click any column header to sort
← SpeedSpeedSamples → · all runs

TTS Bench — Samples — linux-cloning

Rig: linux-3090 — AMD Ryzen 9 5900XT 16-Core Processor · NVIDIA GeForce RTX 3090 24GB · 63 GB RAM · Linux 6.8.0-117-generic
Label: cloning · chris_hemsworth voice (note: metavoice uses the 67s clip — it needs ≥30s ref — all other models use the 15s clip) — ref chris_hemsworth_15s.wav
5 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.

Reference voice

Each model below was given this clip + transcript as the voice to imitate. Source: chris_hemsworth_15s.wav

Prompt 1

[en]"Open the browser and read my email."
Rank Model Device TTFA warm Audio
1 Pocket-TTS cpu 83ms
2 Sopro V2 Turbo (streaming) cuda 85ms
3 StyleTTS 2 cuda 145ms
4 LuxTTS cuda 195ms
5 Sopro V2 Turbo cuda 201ms
6 OpenVoice v2 cuda 254ms
7 Breeze TTS 2 cuda 313ms
8 Audio8 TTS 0.6B (compiled) cuda 350ms
9 NeuTTS Nano cuda 359ms
10 NeuTTS Nano cpu 418ms
11 NeuTTS Air cuda 432ms
12 MiraTTS cuda 453ms
13 Coqui XTTS-v2 cuda 475ms
14 MioTTS 0.1B cuda 518ms
15 NeuTTS Air cpu 559ms
16 AuK-Flash cuda 585ms
17 Chatterbox Turbo cuda 631ms
18 Qwen3-TTS 1.7B (CUDA-graph) cuda 767ms
19 Sopro V2 Turbo (streaming) cpu 767ms
20 Higgs Audio v3 TTS cuda 856ms
21 FireRedTTS3 cuda 893ms
22 CosyVoice 3 0.5B cuda 985ms
23 OpenVoice v2 cpu 988ms
24 Zonos2 cuda 1.10s
25 LongCat-AudioDiT 1B cuda 1.12s
26 Chatterbox cuda 1.13s
27 OmniVoice cuda 1.14s
28 F5-TTS v1 cuda 1.14s
29 VoxCPM2 2B cuda 1.22s
30 StyleTTS 2 cpu 1.26s
31 LuxTTS cpu 1.29s
32 Dia 1.6B-0626 cuda 1.29s
33 Sopro V2 Turbo cpu 1.49s
34 MioTTS 0.6B cuda 1.93s
35 Fish Speech 1.5 cuda 1.93s
36 MOSS-TTS-Nano cuda 1.97s
37 MOSS-TTS v1.5 cuda 2.19s
38 MOSS-TTS v1.0 cuda 2.25s
39 Zonos v0.1 cuda 2.34s
40 MetaVoice-1B cuda 2.51s
41 Audio8 TTS Preview 0.1B cuda 2.97s
42 LongCat-AudioDiT 3.5B cuda 3.03s
43 IndexTTS-2 cuda 3.09s
44 Step-Audio-EditX cuda 3.10s
45 Coqui XTTS-v2 cpu 3.15s
46 Audio8 TTS Preview 0.6B cuda 3.24s
47 Sesame CSM-1B cuda 3.34s
48 dots.tts (soar) cuda 3.49s
49 MOSS-TTS-Nano cpu 3.52s
50 Chatterbox Turbo cpu 3.91s
51 VibeVoice 7B cuda 4.00s
52 WavTTS 0.67B cuda 4.33s
53 Echo-TTS cuda 4.34s
54 OuteTTS 1.0 1B cuda 4.67s
55 Miso TTS 8B cuda 4.86s
56 AuK cuda 5.64s
57 ZipVoice 123M cpu 6.97s
58 Chatterbox cpu 8.01s
59 DramaBox cuda 9.77s
60 Fish Speech S2-Pro cuda 10.52s
61 VoxCPM2 2B cpu 14.19s
62 Audio8 TTS Preview 0.1B cpu 15.38s
63 Zonos v0.1 cpu 18.48s
64 Audio8 TTS Preview 0.6B cpu 19.12s
65 Fish Speech 1.5 cpu 19.19s
66 Sesame CSM-1B cpu 27.72s
67 IndexTTS-2 cpu 34.57s
68 OmniVoice cpu 35.63s
69 F5-TTS v1 cpu 45.27s
70 Mars5-TTS cuda 70.40s

