跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
视频与音频

audio-trim

Trims leading and trailing silence from audio files using FFmpeg. Use when the user wants audio trim, trim silence at start/end, remove leading/trailing silence, batch SFX cleanup, or voice dialogue preprocessing.

godot-fun · 已有 AI 审核记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add godot-fun/godot-agent --skill audio-trim

技能说明


name: audio-trim description: Trims leading and trailing silence from audio files using FFmpeg. Use when the user wants audio trim, trim silence at start/end, remove leading/trailing silence, batch SFX cleanup, or voice dialogue preprocessing.

Audio Trim

Remove leading/trailing silence via FFmpeg silenceremove.

Rules

When this skill applies, read and follow skill-dependency-manager �run scripts as documented, install missing tools into .dependency/.

Quick Start

Default: threshold -50 dB, both sides, output to <audio-dir>/audio-trim/<audio-name>:

.dependency/python/python .ai/audio-trim/trim.py --audio path/to/audio.wav

Custom threshold:

.dependency/python/python .ai/audio-trim/trim.py --audio audio/sfx.wav -t -45

Thresholds

AssetThreshold
UI / SFX / voice-50 dB (default)
Clipped attack / noisy room-40 to -45 dB
Ambience / loops-60 dB or skip

Common Flags

--audio · -t / --threshold · -o / --output

.dependency/python/python .ai/audio-trim/trim.py --audio audio/sfx.wav -t -50

Originals are never modified. Input must be a single audio file (--audio), not a directory. Supported: .wav, .mp3, .ogg, .flac, .aac, .m4a, .wma.

Agent Notes

  1. Use the bundled script, not ad-hoc -ss/-to.
  2. Looping BGM �avoid end-trim; can break loop seams. Skip this skill or trim manually.
  3. Attack or reverb cut off �raise -t (e.g. -45 or -40).
  4. FFmpeg filter details: reference.md

CLI

Copy-paste commands: cli/audio-trim.md