hayeong0/Diff-HierVC

Official Pytorch Implementation of "Diff-HierVC: Diffusion-based Hierarchical Voice Conversion with Robust Pitch Generation and Masked Prior for Zero-shot Speaker Adaptation"

31
/ 100
Emerging

This tool helps convert speech from one speaker's voice to another while maintaining the original spoken content. You provide an audio recording of someone speaking and a sample of a target voice, and it generates a new audio recording where the original speech is spoken in the target voice. This is useful for content creators, game developers, or anyone needing to generate speech in various voices without re-recording.

235 stars. No commits in the last 6 months.

Use this if you need to transform spoken audio to sound like a different person, even if you only have a short sample of the target voice.

Not ideal if you need to create speech from text or are looking for highly customized voice modulation beyond speaker style transfer.

voice conversion audio production dubbing content creation speech synthesis
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 13 / 25

How are scores calculated?

Stars

235

Forks

19

Language

Python

License

Last pushed

Jul 03, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/hayeong0/Diff-HierVC"

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