click any column header to sort

TTS Bench — Speed — 2026-06-02_2119

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 · outetts — 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): OuteTTS 1.0 1B (cuda) — 0.31× warm RTFx, 6.42s warm TTFA

Model	Device	TTFA cold	TTFA warm	RTFx cold	RTFx warm	Peak RAM	Peak VRAM	Size	Released
OuteTTS 1.0 1B	cuda	6.13s	6.42s	0.30×	0.31×	3.60 GB	2.98 GB	1B	Apr 2025
OuteTTS 1.0 1B	cpu	47.92s	46.02s	0.04×	0.04×	5.03 GB	—	1B	Apr 2025