voicepaw/so-vits-svc-fork
so-vits-svc fork with realtime support, improved interface and more features.
Implements SoftVC VITS architecture with ContentVec feature extraction and CREPE pitch estimation for improved accuracy, while supporting real-time inference directly from microphone input via CLI and GUI. Bundles pre-trained models with automatic downloads, eliminating fairseq dependencies and reducing setup friction. Compatible with original so-vits-svc 4.0/4.1 model checkpoints and available as a PyPI package with GPU acceleration for CUDA and ROCm backends.
9,281 stars and 4,743 monthly downloads. Used by 1 other package. Actively maintained with 22 commits in the last 30 days. Available on PyPI.
Stars
9,281
Forks
1,236
Language
Python
License
—
Category
Last pushed
Mar 13, 2026
Monthly downloads
4,743
Commits (30d)
22
Dependencies
25
Reverse dependents
1
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/voicepaw/so-vits-svc-fork"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
ssmall256/mlx-audio-io
Native audio I/O for MLX on macOS and Linux
ssmall256/mlx-spectro
High-performance STFT/iSTFT for Apple MLX with fused Metal kernels and autograd support
sarulab-speech/UTMOSv2
UTokyo-SaruLab MOS Prediction System
daniilrobnikov/vits
VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
MWM-io/SpecTNT-pytorch
Unofficial implementation of SpecTNT in pytorch