Prompt 2

[en]"I'll start a new git branch, push the changes, and open a pull request when the tests pass."
Rank Model Device TTFA warm Audio
1 Sopro V2 Turbo (streaming) cuda 102ms
2 Pocket-TTS cpu 114ms
3 StyleTTS 2 cuda 197ms
4 LuxTTS cuda 219ms
5 OpenVoice v2 cuda 272ms
6 Breeze TTS 2 cuda 302ms
7 Sopro V2 Turbo cuda 341ms
8 NeuTTS Nano cuda 343ms
9 NeuTTS Nano cpu 378ms
10 NeuTTS Air cuda 426ms
11 Sopro V2 Turbo (streaming) cpu 516ms
12 MioTTS 0.6B cuda 588ms
13 NeuTTS Air cpu 598ms
14 AuK-Flash cuda 731ms
15 MioTTS 0.1B cuda 737ms
16 Audio8 TTS 0.6B (compiled) cuda 806ms
17 MiraTTS cuda 814ms
18 Coqui XTTS-v2 cuda 998ms
19 Chatterbox Turbo cuda 1.17s
20 LongCat-AudioDiT 1B cuda 1.20s
21 OmniVoice cuda 1.35s
22 F5-TTS v1 cuda 1.50s
23 Higgs Audio v3 TTS cuda 1.76s
24 LuxTTS cpu 2.08s
25 Chatterbox cuda 2.21s
26 OpenVoice v2 cpu 2.22s
27 Sopro V2 Turbo cpu 2.26s
28 MOSS-TTS-Nano cuda 2.27s
29 VoxCPM2 2B cuda 2.38s
30 Zonos2 cuda 2.44s
31 StyleTTS 2 cpu 2.52s
32 MOSS-TTS v1.0 cuda 3.14s
33 MOSS-TTS v1.5 cuda 3.19s
34 LongCat-AudioDiT 3.5B cuda 3.24s
35 CosyVoice 3 0.5B cuda 3.58s
36 FireRedTTS3 cuda 3.84s
37 Echo-TTS cuda 4.32s
38 IndexTTS-2 cuda 4.62s
39 Step-Audio-EditX cuda 4.62s
40 WavTTS 0.67B cuda 5.22s
41 MetaVoice-1B cuda 5.34s
42 MOSS-TTS-Nano cpu 5.40s
43 Fish Speech 1.5 cuda 5.62s
44 Zonos v0.1 cuda 5.65s
45 Audio8 TTS Preview 0.1B cuda 5.84s
46 Sesame CSM-1B cuda 6.49s
47 AuK cuda 6.64s
48 Audio8 TTS Preview 0.6B cuda 6.71s
49 Coqui XTTS-v2 cpu 6.81s
50 Chatterbox Turbo cpu 7.40s
51 Dia 1.6B-0626 cuda 7.86s
52 VibeVoice 7B cuda 7.98s
53 dots.tts (soar) cuda 8.43s
54 DramaBox cuda 10.81s
55 OuteTTS 1.0 1B cuda 11.19s
56 ZipVoice 123M cpu 13.29s
57 Chatterbox cpu 14.36s
58 Miso TTS 8B cuda 19.99s
59 Audio8 TTS Preview 0.1B cpu 24.47s
60 VoxCPM2 2B cpu 26.35s
61 Fish Speech S2-Pro cuda 27.16s
62 Sesame CSM-1B cpu 38.09s
63 Audio8 TTS Preview 0.6B cpu 38.09s
64 OmniVoice cpu 44.05s
65 Qwen3-TTS 1.7B (CUDA-graph) cuda 45.49s
66 Zonos v0.1 cpu 45.50s
67 F5-TTS v1 cpu 57.96s
68 IndexTTS-2 cpu 58.88s
69 Fish Speech 1.5 cpu 61.64s
70 Mars5-TTS cuda 80.29s

