Troubleshooting¶
Installation¶
Errors that show up while setting up VTC, before you've run it on any audio.
| Error | Fix |
|---|---|
python3.13: command not found |
Install via pyenv: pyenv install 3.13 |
uv: command not found |
curl -LsSf https://astral.sh/uv/install.sh \| sh, then restart your terminal |
ffmpeg: command not found |
sudo apt install ffmpeg (Linux) or brew install ffmpeg (macOS) |
Model weights missing / empty VTC-2/ dir |
git lfs install && git submodule update --init --recursive |
uv sync fails |
Ensure you're inside VTC/ and using Python 3.13+ |
Runtime¶
Errors that show up while VTC is processing your audio.
| Error | Fix |
|---|---|
CUDA out of memory |
Reduce batch size, or use --device cpu |
No CUDA GPUs are available |
Use --device cpu or install CUDA drivers |
No .wav files found |
VTC only reads .wav — convert other formats first (see Getting Started) |
| Empty output files | Check audio format (ffprobe file.wav — should be 16 kHz, mono) and verify model weights are present |
Still stuck?¶
If neither table above helped, please report the issue so it can be diagnosed.
Open an issue on GitHub including:
- your operating system,
- the Python version (
uv run python --version), - the exact command you ran, and
- the full error message (copy and paste, don't paraphrase).