Matchering
Open-source Python library and web app for audio mastering by matching a target track’s RMS, FR, peak and stereo width to a reference track.
Smart Download
Visit Project Homepage
No installer available yet — head to the source repository
Open-source audio mastering that makes any track sound like your reference, locally and free.
Core Features
- Matches RMS, frequency response, peak amplitude, stereo width
- Available as Python library, Docker image, ComfyUI node
- Integrated in UVR5 desktop app – zero coding needed
- Fully open-source, runs locally, no cloud upload
- Uses custom Hyrax brickwall limiter for high quality
What It Can't Do
- •Requires 4GB RAM and Python 3.8+,Linux needs libsndfile1 installed separately,MP3 loading requires FFmpeg,Reference track choice greatly affects output quality
Use Cases
- Quickly master your song to sound like a hit reference
- Unify the mastering of an entire album
- Build AI mastering service backend
- Experiment with different reference tracks for creative ideas
Matchering 2.0 is a novel Containerized Web Application, Python Library, and ComfyUI Node for audio matching and mastering. It takes two audio files: TARGET (the track you want to master) and REFERENCE (a reference track). The algorithm adjusts the target’s RMS, frequency response, peak amplitude, and stereo width to match the reference, making it sound like the reference. It has been reviewed by Benn Jordan and ranked #3 out of 12 (behind two professional master engineers). The library is fully open-source, runs locally (no cloud uploads), and is integrated into UVR5 Desktop App, Songmastr, MVSEP, and Moises. It uses a brickwall limiter (Hyrax) and supports PCM16/24 output, MP3 loading via FFmpeg, and easy Docker deployment.
Tags
Getting Started
Download installer
Click the button above to download the installer for your system
Install the software
Double-click the downloaded installer and follow the prompts
Desktop: Open UVR5 app, choose Audio Tools > Matchering, select target and reference, click process.
Developer: pip install -U matchering, then run: mg.process(target='my_song.wav', reference='ref.wav', results=[mg.pcm16('out.wav')])
Docker: Follow platform-specific Docker guide from docs, start container and use web UI.
- Desktop: Open UVR5 app, choose Audio Tools > Matchering, select target and reference, click process.
- Developer: pip install -U matchering, then run: mg.process(target='my_song.wav', reference='ref.wav', results=[mg.pcm16('out.wav')])
- Docker: Follow platform-specific Docker guide from docs, start container and use web UI.
Checksum not available
This project has not published a SHA-256 checksum on its GitHub Release page
SHA256 Checksum
No checksum available
Download directly from GitHub Releases and verify file integrity yourself
All SHA-256 checksums on this platform are extracted from the project's official GitHub Release page, without any modification. You can independently verify them on the GitHub Releases page.
Open Source Transparency
View GitHub SourceUninstall Info
Python lib: pip uninstall matchering; Docker: docker rm and rmi; UVR5 integration: uninstall UVR5.
No Extra Dependencies
Ready to use after download. No additional runtime required.
Having issues? Check the FAQ below
3 FAQs
Similar Projects
ollama
Ollama lets you download, run, and manage large language models locally. One command, multiple platforms, endless possibilities.
llama.cpp
High-performance LLM inference engine in C/C++ with minimal dependencies, supporting quantized models (1.5–8 bit) and diverse hardware (Apple Silicon, CUDA, Vulkan, etc.).
opencv
OpenCV is an open-source computer vision and machine learning library with over 2500 optimized algorithms for real-time image and video analysis.