WelkinYang/Learn2Sing2.0

Diffusion and Mutual Information-Based Target Speaker SVS by Learning from Singing Teacher

35
/ 100
Emerging

This tool helps you create a high-quality singing voice for a specific person, even if they're not a good singer and you don't have their singing recordings. You provide spoken audio from the target person and singing audio from a 'singing teacher,' and it generates the target person's voice singing the teacher's song. This is ideal for voice artists, content creators, or anyone needing custom singing voices.

181 stars. No commits in the last 6 months.

Use this if you need to generate a specific person's singing voice but only have their speaking voice and want to learn the singing style from another singer.

Not ideal if you already have extensive singing data for the target person or primarily need to modify existing singing performances.

voice-synthesis audio-production content-creation vocal-performance voice-acting
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 17 / 25

How are scores calculated?

Stars

181

Forks

26

Language

JavaScript

License

Last pushed

Apr 28, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/WelkinYang/Learn2Sing2.0"

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