Our take
- Activity
- 19
- Community
- 21
- Issues
- 21
- Pull requests
- 20
+2 stars in the last 30 days
Project history
Daily GitHub snapshots since Oct 7, 2026. History covers stars and forks; health signals are not tracked historically.
Stars
732Forks
54Change since Nov 16, 2026: 0 stars·0 forks
Overview
Fast Music Remover is a media-processing tool for reducing background music and noise in audio from video or audio files. It is intended for people who want to make speech easier to hear while keeping the original media content.
The project pairs a C++ processor with a Flask backend and a web interface. You can submit a media URL or upload a local file, then play back the processed result. It may suit users who want a self-hosted workflow rather than a standalone desktop editor.
Key Features
- Filters background music from media audio using DeepFilterNet for audio enhancement.
- Provides noise removal to improve audio quality.
- Accepts uploaded audio or video files and media URLs through its web interface.
- Returns processed media for playback in the browser.
- Uses a C++
MediaProcessorwith a Flask backend. - Offers a prebuilt Docker image as well as a manual setup path.
Use Cases
- Viewers can reduce background music in online videos when they want to focus on speech or other core audio.
- Researchers and students can make interview or lecture audio easier to listen to by reducing noise and music.
- Developers can use the C++ processor and its APIs as a starting point for media-processing workflows.
- Self-hosters can try the web interface locally with Docker instead of configuring each dependency by hand.
Getting Started
With Docker installed, start the prebuilt image:
docker run -p 8080:8080 ghcr.io/omeryusufyagci/fast-music-remover:latest
Then open http://localhost:8080. For manual installation and dependency details, see the README.
Considerations
- The manual setup requires Python 3.9 or later, FFmpeg, CMake, nlohmann-json, and libsndfile, in addition to compiling the C++ processor.
- The README describes cross-platform support as a roadmap priority, so do not assume all platforms are already equally supported.
- Realtime processing and additional models are described as planned or experimental work, not established capabilities.
- Results depend on the source media and processing. The repository does not promise complete separation of speech, music, and noise.
- The project was last pushed on 2025-01-15, according to the provided repository metadata.
Found this useful?
Share it with someone who would like fast-music-remover.