ComfyUI-OmniVoice-TTS tested by Argusic Runner

What the test found

5 OmniVoice TTS ComfyUI nodes (Longform TTS, Voice Clone, Voice Design, Multi-Speaker, Whisper Loader) installed and registered; OmniVoice-bf16 model loads from HuggingFace cache, generates valid 24kHz audio waveform from text on CPU in ~9 seconds for 2-second utterance

All 5 ComfyUI nodes registered successfully. Model auto-downloaded from HuggingFace (drbaph/OmniVoice-bf16, 2GB). Audio generated, saved as WAV, and verified valid via ffmpeg decode. No GPU available - ran on CPU.

Argusic installed ComfyUI-OmniVoice-TTS in 5 minutes and launched it; verification reached Verified running for real. 7 of 7 recorded errors were worked through (see the timeline below).

Runsall runs of ComfyUI-OmniVoice-TTS

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.