
傳送你的 Podcast、訪談、直播或演講影片,就能拿到做好的直式短片:挑出能獨立成立的片段,裁成 9:16,加上逐字字幕,畫面跟著說話的人,音量調平,每支附標題、開場金句和貼文文案。不需要字幕檔。可以直接上傳影片,或貼上檔案直連。

Create production-ready 15-to-60-second scripts, shot lists, overlays, calls to action, and A/B variants in English or Traditional Chinese.

Surgically trim awkward pauses, dragging breaths, and robotic TTS dead air in 0.4s. Built for TikTok, Reels, Shorts, and podcasts to boost audience retention by 15%-25%. Features studio-grade 10ms anti-click cosine crossfading and 50ms voice-head safety buffers to guarantee crisp, zero-artifact broadcast audio.

Cut the silent pauses out of a talking video on your own computer and get a finished MP4 plus a cut list. Light, normal or strong. Fix by chatting: "keep the pause at 1:23". Any language, no API key. 自動剪掉說話影片的停頓,直接交 MP4 成品。

我長期處理中英夾雜的技術型影音內容(教學影片、會議與簡報錄音),很清楚這類素材最頭痛的就是專有名詞和英文縮寫被聽錯。這個 Skill 把我實際在用的整套做法工具化:以 faster-whisper 在本機 CPU 就能轉錄(免 GPU、免雲端 API、免費),並用「轉錄前餵專有名詞提示+轉錄後批次修正同音錯字」兩道工序把準確率拉高;YouTube 連結則走「先抓現成字幕、失敗自動改抓音訊轉錄」的穩定路線,最後一併產出 SRT 字幕、逐字稿與帶時間戳的重點摘要。全程本機運算、檔案不上雲,適合在意內容隱私又要快速消化長影音的人。 I work daily with mixed Chinese-English technical audio, where jargon and acronyms get mis-heard most. This Skill packages my workflow: faster-whisper runs locally on CPU (no GPU, no cloud API)

Your opening is leaking viewers. Get a band-by-band diagnosis of the full first 30 seconds — plus 5 rewritten hooks you can film word-for-word. English & 中文. 你的视频开头正在流失观众。逐段诊断完整前 30 秒,再送你 5 条可以逐字照着拍的改写开头。支持英文与中文。

有了題目,卻不知道怎麼講?透過對話,陪你釐清核心觀點、取捨內容、安排開場與節奏,把零散想法整理成一場有重點、讓人願意聽下去的演講。 融合理論與實務的強大幫手!

【Lifetime Buyout · 100% Offline】Industrial batch voice & de-breath engine for YouTube Shorts, TikTok & podcast creators! Drag & drop an entire folder of audio/video to cut silent gaps and breath pauses in 0.3s. Features 10ms anti-click cosine crossfade, 50ms consonant buffer to protect word endings, and -14 LUFS mastering. Bundled standalone FFmpeg, 1-click Windows launcher, zero token costs, and 100% local privacy. Ditch tedious Audition timeline slicing forever!

把超过 15 秒的镜头想法,变成一段一段能跑出来的分镜方案。 MiniMax H3 一次只能生成 15 秒。想做一个 40 秒的短片,你面对的不是"写一条更好的提示词",而是拆段、定模式、锁一致性、处理接缝这一整套工程问题。这个技能就是把这件事做完,直接给你可提交的东西。