MOSS-TTS-Nano tested by Argusic Runner

What the test found

MOSS-TTS-Nano ONNX CPU inference works end-to-end: CLI generate produces valid speech WAV files, PyTorch voice cloning produces valid WAV files, and the FastAPI web server starts with a functional /health endpoint.

ONNX models auto-downloaded from HF. PyTorch checkpoint auto-downloaded from HF. No third-party credentials needed. Web /health returns 200. All inference backends produce valid WAV files.

Argusic installed MOSS-TTS-Nano in 8 minutes and launched it; verification reached Verified running for real. 3 of 3 recorded errors were worked through (see the timeline below).

Runsall runs of MOSS-TTS-Nano

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.