Prompt 3

[en]"The Parakeet TDT zero point six billion parameter model achieves one point six nine percent word error rate on LibriSpeech test-clean, beating Whisper Large V3 at two point seven percent while running at over two thousand times realtime on a single GPU."
Rank Model Device TTFA warm Audio
1 Sopro V2 Turbo (streaming) cuda 86ms
2 Pocket-TTS cpu 122ms
3 Breeze TTS 2 cuda 293ms
4 LuxTTS cuda 332ms
5 NeuTTS Nano cuda 373ms
6 StyleTTS 2 cuda 415ms
7 NeuTTS Nano cpu 449ms
8 NeuTTS Air cuda 531ms
9 Sopro V2 Turbo (streaming) cpu 534ms
10 OpenVoice v2 cuda 549ms
11 NeuTTS Air cpu 594ms
12 Sopro V2 Turbo cuda 1.11s
13 AuK-Flash cuda 1.17s
14 LongCat-AudioDiT 1B cuda 1.63s
15 MioTTS 0.6B cuda 1.77s
16 Audio8 TTS 0.6B (compiled) cuda 2.06s
17 MioTTS 0.1B cuda 2.09s
18 OmniVoice cuda 2.23s
19 MiraTTS cuda 2.32s
20 F5-TTS v1 cuda 3.14s
21 Chatterbox Turbo cuda 3.32s
22 Coqui XTTS-v2 cuda 3.65s
23 Qwen3-TTS 1.7B (CUDA-graph) cuda 3.85s
24 Echo-TTS cuda 4.34s
25 Higgs Audio v3 TTS cuda 4.77s
26 LongCat-AudioDiT 3.5B cuda 5.50s
27 LuxTTS cpu 5.76s
28 CosyVoice 3 0.5B cuda 5.98s
29 Chatterbox cuda 6.05s
30 MOSS-TTS-Nano cuda 6.81s
31 Zonos2 cuda 6.90s
32 Sopro V2 Turbo cpu 7.11s
33 MOSS-TTS v1.5 cuda 7.32s
34 VoxCPM2 2B cuda 7.42s
35 OpenVoice v2 cpu 7.54s
36 MOSS-TTS v1.0 cuda 7.68s
37 StyleTTS 2 cpu 9.72s
38 Step-Audio-EditX cuda 9.99s
39 AuK cuda 10.17s
40 WavTTS 0.67B cuda 11.39s
41 IndexTTS-2 cuda 12.24s
42 Sesame CSM-1B cuda 13.52s
43 FireRedTTS3 cuda 14.12s
44 MOSS-TTS-Nano cpu 14.54s
45 MetaVoice-1B cuda 14.56s
46 DramaBox cuda 14.62s
47 Fish Speech 1.5 cuda 15.11s
48 Zonos v0.1 cuda 17.67s
49 Audio8 TTS Preview 0.1B cuda 17.72s
50 Audio8 TTS Preview 0.6B cuda 19.98s
51 Chatterbox Turbo cpu 21.26s
52 Dia 1.6B-0626 cuda 21.73s
53 VibeVoice 7B cuda 24.87s
54 Coqui XTTS-v2 cpu 25.42s
55 OuteTTS 1.0 1B cuda 30.19s
56 dots.tts (soar) cuda 36.35s
57 Chatterbox cpu 42.09s
58 Audio8 TTS Preview 0.1B cpu 58.99s
59 VoxCPM2 2B cpu 67.86s
60 OmniVoice cpu 69.74s
61 Sesame CSM-1B cpu 80.94s
62 Fish Speech S2-Pro cuda 81.01s
63 Miso TTS 8B cuda 84.98s
64 Mars5-TTS cuda 104.33s
65 Audio8 TTS Preview 0.6B cpu 105.93s
66 F5-TTS v1 cpu 141.44s
67 Fish Speech 1.5 cpu 143.99s
68 IndexTTS-2 cpu 160.07s
69 Zonos v0.1 cpu 164.17s

