Voice AI BenchmarksBy

OPENAITEXT-TO-SPEECH51,342 SAMPLES / 30 DAYSLAST RUN AUG 28, 2026, 21:30 UTC

official resource

GPT-4o mini TTS text-to-speech benchmarks

GPT-4o mini TTS is OpenAI's synthesis model with natural-language speaking-style instructions.

Time to First Audio#30 / 30
1075ms
TTFA Network Roundtrip#28 / 28
929ms
TTFA Leading Silence#20 / 28
127ms
Word Error Rate#12 / 30
4.8%

Overview

OpenAI's Speech API accepts text plus style instructions, and Coval counts silence before the first audible sample in TTFA.

GPT-4o mini TTS is tested every day on a fixed set of text prompts, measuring how quickly audible speech starts and how intelligible the result is.

Technical specifications

Made by
OpenAI
Hosted by
OpenAI
Source
Official API
Licensing
Proprietary
Deployment
Cloud
Region
US
Features
Multilingual, Emotion control

How GPT-4o mini TTS ranks

Full TTS dashboard
Time to First Audio — every measured TTS modelMilliseconds · lower is better · 30-day averageEvery TTS model ranked on Time to First Audio, with GPT-4o mini TTS highlighted.
  1. #1Palabra TTS v1116 ms
  2. #2vui124 ms
  3. #3TTS Flash 2128 ms
  4. #4TTS 2176 ms
  5. #5Blizzard235 ms
  6. #6Neural236 ms
  7. #7Mist v3256 ms
  8. #8TTS Rt v2262 ms
  9. #9Sonic 3.5274 ms
  10. #10TTS RT v1275 ms
  11. #11Dragon HD Latest310 ms
  12. #12Coda313 ms
  13. #13Aura 2328 ms
  14. #14S2.1 Pro374 ms
  15. #15Default384 ms
  16. #16Speech 2.8 Turbo411 ms
  17. #17Eleven v3 Conversational412 ms
  18. #18Grok TTS420 ms
  19. #19S1434 ms
  20. #20Flash v2.5455 ms
  21. #21Speech 2.8 HD460 ms
  22. #22Sonic 3.6466 ms
  23. #23Simba 3.2484 ms
  24. #24Chirp 3 HD512 ms
  25. #25Simba 3.0526 ms
  26. #26Falcon 2549 ms
  27. #27Lightning v3.1 Pro586 ms
  28. #28Qwen3 TTS Flash Realtime645 ms
  29. #29S2.1 Pro Free806 ms
  30. #30GPT-4o mini TTS1075 ms
median of all models · 397 ms
TTS models over the last 30 days, ranked on Time to First Audio.
#ModelHostTTFAWERSamples
1Palabra TTS v1Palabra116 ms5.9%14,396
2vuiFluxions124 ms8,624
3TTS Flash 2Inworld AI128 ms8,719
4TTS 2Inworld AI176 ms4.8%14,529
5BlizzardLmnt235 ms7.4%14,117
6NeuralAzure236 ms4.3%3,350
7Mist v3Rime256 ms6.3%14,524
8TTS Rt v2Soniox262 ms8,849
9Sonic 3.5Cartesia274 ms6.1%14,513
10TTS RT v1Soniox275 ms3.7%14,528
11Dragon HD LatestAzure310 ms5.1%3,350
12CodaRime313 ms5.2%14,523
13Aura 2Deepgram328 ms5.3%14,501
14S2.1 ProFish Audio374 ms10,222
15DefaultGradium384 ms4.6%14,002
16Speech 2.8 TurboMiniMax411 ms4.8%1,997
17Eleven v3 ConversationalElevenLabs412 ms6,750
18Grok TTSxAI420 ms4.7%14,524
19S1Fish Audio434 ms4.9%10,236
20Flash v2.5ElevenLabs455 ms6.7%9,259
21Speech 2.8 HDMiniMax460 ms1,995
22Sonic 3.6Cartesia466 ms560
23Simba 3.2Speechify484 ms4.7%14,525
24Chirp 3 HDGoogle512 ms5.2%14,530
25Simba 3.0Speechify526 ms5.3%14,526
26Falcon 2Murf549 ms10,229
27Lightning v3.1 ProSmallest586 ms4.4%14,515
28Qwen3 TTS Flash RealtimeAlibaba645 ms8.8%14,530
29S2.1 Pro FreeFish Audio806 ms4.7%14,464
30GPT-4o mini TTSOpenAI1075 ms4.8%14,517
Under-sampled models are excluded; tied models share a place. Dotted WER values split into substitutions, deletions and insertions on hover or tap.

