click any column header to sort

TTS Bench — Speed — 2026-06-01_2240

Rig: windows-5090 — AMD Ryzen 9 9950X3D 16-Core Processor (16C) · NVIDIA GeForce RTX 5090 32GB · 126 GB RAM · Windows 11
Label: default voice · echo
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: no data

Fastest cloning-capable: Echo-TTS (cuda) — 3.44× warm RTFx, 2.15s warm TTFA

ModelDeviceTTFA coldTTFA warmRTFx coldRTFx warmPeak RAMPeak VRAMSizeReleased
Echo-TTScuda2.83s2.15s2.63×3.44×1.94 GB9.38 GB2.8BDec 2025