click any column header to sort

TTS Bench — Speed — 2026-06-03_1121

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

Label: default voice · melotts,parler

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 predefined-voice: MeloTTS (cuda) — 67.28× warm RTFx, 111ms warm TTFA

Fastest cloning-capable: no data

Model	Device	TTFA cold	TTFA warm	RTFx cold	RTFx warm	Peak RAM	Peak VRAM	Size	Released
MeloTTS	cuda	1.58s	111ms	5.08×	67.28×	2.89 GB	1.16 GB	~52M	Feb 2024
MeloTTS	cpu	1.96s	876ms	3.87×	9.27×	2.48 GB	—	~52M	Feb 2024
Parler-TTS Mini v1	cuda	8.29s	8.14s	0.96×	1.05×	3.19 GB	2.63 GB	878M	Jun 2024
Parler-TTS Mini v1	cpu	63.39s	62.77s	0.14×	0.14×	4.31 GB	—	878M	Jun 2024