Drop your raw lecture, talking-head, or vlog footage into the chat and get back an MP4 with the silences and filler words ("um," "uh") cut out. You also get FCPXML, EDL, and CSV edit lists so you can keep editing at full source quality in Premiere or DaVinci Resolve. Runs in the cloud, nothing to install. Measured: a 1:50 synthetic-voice sample came back at 0:57 (20 cuts); an 11-minute clip processed in 3:13. This isn't a highlight picker.
Automatically cuts silences and filler words like "um" and "uh" from talking-head, lecture and vlog footage. ffmpeg silence detection (plus optional local STT filler detection) works out the segments to keep, then it renders a frame-accurate mp4 plus EDL and FCPXML for Premiere or DaVinci at source quality. In a measured sample, 47.3% of a 33.87 s source was removed with an 11.6 ms audio/video length gap. It strips dead time, it does not pick highlights. Works with ffmpeg only, no API key.
提供長影片連結，或上傳檔案。它會讀取來源內容，自行判斷值得剪輯的片段，產生附字幕的短片、審查結果，並只交付通過審查的短片——每支都附上建議標題、開場吸睛句與主題標籤。
口播文案一键变分镜表 + FFmpeg 命令流：粘贴文案和素材清单，自动生成分镜规划、素材匹配与转场标注，以及 8K 代理剪辑、响度归一化、多画幅转换的 FFmpeg 命令，附 YouTube/B站/抖音交付清单。你的剪辑大脑，不是云端渲染农场。
給它還沒剪的影片（3 分鐘以內，自動聽打）或原始逐字稿，拿回保留計畫（每一句留哪一遍、為什麼）、慢中快三種節奏、B-Roll 清單、剪輯清單和字幕檔。超過目標長度時給「整體加速」和「刪句」兩個方案讓你選，不自己偷刪。Upload raw footage or a transcript and get a keep plan, three pacing versions, a B-roll list, an edit list and subtitles.
Upload a podcast or long-video transcript and get ~10 ready-to-cut clips for Shorts, TikTok & Reels: exact timecodes, explainable scores, a reused-content risk check, editor files, a cutting script and vertical-video captions.