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)
Upload your mix or master and get a real technical diagnostic - loudness, frequency balance, dynamics, stereo image - turned into a prioritized, DAW-agnostic action plan.
Cuts background noise (AC, fans, electrical hum) and softens sibilance in meeting, lecture, and interview recordings and video, then normalizes loudness to podcast (-16), YouTube (-14), or broadcast (-23 LUFS). Point to a quiet patch and profile mode removes only that noise. Also trims leading/trailing silence and builds a before/after report (spectrogram, LUFS). On a 60-second 1962 Kennedy clip, the noise floor fell 5.6 dB and loudness moved from -17.1 to -15.9 LUFS. Only ffmpeg, no API key.
【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!
將加密貨幣技術分析自動轉成修仙風YouTube影片。支援K線、SNR、SMC、CHOCH、FVG、OB與POC教學，以及BingX主流幣行情分析；產出英文配音腳本、繁體中文字幕、分鏡、縮圖、影片說明，並在工具支援時生成完整MP4。沒有合格交易機會時會明確建議等待，不報明牌、不保證獲利。