yxlllc/DDSP-SVC

Health v2 · maintenance only

Adoption not part of the score

2656 stars · 285 forks observed · 2026-08-28

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

DDSP-SVC is an open-source singing voice conversion system built on Differentiable Digital Signal Processing, designed as a free AI voice changer for personal computers. It offers low hardware requirements and fast training compared to alternatives like SO-VITS-SVC, with quality enhanced via diffusion or rectified-flow models.

Use cases

• convert my singing voice to another voice in real time
• train a singing voice conversion model on my own dataset
• run an AI voice changer on a low-end PC
• clone a singing voice from audio samples
• do real-time voice changing during streaming or calls
• compare DDSP-SVC with RVC and so-vits-svc for voice conversion

When to choose

• you need real-time voice changing with lower hardware cost than SO-VITS-SVC
• you want fast model training on consumer hardware
• you need high-quality singing voice conversion enhanced with diffusion or rectified flow
• you want an open-source, MIT-licensed SVC solution

When to avoid

• you only need simple speech-to-speech conversion rather than singing voice conversion
• you have no GPU and cannot meet the PyTorch/CUDA requirements
• you cannot legally obtain authorized training data
• you need a plug-and-play GUI tool with no configuration

Facets

application · maturity active

audio-processing speech-recognition machine-learning deep-learning machine-learning artificial-intelligence python cross-platform windows singing-voice-conversion voice-changer ddsp real-time diffusion-model pytorch audio linux macos gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="yxlllc/DDSP-SVC")