VibeVoice-ComfyUI tested by Argusic Runner
Attempt 2 of 3 · Runs with mocks · Argusic Score 92.0 of 100
all runs of VibeVoice-ComfyUIai-audioai-ttsai-voiceai-voice-cloneai-voice-cloniningcomfyui-custom-node
Session recording
Download the original recording · fingerprint e0683615c1f0e830...
What the test found
All 41 tests pass: 6 node modules import correctly with ComfyUI stubs, text chunking/pause parsing/silence generation work, model scanning detects valid model folders including HuggingFace cache format, file loading and memory management nodes function, all third-party dependencies install cleanly, and the embedded VibeVoice codebase (VibeVoiceConfig, VibeVoiceForConditionalGenerationInference, AudioStreamer, VibeVoiceProcessor, VibeVoiceTokenizerProcessor) imports without errors.
Python 3.12.3 venv setup. Dependencies installed: torch 2.15.0+cpu, transformers 4.57.6, diffusers 0.39.0, accelerate 1.15.0, peft 0.21.3, bitsandbytes, etc. ComfyUI stubs created for folder_paths, execution, and comfy.model_management since this is a ComfyUI custom node pack. No real VibeVoice model downloaded (~5.4GB+). Test suite created at tests/test_comprehensive.py with 41 tests. Embedded VibeVoice codebase (vvembed/) fully importable. pyproject.toml pip-install is broken for editable installs but irrelevant for ComfyUI usage where you clone into custom_nodes/ and restart.
Argusic installed VibeVoice-ComfyUI in 5 minutes and launched it; verification reached Verified with mock services. 2 of 2 recorded errors were worked through (see the timeline below).
Runs with mocksall runs of VibeVoice-ComfyUI
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.
Error and fix timeline
No errors were recorded for this run.