ComfyUI-VoxCPM tested by Argusic Runner

What the test found

ComfyUI-VoxCPM v2.4.0 loads in ComfyUI 0.42.0 on CPU; all 6 custom nodes registered under audio/tts categories; test suite runs 61/62 passing; ComfyUI server starts and responds on --cpu flag; frontend JS extension served; model scanning, settings, validation, and configuration types all verified standalone

Real model inference requires downloading 1.6-8GB VoxCPM models (openbmb/VoxCPM2, openbmb/VoxCPM1.5) and a GPU with CUDA — neither available in this container. All node registration, API routes, config management, settings persistence, model scanning/discovery, dataset creation, dtype/device utilities, and validation logic are verified with mocks.

Argusic installed ComfyUI-VoxCPM in 28 minutes and launched it; verification reached Verified with mock services. 3 of 3 recorded errors were worked through (see the timeline below).

Runs with mocksall runs of ComfyUI-VoxCPM

This summary is drawn from the agent's recorded report for this run. Every figure traces to the log and recording above; nothing here is authored.