菜单
Audio processing utilities - noise reduction, normalization, enhancement
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
Extract a video segment using FFmpeg with precise start/end times
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 | audio-process |
| description | Audio processing utilities - noise reduction, normalization, enhancement |
Audio processing utilities for cleaning and enhancing voice recordings.
# Remove background noise
python skills/audio-process/denoise.py input.wav output.wav
# Normalize audio levels
python skills/audio-process/normalize.py input.wav output.wav
# Full voice cleanup pipeline (denoise + normalize + enhance)
python skills/audio-process/clean_voice.py input.wav output.wav
| Operation | Description | Use Case |
|---|---|---|
denoise | Remove background noise | Voice cloning prep |
normalize | Normalize audio levels | Consistent volume |
clean_voice | Full cleanup pipeline | Best for voice samples |
afftdn and anlmdn filters