media-denoise-ai

Community

Open-source AI denoise for clean audio.

Authordamionrashford
Version1.0.0
Installs0

System Documentation

What problem does it solve?

AI-powered audio denoising and restoration that goes beyond built-in FFmpeg filters, delivering cleaner voice, reduced hum and hiss, and improved intelligibility across speech recordings.

Core Features & Use Cases

  • Open-backend options include DeepFilterNet for real-time full-band speech denoise, RNNoise via ffmpeg arnndn for quick cleanups, and Resemble Enhance for full restoration (denoise + dereverb + bandwidth extension).
  • Use cases span podcasts, interviews, meeting recordings, archival audio restoration, and pre-processing for ASR/TTs workflows, with support for single-file or batch processing.
  • Flexible deployment: mirror directory structures when processing folders and mix backends to fit production pipelines.

Quick Start

Denoise a noisy audio file using the default DeepFilterNet model to produce a clean output.

Dependency Matrix

Required Modules

deepfilternetsoundfiletorchresemble_enhance

Components

scriptsreferences

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: media-denoise-ai
Download link: https://github.com/damionrashford/media-os/archive/main.zip#media-denoise-ai

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.