jacob7choi-xyz/harmonyrestorer-v1
Audio restoration platform implementing 1D Operational GANs (Kiranyaz et al. 2022) for blind denoising of degraded recordings. Production API uses UVR for source separation; experimental OpGAN pipeline for analog noise removal. Full-stack: FastAPI, React, Docker.
This tool helps podcasters, musicians, or anyone working with audio clean up noisy recordings quickly. You upload an audio file (like a voiceover, instrument track, or old recording) and get back a much clearer version, free from common background noise. It's designed for individuals who need to improve the quality of their audio without complex software.
Use this if you have audio recordings with unwanted background noise (like hiss, hum, or static) and need a simple way to get a clean, professional-sounding result.
Not ideal if you need to separate individual instruments or vocals from a full song, as its primary function is blind denoising rather than source separation.
Stars
9
Forks
1
Language
Python
License
MIT
Category
Last pushed
Mar 12, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/jacob7choi-xyz/harmonyrestorer-v1"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.