PlayVoice/whisper-vits-svc

Health v2 · maintenance only

Adoption not part of the score

2864 stars · 907 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A PyTorch-based singing voice conversion and voice cloning engine built on VITS with Whisper, BigVGAN, and diffusion components. It lets users train multi-speaker SVC models and convert singing voices, including with light accompaniment.

Use cases

• convert a singing voice to another singer's timbre
• clone a singing voice from audio samples
• train a so-vits-svc model on my own dataset
• change the voice of a song while keeping the accompaniment
• create a multi-speaker singing voice conversion model
• edit pitch (F0) of converted singing audio

When to choose

• you want to train or fine-tune a singing voice conversion model in Python/PyTorch
• you need multi-speaker SVC or one-shot voice cloning
• you have a GPU with at least 6GB VRAM and want an open-source SVC engine

When to avoid

• you need real-time voice conversion
• you want a one-click GUI package with no coding
• you need active development or new features - the project is no longer upgraded

Facets

library · maturity maintenance

machine-learning deep-learning audio-processing speech-recognition tts deep-learning machine-learning artificial-intelligence python cross-platform singing-voice-conversion voice-cloning so-vits-svc vits diffusion whisper bigvgan pytorch audio gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="PlayVoice/whisper-vits-svc")