MOSS-TTS-Nano tested by Argusic Runner

What the test found

Dependencies installed in venv; PyTorch CPU inference via infer.py produces valid WAV audio; FastAPI web server responds to health checks and generates 48kHz stereo speech via POST /api/generate with demo presets

All dependencies installed in venv at /tmp/venv. Models downloaded from HuggingFace (OpenMOSS-Team/MOSS-TTS-Nano, MOSS-Audio-Tokenizer-Nano). Both CLI inference and web API verified with real model weights.

Argusic installed MOSS-TTS-Nano in 2 minutes and launched it; verification reached Verified running for real.

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.