dsh-soundtry CixiSVesper

Local audio understanding for DeepSeek Harness: transcription (whisper medium), rhythm, melody, chords, structure - six tools, fully offline. Needs a Python 3.10-3.12: point DSH at an existing environment (e.g. ComfyUI), or let the plugin create and install its own. Vocal separation runs UVR MDX-Net on onnxruntime, so torch is not required.