Audio Denoise logo

Audio Denoise

OrganizationPopular
ZJU-REAL
audio-denoise

音频降噪:去除录音中的背景噪声、电流声、风噪、嗡嗡声,基于 ffmpeg 滤镜链(afftdn/highpass/lowpass)。 当用户说"降噪""去噪""去杂音""消除背景噪声""电流声""风噪""录音有杂音""音频降噪"时使用。 和 audio-editing 的区别:audio-editing 做剪辑/转码/音量等通用音频操作(内置 denoise 兜底),本 SKILL 专做降噪调参。

Overview

PublisherZJU-REAL
RepositoryEasel
Skill nameaudio-denoise
Stars
1.2K
Forks
175
Bundled files
1
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by ZJU-REAL on GitHub. Read the source before you install it.

Installation

Install the Audio Denoise AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/ZJU-REAL/Easel.git /tmp/Easel
mkdir -p .claude/skills
cp -r /tmp/Easel/skills/openclaw/audio-denoise .claude/skills/audio-denoise
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Audio Denoise in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Audio Denoise on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Audio Denoise is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

音频降噪

清理录音中的背景噪声。降噪专项 SKILL——通过共享脚本 skills/shared/scripts/audio_ops.py denoise 封装 ffmpeg 降噪滤镜,提供三级方案(从基础滤波到 RNN 神经网络),参数确定、可复现,不现场手拼命令。

通用音频操作(裁剪/转码/音量/提取/拼接/淡入淡出/变速)见 audio-editing。本 SKILL 专注降噪。

输入

字段必填说明
input_file音频或视频文件路径
tier1 / 2 / 3(默认 2
output_file默认 outputs/主题名/{filename}-clean.{ext}
mix降噪强度 0.0-1.0(默认 0.8,仅 tier3 RNNoise)
preserve_original保留原始文件(默认 true)

支持格式:wav, mp3, flac, aac, m4a, mp4, mkv, mov。

输出

  • 降噪后的音频文件(放入 outputs/主题名/
  • 处理报告:原始文件信息、所用 tier 与滤镜链、输出文件信息、大小对比

三级降噪方案(对应脚本 --tier

脚本按 tier 自动选滤镜链并打印实际执行的 ffmpeg 命令。

Tier 1 — 基础降噪(ffmpeg 内置滤波)

切除低频隆隆声、高频嘶嘶声 + FFT 降噪,纯 ffmpeg 无外部依赖。 滤镜:highpass=f=80,lowpass=f=8000,afftdn=nr=12:nf=-40:tn=1 适用:轻度噪声、无需模型的快速处理。

Tier 2 — 加强降噪(更强 FFT + 非局部均值)

更激进的 FFT 降噪叠加 anlmdn,仍纯 ffmpeg。 滤镜:highpass=f=70,afftdn=nr=24:nf=-30:tn=1,anlmdn=s=0.0005 适用:中度噪声、稳态背景噪声(空调/风扇/底噪)。默认档

Tier 3 — RNN 神经网络降噪(arnndn + 后处理)

RNNoise 针对人声优化 + 高通预处理 + 动态压缩 + 响度归一化。 滤镜:highpass=f=60,arnndn=m=<model>:mix=<mix>,acompressor=...,loudnorm=... 适用:人声录音、播客、访谈、复杂噪声环境。 需要 RNNoise 模型 sh.rnnn;缺失时脚本自动降级 Tier2 并打印下载提示。

执行步骤

脚本路径(相对项目根):skills/shared/scripts/audio_ops.py

1. 探测输入文件

bash
python skills/shared/scripts/audio_ops.py info input_file

脚本自身检查 ffmpeg/ffprobe,缺失时给安装提示。向用户展示时长/码率/声道,判断音频还是视频。

2. 准备 RNN 模型(仅 Tier3)

检查脚本旁 skills/shared/scripts/models/sh.rnnn 是否存在。不存在则下载:

bash
mkdir -p skills/shared/scripts/models
curl -L https://github.com/GregorR/rnnoise-models/raw/master/somnolent-hogwash-2018-09-01/sh.rnnn \
  -o skills/shared/scripts/models/sh.rnnn

不下载也可——脚本会自动降级 Tier2。也可用 --model <path> 指定其它模型。

3. 执行降噪

bash
# 默认 Tier2
python skills/shared/scripts/audio_ops.py denoise input.wav -o outputs/主题名/input-clean.wav --tier 2
# Tier3(RNNoise,人声)
python skills/shared/scripts/audio_ops.py denoise input.wav -o outputs/主题名/input-clean.wav --tier 3 --mix 0.8
  • 脚本会打印实际运行的 ffmpeg 命令(透明执行)。
  • 视频输入自动 -c:v copy:只处理音轨,视频轨原样保留。

4. 验证输出 + 报告

脚本处理完自动打印输出文件的时长/码率/声道/采样率。如需完整对比:

bash
python skills/shared/scripts/audio_ops.py info outputs/主题名/input-clean.wav

报告内容:原始 vs 输出(格式/时长/大小/采样率)、所用 tier 与滤镜链、大小变化。

规则

  1. 绝不删除原始文件 — 即使用户未指定 preserve_original
  2. 先探测再处理 — 始终先 info 展示文件信息。
  3. 视频输入只动音频 — 脚本自动 -c:v copy
  4. 透明执行 — 脚本打印实际 ffmpeg 命令。
  5. 降噪过度时 — 建议降低 tier 或 --mix(如 0.8→0.5)。
  6. 无 Profile 依赖 — 音频处理不需要账号画像。

自研参考

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Audio Denoise AI skill do?

音频降噪:去除录音中的背景噪声、电流声、风噪、嗡嗡声,基于 ffmpeg 滤镜链(afftdn/highpass/lowpass)。 当用户说"降噪""去噪""去杂音""消除背景噪声""电流声""风噪""录音有杂音""音频降噪"时使用。 和 audio-editing 的区别:audio-editing 做剪辑/转码/音量等通用音频操作(内置 denoise 兜底),本 SKILL 专做降噪调参。

Why use Audio Denoise on TypingMind?

Because you install it once and use it with any model. Audio Denoise is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Audio Denoise in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ZJU-REAL/Easel/tree/main/skills/openclaw/audio-denoise. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Audio Denoise?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Audio Denoise?

As many as you like. As long as a model supports skills, you can use Audio Denoise with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Audio Denoise AI skill free?

Yes. It is published on GitHub by ZJU-REAL under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