click any column header to sort
TTS Bench — Samples — windows-es-default
Rig: windows-5090 — AMD Ryzen 9 9950X3D 16-Core Processor (16C) · NVIDIA GeForce RTX 5090 32GB · 126 GB RAM · Windows 11
Label: Spanish default voice
1 prompt(s) · one section per prompt · all models ranked by warm TTFA (fastest first) within each
Each prompt section shows every model's audio output, ordered by warm TTFA (fastest first). Click any audio player to hear that model's rendering.
Prompt 6
[es]"¿Este modelo es bilingüe? Añade el español, corrige la pronunciación automática y reinicia el servidor."
| Rank |
Model |
Device |
TTFA warm |
Audio |
| 1 |
Piper |
cpu |
34ms |
|
| 2 |
Kokoro |
cuda |
67ms |
|
| 3 |
MeloTTS |
cuda |
84ms |
|
| 4 |
NeuTTS Nano |
cuda |
165ms |
|
| 5 |
NeuTTS Nano |
cpu |
206ms |
|
| 6 |
OpenVoice v2 |
cuda |
395ms |
|
| 7 |
Pocket-TTS |
cpu |
398ms |
|
| 8 |
Kokoro |
cpu |
472ms |
|
| 9 |
Audio8 TTS 0.6B (compiled) |
cuda |
542ms |
|
| 10 |
Supertonic 3 |
cpu |
807ms |
|
| 11 |
MeloTTS |
cpu |
842ms |
|
| 12 |
Scylla's Band |
cpu |
898ms |
|
| 13 |
OpenVoice v2 |
cpu |
1.63s |
|
| 14 |
Qwen3-TTS 1.7B (CUDA-graph) |
cuda |
1.77s |
|
| 15 |
Coqui XTTS-v2 |
cuda |
2.65s |
|
| 16 |
Qwen3-TTS 0.6B Base |
cuda |
8.87s |
|
| 17 |
Audio8 TTS Preview 0.6B |
cuda |
9.33s |
|
| 18 |
Qwen3-TTS 1.7B Base |
cuda |
11.50s |
|
| 19 |
Coqui XTTS-v2 |
cpu |
12.04s |
|
| 20 |
Audio8 TTS Preview 0.1B |
cuda |
12.20s |
|
| 21 |
Audio8 TTS Preview 0.1B |
cpu |
21.19s |
|
| 22 |
Audio8 TTS Preview 0.6B |
cpu |
49.77s |
|