- Home
- AI Voice Changer Software
- DDSP-SVC
On the recordRead 9 Oct 202612 facts
DDSP-SVC
Plans and prices
Free
Free
Personal computer software · Requires local Python dependencies and pretrained model assets
Read 9 Oct 2026 · github.com
On the record
- Data and legal use
- The author asks users to train only with legally obtained authorized data and not use models or generated audio for illegal purposes.github.com · read 9 Oct 2026
- Dataset guidance
- The project recommends about 1,000 training clips and about 10 validation clips, with each audio clip at least two seconds long.github.com · read 9 Oct 2026
- Hardware and setup
- The README says its default configuration suits 44.1 kHz training with an RTX 4060 and reports a working Python 3.11, Windows, CUDA 13.0, PyTorch 2.9.1, and torchaudio 2.9.1 setup.github.com · read 9 Oct 2026
- Integrations
- The README recommends installing PyTorch and documents TensorBoard for viewing training status and generated test audio.github.com · read 9 Oct 2026
- Intended users
- The project describes its goal as developing free AI voice-changer software that can be used on personal computers.github.com · read 9 Oct 2026
- Local processing
- The README describes installing dependencies and running the conversion GUI locally with Python.github.com · read 9 Oct 2026
- Model components
- The setup instructions support ContentVec or HubertSoft encoders, an NSF-HiFiGAN vocoder, and the RMVPE pitch extractor.github.com · read 9 Oct 2026
- Model training
- The project documents preprocessing audio datasets and training a model with a rectified-flow script.github.com · read 9 Oct 2026
- Multi-speaker support
- Training supports multi-speaker models configured with a speaker count and speaker-numbered audio folders.github.com · read 9 Oct 2026
- Offline conversion
- The command-line interface converts an input WAV file to an output WAV file and accepts pitch-shift and speaker options.github.com · read 9 Oct 2026
- Real-time conversion
- Its real-time interface uses sliding windows, cross-fading, SOLA-based splicing, and contextual semantic reference.github.com · read 9 Oct 2026
- What it does
- DDSP-SVC is an open-source project for real-time singing voice conversion.github.com · read 9 Oct 2026
