Repository files navigation

Loved Matchering?

Check out.masterknecht - free WebAssembly reference mastering tool byBenjamin Rosseaux!

Massive props! 🚀

Note:.masterknecht is not related to Matchering's source code at all. It's a completely separate tool written in C and compiled to WebAssembly, which processes all audio locally in your browser without the need for any servers!

— Sergree

Matchering 2.0 is a novelContainerized Web Application,Python Library, andComfyUI Node for audio matching andmastering.

🔥 Also integrated in theUVR5 Desktop App!

It follows asimple idea - you take TWO audio files and feed them intoMatchering:

• TARGET (the track you want to master, you want it to sound like the reference)
• REFERENCE (another track, like some kind of "wet" popular song, you want your target to sound like it)

Our algorithm matches both of these tracks and provides you the masteredTARGET track with the sameRMS,FR,peak amplitude andstereo width as theREFERENCE track has.

🔥Benn Jordan Matchering review:

• Matchering 2.0 beating all other AI's! (note: by carefully selecting a proper song as reference)
• Ranking it no.3 (out of 12) right behind 2 professional master engineers
• Seems a rock-solid study with 472 judged entries

(Thanks to@bascurtiz forthe find)

You can try outMatchering yourself without having to install it, thanks to the hosting provided bySongmastr andMoises.

Watchthe video:

SoMatchering 2.0 will make your song sound the way you want! It opens up a wide range of opportunities:

• You can make your music instantly sound like your favorite artist's music
• You can make all the tracks on your new album sound the same very quickly
• You can find new aspects of your sound in experiments
• You can do everything as you want! Because ofYour References, Your Rules.™(just a little nostalgic note) 🤭

Differences from the previous major version:

• Completely rewritten inPython 3, based on open source tech stack (no moreMATLAB)
• Our own open sourceHyraxbrickwall limiter was implemented for it
• Processing speed and accuracy have been increased
• Now it isthe library that can be connected toeverything inthe Python world

If you are looking for aMatchering paper, you can readthis Habr article.

If you are a music producer or an audio engineer, choose theDesktop App orComfyUI Node.

If you are an AI mastering startup, choose theDocker Image.

If you are a developer, choose thePython Library.

You can find Matchering underChoose Process Method > Audio Tools & Choose Audio Tool > Matchering.

If you need to update the version of the installedDocker Image, followthese instructions.

4 GB RAM machine withPython 3.8.0 or higher is required

Matchering 2.0 depends on theSoundFile library, which depends on the system librarylibsndfile. On Windows and macOS, it installs automatically. On Linux, you need to installlibsndfile using your distribution's package manager, for example:

sudo apt update && sudo apt -y install libsndfile1

On some Linux distributions,python3-pip is not installed by default. For example use this command on Ubuntu Linux to fix this:

sudo apt -y install python3-pip

Finally, install ourmatchering package:

# Linux / macOSpython3 -m pip install -U matchering# Windowspython -m pip install -U matchering

If you would like to enableMP3 loading support, you need to install theFFmpeg library. For example use this command on Ubuntu Linux:

sudo apt -y install ffmpeg

Or follow these instructions:Windows,macOS.

importmatcheringasmg# Sending all log messages to the default print function# Just delete the following line to work silentlymg.log(print)mg.process(# The track you want to mastertarget="my_song.wav",# Some "wet" reference trackreference="some_popular_song.wav",# Where and how to save your resultsresults=[mg.pcm16("my_song_master_16bit.wav"),mg.pcm24("my_song_master_24bit.wav"),    ],)

You can find more examples in theexamples directory.

Looking for the perfect BPM or key for a new EDM track?

Check out WhatBPM!

A completely free open-source web service from the author of Matchering.

If our package saved your time or money, you may:

Thank you!

• Press About Us
• Supporters
• Our Limiter Quality Test
• Matchering Hyrax Limiter JSFX clone by Tokyo Dawn Labs
• Log Codes Overview
• Our Thoughts