jxzhanggg/nonparaSeq2seqVC_code

Implementation code of non-parallel sequence-to-sequence VC

48
/ 100
Emerging

This project provides the underlying code for advanced voice conversion, allowing you to change a speaker's voice in an audio recording while preserving the speech content. You input an audio recording (or text) and specify a target voice, and the system outputs a new audio recording with the speech spoken in the target voice. This is primarily for researchers and engineers working in speech synthesis, voice cloning, or audio production.

248 stars. No commits in the last 6 months.

Use this if you need to perform high-quality voice conversion or text-to-speech synthesis using disentangled linguistic and speaker representations.

Not ideal if you're looking for an off-the-shelf, easy-to-use application for voice conversion without needing to delve into model training or data preparation.

voice-conversion speech-synthesis audio-research voice-cloning audio-engineering
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

248

Forks

56

Language

Python

License

MIT

Last pushed

Mar 24, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/jxzhanggg/nonparaSeq2seqVC_code"

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