Rongjiehuang/Multi-Singer

PyTorch Implementation of Multi-Singer (ACM-MM'21)

42
/ 100
Emerging

This project helps music producers, sound engineers, and content creators generate realistic singing voices. It takes raw audio recordings of singing and converts them into high-quality, synthetic singing waveforms. The output can be customized to sound like different singers, making it useful for creating demos, vocal tracks, or even entirely new vocal performances.

139 stars. No commits in the last 6 months.

Use this if you need to create synthetic singing voices from audio inputs, especially if you want flexibility in the vocal characteristics.

Not ideal if you're looking for a tool to analyze existing vocal performances or enhance natural singing recordings without synthesizing new audio.

music-production vocal-synthesis audio-engineering sound-design content-creation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

139

Forks

20

Language

Python

License

MIT

Last pushed

May 08, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/Rongjiehuang/Multi-Singer"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.