Transcribes the microphone audio with ElevenLabs Scribe, proofreads product names via web search, plans brief corner-PiP visual moments, generates each visual with Hyperframes (HTML + GSAP) via parallel sub-agents, renders to MP4, and composites via ScreenKite's setSceneLayout with magicMove transitions. Use when (1) the user opens or references a .skbundle ScreenKite recording and wants animated B-roll accents on top of screen + camera, (2) the user says "add B-roll", "advanced layout", "overlay visuals", "plan visuals for this recording", "ScreenKite DSL", (3) the user wants transcript-driven visual planning where visuals are brief corner accents rather than full-frame takeovers.
13screenkite-transcription-cut
>
10