seahore/PPG-GradVC

A diffusion-based cross-lingual voice conversion model, as my bachelor's thesis

29
/ 100
Experimental

This project helps convert a person's voice into different voices while keeping the original speech content. You provide an audio recording and it generates new audio that sounds like a different speaker, potentially in another language. This is useful for anyone working with audio content who needs to change the speaker's identity or language without re-recording.

No commits in the last 6 months.

Use this if you need to transform the voice in an audio file to sound like someone else, possibly across different languages, without altering the spoken words.

Not ideal if you are looking for a tool to transcribe audio to text, translate spoken content, or synthesize speech from text.

voice-conversion audio-localization speech-synthesis multilingual-audio media-production
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 13 / 25

How are scores calculated?

Stars

44

Forks

6

Language

Python

License

Last pushed

Jul 24, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/seahore/PPG-GradVC"

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