Audio

面向用户显式提供的音频文件，用 FFmpeg/SoX 完成格式转换、降噪、响度标准化、变速与提取视频音轨，可选通过 Whisper 或 AssemblyAI 生成 TXT/SRT/VTT 转录，并附播客与各平台响度标准参考文档。

热度 92.44

最近更新 2026-05-17 11:56:14

分类：效率依赖：代码执行 / 读写文件 / 第三方 API应用场景：文件转换 / 工作流 / 摘要总结

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add audio

Metadata

name: Audio
slug: audio
version: 1.0.1
description: Process, enhance, and convert audio files with noise removal, normalization, format conversion, transcription, and podcast workflows.
changelog: Declare required binaries (ffmpeg, ffprobe), add requirements section with optional deps, add explicit scope
metadata: {"clawdbot":{"emoji":"🔊","requires":{"bins":["ffmpeg","ffprobe"]},"os":["linux","darwin","win32"]}}

Required:

Optional (for advanced features):

Situation	Load
FFmpeg commands by task	`commands.md`
Loudness standards by platform	`loudness.md`
Podcast production workflow	`podcast.md`
Transcription workflow	`transcription.md`

Task	Method
Convert formats	FFmpeg (`-acodec`)
Remove noise	FFmpeg filters or SoX
Normalize loudness	`ffmpeg-normalize` or `-af loudnorm`
Transcribe	Whisper → text, SRT, VTT
Separate stems	Demucs (vocals, drums, bass, other)

User says	Agent does
"Convert to MP3"	`-acodec libmp3lame -q:a 2`
"Remove background noise"	Apply highpass/lowpass or dedicated denoiser
"Normalize for podcast"	`-af loudnorm=I=-16:TP=-1.5:LRA=11`
"Transcribe this"	Whisper → output SRT/VTT/TXT
"Extract audio from video"	`-vn -acodec copy` or re-encode
"Make it smaller"	Lower bitrate: `-b:a 128k` or `-b:a 96k`
"Speed up 1.5x"	`-af atempo=1.5`

This skill: