sergree/matchering

🎚️ Open Source Audio Matching and Mastering

What it solves

Matchering provides an automated way to master audio tracks by matching a target track's characteristics to those of a reference track. This eliminates the need for manual mastering engineers for basic audio polishing and ensures consistency across an album or makes a music track sound like a specific artist's style.

How it works

The tool takes two audio files: a target track (the one to be mastered) and a reference track (a professionally mastered song). The algorithm then analyzes and matches the target track's RMS (Root Mean Square), frequency response, peak amplitude, and stereo width to match the reference track.

Who it’s for

  • Music Producers and Audio Engineers: Those looking for a quick way to achieve professional sound characteristics.
  • AI Mastering Startups: Developers who can deploy the project as a containerized web application via Docker.
  • Developers: Those who want to integrate audio matching and mastering capabilities into Python applications.

Highlights

  • Multiple Deployment Options: Available as a Python library, a Docker image, containerized web app, and a ComfyUI node.
  • Integrated in UVR5: Now part of the Ultimate Vocal Remover 5 desktop application.
  • Open Source Stack: Completely rewritten in Python 3, replacing previous MATLAB versions.
  • Custom Limiter: Includes the open-source Hyrax brickwall limiter for final audio processing.

Related

  • Project
    Zafer-Liu/Data-Analysis-Agent

    Data‑Analysis‑Agent is a Flask‑based AI agent that turns natural‑language questions into SQL queries, runs them on uploaded files or connected databases, auto‑generates Plotly visualisations, and returns business insights. It works with any OpenAI‑compatible LLM, supports many chart types, and offers Windows installers, cross‑platform zip, or script‑based installation.

  • Project
    apache/hamilton

    Apache Hamilton is an incubating Apache project that lets you write ordinary Python functions whose arguments declare data dependencies. Hamilton automatically builds a portable DAG of those transformations, validates outputs, and can visualise or track runs via a web UI. It’s designed for data‑centric workloads—ETL, ML pipelines, LLM/RAG systems—while staying infrastructure‑agnostic (works in notebooks, scripts, Airflow, FastAPI, etc.). Install with `pip install "apache-hamilton[visualization]"` (or add `ui,sdk` for the UI). Licensed under Apache 2.0 and backed by an active open‑source community.

  • Project
    dzhng/jevgrep

    jevgrep is a Node‑based CLI that lets AI coding agents locate relevant source files and snippets by asking natural‑language questions about a repository. It sends filtered code to a Jev‑compatible LLM endpoint, returns concise file lists and code excerpts, and has been shown to cut coding‑agent inference cost by about 30 % while maintaining the same task‑success rate.

  • Project
    papersgpt/papersgpt-for-zotero

    PapersGPT is a native C++ Zotero plug‑in that indexes thousands of PDFs locally and lets you query them with offline LLMs. It offers millisecond‑fast retrieval, cross‑paper synthesis with clickable citations, and an AutoPilot mode for batch processing, all without sending data to the cloud.