Fastest (this cloning run): StyleTTS 2 (cuda) — 41.66× warm RTF, 212ms warm TTFA
| Model | Device | TTFA cold | TTFA warm | RTF cold | RTF warm | Peak RAM | Peak VRAM | Size |
|---|---|---|---|---|---|---|---|---|
| StyleTTS 2 | cuda | 1.66s | 212ms | 5.45× | 41.66× | 2.63 GB | 1.52 GB | ~148M |
| StyleTTS 2 | cpu | 1.70s | 218ms | 5.27× | 40.62× | 2.63 GB | — | ~148M |
| OpenVoice v2 | cuda | 1.72s | 361ms | 3.61× | 16.73× | 2.65 GB | 1.35 GB | ~100M |
| OmniVoice | cuda | 1.20s | 803ms | 6.67× | 9.75× | 2.27 GB | 2.42 GB | ~1B |
| MiraTTS | cuda | 2.14s | 1.46s | 4.76× | 7.01× | 3.58 GB | 1.28 GB | 0.5B |
| LongCat-AudioDiT 1B | cuda | 1.66s | 1.36s | 4.72× | 5.67× | 2.36 GB | 5.78 GB | 1.42B |
| F5-TTS v1 | cuda | 1.56s | 1.06s | 3.75× | 5.50× | 2.67 GB | 883 MB | 330M |
| Coqui XTTS-v2 | cuda | 2.02s | 1.51s | 3.02× | 4.76× | 2.35 GB | 2.10 GB | 750M |
| OpenVoice v2 | cpu | 2.60s | 1.44s | 2.23× | 4.25× | 2.78 GB | — | ~100M |
| Chatterbox Turbo | cuda | 2.66s | 1.59s | 2.43× | 4.15× | 2.69 GB | 3.33 GB | 744M |
| Pocket-TTS | cpu | 136ms | 124ms | 4.11× | 4.10× | 2.29 GB | — | 100M |
| Qwen3-TTS 1.7B (CUDA-graph) | cuda | 7.93s | 1.57s | 0.83× | 3.66× | 2.61 GB | 4.89 GB | 1.7B |
| LongCat-AudioDiT 3.5B | cuda | 2.59s | 2.32s | 3.13× | 3.49× | 2.26 GB | 15.14 GB | 3.83B |
| Echo-TTS | cuda | 2.84s | 2.23s | 2.62× | 3.39× | 1.94 GB | 9.38 GB | 2.8B |
| Chatterbox | cuda | 4.01s | 2.88s | 1.63× | 2.33× | 3.02 GB | 3.63 GB | 1.2B |
| DramaBox | cuda | 6.46s | 4.99s | 1.66× | 2.14× | 2.45 GB | 17.39 GB | 3.3B |
| WavTTS 0.67B | cuda | 3.16s | 2.84s | 1.85× | 2.08× | 2.00 GB | 1.44 GB | 0.67B |
| NeuTTS Nano | cuda | 854ms | 331ms | 1.60× | 2.00× | 2.59 GB | 3.26 GB | 229M |
| MOSS-TTS-Nano | cuda | 5.59s | 4.87s | 1.34× | 1.66× | 2.42 GB | 910 MB | 100M |
| VibeVoice 7B | cuda | 5.22s | 4.86s | 1.41× | 1.58× | 2.04 GB | 17.63 GB | 7B |
| NeuTTS Nano | cpu | 863ms | 387ms | 1.23× | 1.58× | 5.12 GB | — | 229M |
| IndexTTS-2 | cpu | 5.77s | 4.87s | 1.20× | 1.47× | 5.54 GB | — | 1.5B |
| MOSS-TTS v1.0 | cuda | 5.44s | 4.73s | 1.31× | 1.44× | 2.10 GB | 22.83 GB | 8B |
| VoxCPM2 2B | cuda | 6.36s | 4.72s | 0.96× | 1.33× | 2.49 GB | 5.71 GB | 2B |
| NeuTTS Air | cuda | 1.46s | 492ms | 0.88× | 1.30× | 2.96 GB | 3.26 GB | 748M |
| IndexTTS-2 | cuda | 6.80s | 5.66s | 1.03× | 1.26× | 4.05 GB | 7.71 GB | 1.5B |
| MOSS-TTS-Nano | cpu | 5.69s | 5.04s | 1.16× | 1.25× | 3.05 GB | — | 100M |
| MOSS-TTS v1.5 | cuda | 5.88s | 5.28s | 1.14× | 1.24× | 2.36 GB | 22.83 GB | 8B |
| NeuTTS Air | cpu | 1.75s | 568ms | 0.75× | 0.96× | 5.47 GB | — | 748M |
| Fish Speech 1.5 | cuda | 8.04s | 8.21s | 0.85× | 0.95× | 3.82 GB | 1.76 GB | ~500M |
| Coqui XTTS-v2 | cpu | 9.93s | 8.76s | 0.84× | 0.85× | 3.43 GB | — | 750M |
| Zonos v0.1 | cuda | 10.36s | 9.85s | 0.67× | 0.73× | 6.55 GB | 4.45 GB | 1.6B |
| Chatterbox Turbo | cpu | 10.84s | 9.37s | 0.68× | 0.71× | 4.39 GB | — | 744M |
| ZipVoice 123M (4/5 ok) | cuda | 68.19s | 105.99s | 0.38× | 0.60× | 25.56 GB | 53.24 GB | 123M |
| Sesame CSM-1B | cuda | 13.21s | 11.46s | 0.47× | 0.55× | 2.47 GB | 3.54 GB | 1B |
| Dia 1.6B-0626 | cuda | 14.04s | 11.22s | 0.33× | 0.47× | 8.53 GB | 4.82 GB | 1.6B |
| ZipVoice 123M | cpu | 50.03s | 47.06s | 0.30× | 0.43× | 39.66 GB | — | 123M |
| VoxCPM2 2B | cpu | 18.12s | 16.04s | 0.34× | 0.39× | 7.53 GB | — | 2B |
| Chatterbox | cpu | 17.39s | 17.39s | 0.36× | 0.38× | 4.72 GB | — | 1.2B |
| Miso TTS 8B | cuda | 37.67s | 32.57s | 0.30× | 0.32× | 2.07 GB | 16.55 GB | 8.2B |
| OuteTTS 1.0 1B | cuda | 18.32s | 17.44s | 0.30× | 0.30× | 3.64 GB | 3.56 GB | 1B |
| Fish Speech 1.5 | cpu | 37.45s | 42.66s | 0.18× | 0.18× | 4.43 GB | — | ~500M |
| OmniVoice | cpu | 54.74s | 53.28s | 0.14× | 0.14× | 3.98 GB | — | ~1B |
| Zonos v0.1 | cpu | 61.60s | 60.84s | 0.12× | 0.12× | 8.57 GB | — | 1.6B |
| Sesame CSM-1B | cpu | 48.90s | 48.64s | 0.12× | 0.12× | 6.32 GB | — | 1B |
| Mars5-TTS | cpu | 41.89s | 43.23s | 0.08× | 0.10× | 2.24 GB | — | 1.2B |
| F5-TTS v1 | cpu | 71.35s | 71.18s | 0.08× | 0.08× | 2.71 GB | — | 330M |
| Mars5-TTS | cuda | 41.12s | 39.53s | 0.09× | 0.07× | 2.23 GB | 7.23 GB | 1.2B |
| LuxTTS | cpu | LuxTTS install failed (piper-phonemize has no Windows wheels) | ||||||