Highest relative placement: 12th of 30 on Word Error Rate.

Latency vs accuracy

TTFA vs WEREach point is one measured model · GPT-4o mini TTS highlighted · 30-day averagesTime to First Audio against Word Error Rate for every measured TTS model, with GPT-4o mini TTS highlighted.
Palabra TTS v1 — 116 ms, 5.9%vui — 124 ms, 7.9%TTS Flash 2 — 128 ms, 4.9%TTS 2 — 176 ms, 4.8%Blizzard — 235 ms, 7.4%Neural — 236 ms, 4.3%Mist v3 — 256 ms, 6.3%TTS Rt v2 — 262 ms, 3.9%Sonic 3.5 — 274 ms, 6.1%TTS RT v1 — 275 ms, 3.7%Dragon HD Latest — 310 ms, 5.1%Coda — 313 ms, 5.2%Aura 2 — 328 ms, 5.3%S2.1 Pro — 374 ms, 4.6%Default — 384 ms, 4.6%Speech 2.8 Turbo — 411 ms, 4.8%Eleven v3 Conversational — 412 ms, 4.4%Grok TTS — 420 ms, 4.7%S1 — 434 ms, 4.9%Flash v2.5 — 455 ms, 6.7%Speech 2.8 HD — 460 ms, 4.7%Sonic 3.6 — 466 ms, 5.5%Simba 3.2 — 484 ms, 4.7%Chirp 3 HD — 512 ms, 5.2%Simba 3.0 — 526 ms, 5.3%Falcon 2 — 549 ms, 5.2%Lightning v3.1 Pro — 586 ms, 4.4%Qwen3 TTS Flash Realtime — 645 ms, 8.8%S2.1 Pro Free — 806 ms, 4.7%GPT-4o mini TTS — 1075 ms, 4.8%

Averages and tail latency

Averages hide slow outliers — these are the distributions behind each figure.

GPT-4o mini TTS latency distributionMilliseconds · shared axis across metrics · last 30 daysGPT-4o mini TTS's latency percentiles per metric: p25–p75 band, p50 tick, whisker to p99.
  • Time to First Audiop50 757 ms · p99 4962 ms
  • TTFA Network Roundtripp50 564 ms · p99 4819 ms
  • TTFA Leading Silencep50 33 ms · p99 761 ms
band p25–p75 · tick p50 · whisker to p99 with p90 and p95 stops
Average and percentile values per metric, with the number of samples behind each row.
MetricAveragep25p50p75p90p95p99Samples
Time to First Audio1075 ms488 ms757 ms1013 ms2880 ms3845 ms4962 ms14,517
TTFA Network Roundtrip929 ms383 ms564 ms844 ms2732 ms3742 ms4819 ms11,149
TTFA Leading Silence127 ms17 ms33 ms121 ms450 ms543 ms761 ms11,149
Word Error Rate4.8%0.0%0.0%6.3%20.0%21.4%35.7%14,527

Last 30 days

Daily medians from the same measurement runs · gaps are days without qualifying runs.

