click any column header to sort

TTS Bench — Speed — 2026-06-01_2241

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 · echo — 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): Echo-TTS (cuda) — 3.39× warm RTFx, 2.23s warm TTFA

Model	Device	TTFA cold	TTFA warm	RTFx cold	RTFx warm	Peak RAM	Peak VRAM	Size	Released
Echo-TTS	cuda	2.84s	2.23s	2.62×	3.39×	1.94 GB	9.38 GB	2.8B	Dec 2025