菜单
Extract a video segment using FFmpeg with precise start/end times
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Generate karaoke-style word-level timestamps by aligning script text to audio using Qwen3-ForcedAligner + jieba for Chinese word segmentation. Use when the user says 'align captions', 'karaoke timestamps', 'word timestamps', 'caption alignment', 'sync text to audio'.
Analyze raw video content using Gemini to identify speakers, topics, key moments, and potential clip opportunities
Audio processing utilities - noise reduction, normalization, enhancement
Find naturally clean, coherent video segments worth keeping (selection over repair)
Text-guided audio source separation using SAM-Audio via mlx-audio
ASR with ~30ms timestamp precision using Qwen3-ASR + ForcedAligner
| name | extract-clip |
| description | Extract a video segment using FFmpeg with precise start/end times |
Use this skill to cut a segment from a longer video file.
python skills/extract-clip/extract.py <input_video> <start_time> <end_time> [output_path]
# Examples
python skills/extract-clip/extract.py video.mp4 01:48 02:25
python skills/extract-clip/extract.py video.mp4 00:30 01:00 output/my_clip.mp4
input_video: Path to source videostart_time: Start timestamp (MM:SS or HH:MM:SS)end_time: End timestamp (MM:SS or HH:MM:SS)output_path: (optional) Output file path, defaults to assets/outputs/clips/<name>_<start>-<end>.mp4Creates an MP4 file with the extracted segment. Uses stream copy when possible for fast extraction.