so-vits-svc-fork and so-vits-svc
About so-vits-svc-fork
voicepaw/so-vits-svc-fork
so-vits-svc fork with realtime support, improved interface and more features.
This tool helps musicians, content creators, and performers transform their singing or speaking voice in real-time or from audio files. You provide your voice (live through a microphone or a pre-recorded WAV file) and a pre-trained voice model, and it outputs your performance with the characteristics of the chosen voice. It's designed for anyone looking to alter their vocal identity for creative projects.
About so-vits-svc
svc-develop-team/so-vits-svc
SoftVC VITS Singing Voice Conversion
Uses a SoftVC content encoder to extract speech features directly from audio, feeding them into VITS while preserving pitch and intonation without text-based intermediate representations. Replaces the vocoder with NSF HiFiGAN to eliminate sound artifacts, and supports multiple encoders including ContentVec and Whisper-PPG. Includes shallow diffusion refinement, feature retrieval integration with RVC, and loudness embedding for enhanced voice conversion quality.
Scores updated daily from GitHub, PyPI, and npm data. How scores work