SoftVC VITS Singing Voice Conversion

Easily train a good VC model with voice data <= 10 mins!

so-vits-svc fork with realtime support, improved interface and more features.

Just a fork of RVC for easy audio file voice conversion locally

So-VITS-SVC 本地部署/训练/推理/使用帮助文档 So-VITS-SVC Local Deployment/Training/Inference/Usage Help Document

收集有关so-vits-svc、TTS、SD、LLMs的各种模型、应用以及文字、声音、图片、视频有关的model。

🌻 VITS ONNX TTS server designed for fast inference 🔥

Follow the rapid development of AIGC models and applications. | 跟上AIGC模型和应用快速发展的步伐 🚀

A small VITS+SOVITS/RVC TTS API

Make Kanye sing any song ya want 🎤🔥

Cover Song Powered by SoftVC VITS

整理测试so-vits4.0模型效果（模型来自网络）

run voice model (so-vits-svc-4.0) of "Serial Experiments Lain" on Windows

Python scripts for AI voice changers

Change the voice of audios using pre-trained streamer voice models using AI.

VI-SVC model is just VITS without MAS and DurationPredictor.

Training and Inference with simple tools to help you

so-vits-svs 4.0 v1训练的Kasugano Sora模型

improved version of so-vits-svc-fork by 34j

A python CLI pipeline script for running UVR tasks, SO-VITS-SVC model inference and ffmpeg merge with end-to-end automation.