Diff-SVC

What it does

Attribution

The maker asks users who redistribute the code or publicly publish results to credit the original author and repository.checked 9 Oct 2026

Audio formats

The training guide says data preparation supports WAV and Ogg audio.checked 9 Oct 2026

Audio sample rates

The README records support for 44.1 kHz audio.checked 9 Oct 2026

Custom datasets

The project supports training on custom datasets.checked 9 Oct 2026

Dependencies

The README credits DiffSinger, the OpenVPI-maintained DiffSinger version, and Soft-VC as project bases.checked 9 Oct 2026

Inference

Inference is available through the included inference.ipynb notebook or infer.py script.checked 9 Oct 2026

Integrations

The maker identifies DiffSinger, the OpenVPI-maintained DiffSinger version, and soft-vc as project foundations.checked 9 Oct 2026

Intended use

The project says it is for academic exchange and is not intended for production environments.checked 9 Oct 2026

License

The repository identifies its license as AGPL-3.0.checked 9 Oct 2026

Long audio

Inference automatically slices audio longer than 30 seconds at silences.checked 9 Oct 2026

Maintenance

The project is no longer actively maintained, and its README describes it as an early exploration of diffusion models for singing voice conversion.checked 9 Oct 2026

Method

The project describes itself as singing voice conversion via diffusion models.checked 9 Oct 2026

Performance

The guide says full inference can run on a 6 GB GTX 1060 GPU.checked 9 Oct 2026

Purpose

Diff-SVC converts input singing voices into a target timbre and supports basic pitch correction.checked 9 Oct 2026

Real-time conversion

The README mentions support files for real-time voice conversion inference.checked 9 Oct 2026

Redistribution

The README asks users who redistribute the code or publicly publish results to credit the original author and repository.checked 9 Oct 2026

Security

The repository page displays no reported security advisories in its Security and quality section.checked 9 Oct 2026

Support

The README points users to a Discord for English support.checked 9 Oct 2026

Training

The README provides a command to train a model using a configuration file and a user-supplied experiment name.checked 9 Oct 2026

Training data

The guide supports single-speaker training and recommends at least three hours of target-speaker dry vocals.checked 9 Oct 2026