Prompt 4

[en]"Run pytest tests slash test underscore voice dot py with verbose flag and capture flag set to no."
Rank Model Device TTFA warm Audio
1 Sopro V2 Turbo (streaming) cuda 86ms
2 Pocket-TTS cpu 113ms
3 LuxTTS cuda 220ms
4 StyleTTS 2 cuda 254ms
5 Breeze TTS 2 cuda 312ms
6 NeuTTS Nano cuda 366ms
7 OpenVoice v2 cuda 384ms
8 NeuTTS Nano cpu 428ms
9 Sopro V2 Turbo cuda 487ms
10 Sopro V2 Turbo (streaming) cpu 509ms
11 NeuTTS Air cuda 523ms
12 NeuTTS Air cpu 597ms
13 AuK-Flash cuda 692ms
14 MioTTS 0.6B cuda 848ms
15 MioTTS 0.1B cuda 882ms
16 Audio8 TTS 0.6B (compiled) cuda 989ms
17 Chatterbox Turbo cuda 1.32s
18 MiraTTS cuda 1.35s
19 OmniVoice cuda 1.40s
20 LongCat-AudioDiT 1B cuda 1.41s
21 F5-TTS v1 cuda 1.56s
22 Coqui XTTS-v2 cuda 1.70s
23 LuxTTS cpu 2.24s
24 Higgs Audio v3 TTS cuda 2.52s
25 OpenVoice v2 cpu 2.63s
26 StyleTTS 2 cpu 2.67s
27 MOSS-TTS-Nano cuda 2.99s
28 Chatterbox cuda 3.04s
29 CosyVoice 3 0.5B cuda 3.07s
30 VoxCPM2 2B cuda 3.10s
31 Zonos2 cuda 3.16s
32 Sopro V2 Turbo cpu 3.17s
33 FireRedTTS3 cuda 3.37s
34 MOSS-TTS v1.0 cuda 3.43s
35 LongCat-AudioDiT 3.5B cuda 3.91s
36 MOSS-TTS v1.5 cuda 3.92s
37 Echo-TTS cuda 4.34s
38 Fish Speech 1.5 cuda 5.13s
39 WavTTS 0.67B cuda 5.34s
40 Step-Audio-EditX cuda 5.58s
41 MOSS-TTS-Nano cpu 5.89s
42 IndexTTS-2 cuda 6.00s
43 AuK cuda 6.01s
44 Zonos v0.1 cuda 6.11s
45 MetaVoice-1B cuda 7.53s
46 Audio8 TTS Preview 0.1B cuda 8.36s
47 Chatterbox Turbo cpu 8.85s
48 Dia 1.6B-0626 cuda 8.86s
49 Coqui XTTS-v2 cpu 8.87s
50 Audio8 TTS Preview 0.6B cuda 9.33s
51 Sesame CSM-1B cuda 9.56s
52 DramaBox cuda 10.95s
53 VibeVoice 7B cuda 11.79s
54 OuteTTS 1.0 1B cuda 12.30s
55 dots.tts (soar) cuda 12.70s
56 ZipVoice 123M cpu 15.77s
57 Miso TTS 8B cuda 17.72s
58 Chatterbox cpu 18.60s
59 Audio8 TTS Preview 0.1B cpu 29.91s
60 VoxCPM2 2B cpu 37.91s
61 OmniVoice cpu 45.42s
62 Qwen3-TTS 1.7B (CUDA-graph) cuda 45.62s
63 Audio8 TTS Preview 0.6B cpu 50.49s
64 Zonos v0.1 cpu 50.77s
65 Fish Speech S2-Pro cuda 57.62s
66 Sesame CSM-1B cpu 58.88s
67 F5-TTS v1 cpu 59.69s
68 Fish Speech 1.5 cpu 74.24s
69 IndexTTS-2 cpu 75.24s
70 Mars5-TTS cuda 96.21s

Prompt 5

[fr]"Bonjour, je m'appelle Cicero et je vais vous aider avec votre code aujourd'hui."
Rank Model Device TTFA warm Audio
1 Sopro V2 Turbo (streaming) cuda 87ms
2 Sopro V2 Turbo cuda 293ms
3 Pocket-TTS cpu 320ms
4 NeuTTS Nano cuda 343ms
5 OpenVoice v2 cuda 352ms
6 NeuTTS Nano cpu 424ms
7 Sopro V2 Turbo (streaming) cpu 517ms
8 Audio8 TTS 0.6B (compiled) cuda 648ms
9 AuK-Flash cuda 702ms
10 Coqui XTTS-v2 cuda 808ms
11 OmniVoice cuda 1.33s
12 VoxCPM2 2B cuda 1.37s
13 Qwen3-TTS 1.7B (CUDA-graph) cuda 1.41s
14 Higgs Audio v3 TTS cuda 1.42s
15 Sopro V2 Turbo cpu 1.57s
16 CosyVoice 3 0.5B cuda 2.05s
17 MOSS-TTS-Nano cuda 2.06s
18 OpenVoice v2 cpu 2.20s
19 MOSS-TTS v1.5 cuda 2.76s
20 MOSS-TTS v1.0 cuda 3.20s
21 dots.tts (soar) cuda 3.24s
22 Fish Speech 1.5 cuda 3.74s
23 MOSS-TTS-Nano cpu 3.79s
24 Zonos v0.1 cuda 3.97s
25 Audio8 TTS Preview 0.1B cuda 5.20s
26 Audio8 TTS Preview 0.6B cuda 5.83s
27 Coqui XTTS-v2 cpu 5.99s
28 AuK cuda 6.40s
29 OuteTTS 1.0 1B cuda 8.54s
30 ZipVoice 123M cpu 12.85s
31 VoxCPM2 2B cpu 18.72s
32 Audio8 TTS Preview 0.1B cpu 23.21s
33 Zonos v0.1 cpu 31.28s
34 Audio8 TTS Preview 0.6B cpu 31.52s
35 Fish Speech S2-Pro cuda 32.07s
36 OmniVoice cpu 42.37s
37 Fish Speech 1.5 cpu 61.05s