click any column header to sort

TTS Bench — Speed — 2026-06-07_2334

Rig: windows-5090 — AMD Ryzen 9 9950X3D 16-Core Processor (16C) · NVIDIA GeForce RTX 5090 32GB · 126 GB RAM · Windows 11

Label: cloning · chris_hemsworth_15s · moss_tts — ref chris_hemsworth_15s.wav

TTFA = time to first audio (ms; lower is better). RTFx = realtime speed (× realtime; higher is better; e.g. 10× means 10 sec of audio generated per 1 sec of compute). Cold = first run after process start; warm = subsequent runs.

Speed winners

Fastest (this cloning run): MOSS-TTS v1.0 (cuda) — 1.24× warm RTFx, 5.28s warm TTFA

Model	Device	TTFA cold	TTFA warm	RTFx cold	RTFx warm	Peak RAM	Peak VRAM	Size	Released
MOSS-TTS v1.0	cuda	5.88s	5.28s	1.14×	1.24×	2.36 GB	22.83 GB	8B	Feb 2026