lucidrains/HS-TasNet
Implementation of HS-TasNet, "Real-time Low-latency Music Source Separation using Hybrid Spectrogram-TasNet"
This tool helps audio engineers, music producers, and sound designers separate individual instruments or vocals from mixed music tracks in real-time. You input a stereo audio recording, and it outputs the isolated audio streams for drums, bass, vocals, and 'other' instruments. It's ideal for anyone needing to isolate components of a song for remixing, analysis, or live performance adjustments.
Available on PyPI.
Use this if you need to quickly and efficiently isolate different sound sources within a live or pre-recorded music track.
Not ideal if you need to separate extremely niche or non-standard sound sources beyond common instruments and vocals.
Stars
86
Forks
15
Language
Python
License
MIT
Category
Last pushed
Mar 25, 2026
Monthly downloads
342
Commits (30d)
0
Dependencies
13
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/lucidrains/HS-TasNet"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
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
gitmylo/audio-webui
A webui for different audio related Neural Networks