mbrotos/SoundSeg
Spectral Mapping of Singing Voices: U-Net-Assisted Vocal Segmentation
This tool helps music producers, audio engineers, and sound designers isolate vocals from full songs. You input an audio file containing a song, and it outputs the separated vocal track, allowing you to easily work with or remix the singing without background music. It's designed for anyone needing clean vocal stems for their projects.
Use this if you need to extract the singing voice from a mixed audio track with high precision.
Not ideal if you need to separate other instruments or sounds beyond just the vocals.
Stars
13
Forks
—
Language
Jupyter Notebook
License
—
Category
Last pushed
Feb 18, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/mbrotos/SoundSeg"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
lucidrains/HS-TasNet
Implementation of HS-TasNet, "Real-time Low-latency Music Source Separation using Hybrid...
justinsalamon/scaper
A library for soundscape synthesis and augmentation
stemrollerapp/stemroller
Isolate vocals, drums, bass, and other instrumental stems from any song
thepirat000/spleeter-api
Audio separation API using Spleeter from Deezer
tsurumeso/vocal-remover
Vocal Remover using Deep Neural Networks