Time to First Audio — daily p50Line p50 · band p25–p75 · UTC daysGPT-4o mini TTS's daily median Time to First Audio over the last 30 days.
GPT-4o mini TTS · Jul 30: 700 msGPT-4o mini TTS · Jul 31: 964 msGPT-4o mini TTS · Aug 1: 658 msGPT-4o mini TTS · Aug 2: 1,026 msGPT-4o mini TTS · Aug 3: 749 msGPT-4o mini TTS · Aug 4: 775 msGPT-4o mini TTS · Aug 5: 996 msGPT-4o mini TTS · Aug 6: 749 msGPT-4o mini TTS · Aug 7: 792 msGPT-4o mini TTS · Aug 8: 586 msGPT-4o mini TTS · Aug 9: 586 msGPT-4o mini TTS · Aug 10: 511 msGPT-4o mini TTS · Aug 11: 873 msGPT-4o mini TTS · Aug 12: 784 msGPT-4o mini TTS · Aug 13: 566 msGPT-4o mini TTS · Aug 14: 824 msGPT-4o mini TTS · Aug 15: 587 msGPT-4o mini TTS · Aug 16: 928 msGPT-4o mini TTS · Aug 17: 740 msGPT-4o mini TTS · Aug 18: 805 msGPT-4o mini TTS · Aug 19: 779 msGPT-4o mini TTS · Aug 20: 752 msGPT-4o mini TTS · Aug 21: 656 msGPT-4o mini TTS · Aug 22: 672 msGPT-4o mini TTS · Aug 23: 781 msGPT-4o mini TTS · Aug 24: 847 msGPT-4o mini TTS · Aug 25: 694 msGPT-4o mini TTS · Aug 26: 721 msGPT-4o mini TTS · Aug 27: 745 msGPT-4o mini TTS · Aug 28: 499 ms
Word Error Rate — daily averageDaily average · UTC daysGPT-4o mini TTS's daily Word Error Rate over the last 30 days.
GPT-4o mini TTS · Jul 30: 4.5%GPT-4o mini TTS · Jul 31: 4.4%GPT-4o mini TTS · Aug 1: 6.1%GPT-4o mini TTS · Aug 2: 4.7%GPT-4o mini TTS · Aug 3: 5.4%GPT-4o mini TTS · Aug 4: 4.9%GPT-4o mini TTS · Aug 5: 4.6%GPT-4o mini TTS · Aug 6: 5.4%GPT-4o mini TTS · Aug 7: 5.4%GPT-4o mini TTS · Aug 8: 5.4%GPT-4o mini TTS · Aug 9: 5.4%GPT-4o mini TTS · Aug 10: 4.7%GPT-4o mini TTS · Aug 11: 5.7%GPT-4o mini TTS · Aug 12: 5.2%GPT-4o mini TTS · Aug 13: 3.8%GPT-4o mini TTS · Aug 14: 5.2%GPT-4o mini TTS · Aug 15: 4.7%GPT-4o mini TTS · Aug 16: 5.8%GPT-4o mini TTS · Aug 17: 4.9%GPT-4o mini TTS · Aug 18: 4.7%GPT-4o mini TTS · Aug 19: 5.1%GPT-4o mini TTS · Aug 20: 4.7%GPT-4o mini TTS · Aug 21: 4.5%GPT-4o mini TTS · Aug 22: 4.2%GPT-4o mini TTS · Aug 23: 6.0%GPT-4o mini TTS · Aug 24: 5.3%GPT-4o mini TTS · Aug 25: 4.2%GPT-4o mini TTS · Aug 26: 5.6%GPT-4o mini TTS · Aug 27: 4.8%GPT-4o mini TTS · Aug 28: 5.1%

Time to First Audio by dataset

GPT-4o mini TTS by test conditionMilliseconds · lower is better · best condition firstGPT-4o mini TTS's Time to First Audio on each benchmark dataset.
  1. Text prompts1075 ms
Time to First Audio per dataset, with the number of samples behind each figure.
DatasetTTFASamples
Text prompts1075 ms14,517

Strongest condition: Text prompts at 1075 ms · weakest: Text prompts at 1075 ms.

Limits of this comparison

Coval measures a fixed voice and prompt configuration so changing content does not obscure API timing.

  • A single voice and instruction setting cannot represent the model's complete expressive range.

Official sources

Results are re-measured daily using fixed datasets and reported over a rolling 30-day window. Same datasets, prompts and metric definitions for every model, measured by Coval’s open-source runner. Full methodology on the overview.

Evaluate your own voice agent

Use Coval to test your production configuration, prompts and calls—not only the public benchmark endpoints.

Book a Demo