# yxlllc/DDSP-SVC

Real-time end-to-end singing voice conversion system based on DDSP (Differentiable Digital Signal Processing)

Repository: https://github.com/yxlllc/DDSP-SVC
Canonical: https://ross.abutalabs.com/products/ddsp-svc
Language: Python
License: MIT
License Family: permissive
Topics: pytorch
Last push: 2026-08-12T05:33:39+00:00

## Health v2 (maintenance only)
Score: 65/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 97, release rhythm 8, longevity 91
- inputs: {"age_days": 1278, "days_push": 21, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2656, forks 285 (observed 2026-08-28T04:07:07.298356+00:00)

## What it is
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
- artifact type: application
- maturity: active
- function: audio-processing, speech-recognition, machine-learning, deep-learning
- domain: machine-learning, artificial-intelligence
- platform: python, cross-platform, windows
- tags: singing-voice-conversion, voice-changer, ddsp, real-time, diffusion-model, pytorch, audio, linux, macos, gpu

## Member repositories
- yxlllc/DDSP-SVC (main) score 65

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:07.298356+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:18:29.500712+00:00, confidence not recorded.
  - readme: https://github.com/yxlllc/DDSP-SVC (fetched 2026-08-28T04:07:07.298356+00:00, sha 55ed79288126)
- Data as of 2026-08-30T08:39:29.467469+00:00.