Voice AI BenchmarksBy

OPENAITEXT-TO-SPEECH7,244 SAMPLES / 30 DAYSLAST RUN OCT 14, 2026, 06:30 UTC

official resource

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

GPT-4o mini TTS, hosted by OpenAI, measures mean 2583 ms time to first audio (32nd of 32) and 1.8% word error rate (15th of 32) among TTS systems. Results cover the last 30 days. Coval benchmarks hosted endpoints daily using a consistent evaluation methodology. Last measured .

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

Time to First Audio#32 / 32
2583ms
TTFA Network Roundtrip#32 / 32
2375ms
TTFA Leading Silence#22 / 32
117ms
Word Error Rate#15 / 32
1.8%

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
Emotion control, Multilingual

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. #1vui60 ms
  2. #2Default63 ms
  3. #3Qwen3 TTS Fast68 ms
  4. #4TTS Flash 292 ms
  5. #5Qwen3 TTS 1.7b107 ms
  6. #6Simba 3.0111 ms
  7. #7Palabra TTS v1119 ms
  8. #8Simba 3.2126 ms
  9. #9drama3-preview161 ms
  10. #10Flash v2.5191 ms
  11. #11TTS 2192 ms
  12. #12Eleven v4 Turbo201 ms
  13. #13Flux TTS205 ms
  14. #14TTS RT v1254 ms
  15. #15TTS Rt v2256 ms
  16. #16Mist v3287 ms
  17. #17Sonic 3.5293 ms
  18. #18Phantom Z 3.4 conversational295 ms
  19. #19Aura 2297 ms
  20. #20Sonic 3.6299 ms
  21. #21Falcon 2303 ms
  22. #22Coda332 ms
  23. #23S2.1 Pro341 ms
  24. #24Grok TTS362 ms
  25. #25S1389 ms
  26. #26Lightning v3.1 Pro392 ms
  27. #27Daytona TTS486 ms
  28. #28Aura 2 En572 ms
  29. #29Chirp 3 HD598 ms
  30. #30Qwen3 TTS Flash Realtime718 ms
  31. #31S2.1 Pro Free850 ms
  32. #32GPT-4o mini TTS2583 ms
median of all models · 290 ms
TTS models over the last 30 days, ranked on Time to First Audio.
#ModelHostTTFAWERSamples
1vuiFluxions60 ms1,708
2Gradium TTS Beta 202609Gradium63 ms1,880
3Qwen3 TTS FastNari Labs68 ms1,880
4TTS Flash 2Inworld AI92 ms1,684
5Qwen3 TTS 1.7bBaseten107 ms1,248
6Simba 3.0SpeechifyAI111 ms1,879
7Palabra TTS v1Palabra119 ms1,545
8Simba 3.2SpeechifyAI126 ms1,876
9Drama 3 Preview Us EastFish Audio161 ms126
10Flash v2.5ElevenLabs191 ms1,871
11TTS 2Inworld AI192 ms1,684
12Eleven v4 TurboElevenLabs201 ms1,190
13Flux TTSDeepgram205 ms1,743
14TTS RT v1Soniox254 ms1,585
15TTS Rt v2Soniox256 ms1,583
16Mist v3Rime287 ms602
17Sonic 3.5Cartesia293 ms1,880
18Phantom Z 3.4 conversationalDeepdub295 ms1,615
19Aura 2Deepgram297 ms1,812
20Sonic 3.6Cartesia299 ms1,880
21Falcon 2Murf303 ms1,879
22CodaRime332 ms602
23S2.1 ProFish Audio341 ms1,880
24Grok TTSSpaceXAI362 ms1,875
25S1Fish Audio389 ms1,879
26Lightning v3.1 ProSmallest392 ms1,880
27Daytona TTSGuava486 ms1,152
28Aura 2 EnCloudflare572 ms1,879
29Chirp 3 HDGoogle598 ms1,880
30Qwen3 TTS Flash RealtimeAlibaba718 ms1,879
31S2.1 Pro FreeFish Audio850 ms1,873
32GPT-4o mini TTSOpenAI2583 ms1,816
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: 15th of 32 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.
vui — 60 ms, 2.1%Default — 63 ms, 1.9%Qwen3 TTS Fast — 68 ms, 1.8%TTS Flash 2 — 92 ms, 1.7%Qwen3 TTS 1.7b — 107 ms, 1.8%Simba 3.0 — 111 ms, 1.5%Palabra TTS v1 — 119 ms, 2.6%Simba 3.2 — 126 ms, 1.9%drama3-preview — 161 ms, 2.1%Flash v2.5 — 191 ms, 1.8%TTS 2 — 192 ms, 1.6%Eleven v4 Turbo — 201 ms, 1.7%Flux TTS — 205 ms, 1.7%TTS RT v1 — 254 ms, 2.4%TTS Rt v2 — 256 ms, 2.4%Mist v3 — 287 ms, 2.1%Sonic 3.5 — 293 ms, 1.5%Phantom Z 3.4 conversational — 295 ms, 1.8%Aura 2 — 297 ms, 1.8%Sonic 3.6 — 299 ms, 1.5%Falcon 2 — 303 ms, 1.7%Coda — 332 ms, 9.5%S2.1 Pro — 341 ms, 1.5%Grok TTS — 362 ms, 1.6%S1 — 389 ms, 1.8%Lightning v3.1 Pro — 392 ms, 1.5%Daytona TTS — 486 ms, 1.6%Aura 2 En — 572 ms, 2.1%Chirp 3 HD — 598 ms, 1.5%Qwen3 TTS Flash Realtime — 718 ms, 3.0%S2.1 Pro Free — 850 ms, 1.5%GPT-4o mini TTS — 2583 ms, 1.8%

Where the errors come from

WER compositionGPT-4o mini TTS's Word Error Rate split by error type · 30-day averageGPT-4o mini TTS's WER split into substitutions, deletions and insertions.
  • GPT-4o mini TTS1.8%
SubstitutionsDeletionsInsertions

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 max.
  • Time to First Audiop50 2771 ms · Max 29788 ms
  • TTFA Network Roundtripp50 2467 ms · Max 29784 ms
  • TTFA Leading Silencep50 28 ms · Max 1252 ms
band p25–p75 · tick p50 · whisker to max with p90 and p95 stops
Average and percentile values per metric, with the number of samples behind each row.
MetricAveragep25p50p75p90p95MaxSamples
Time to First Audio2583 ms574 ms2771 ms3927 ms4691 ms5283 ms29788 ms1,816
TTFA Network Roundtrip2375 ms499 ms2467 ms3789 ms4458 ms5009 ms29784 ms1,802
TTFA Leading Silence117 ms15 ms28 ms100 ms439 ms535 ms1252 ms1,802
Word Error Rate1.8%0.0%0.0%2.0%7.5%12.0%50.0%1,824

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 · Sep 23: 1,887 msGPT-4o mini TTS · Sep 24: 2,469 msGPT-4o mini TTS · Sep 25: 2,190 msGPT-4o mini TTS · Sep 26: 2,903 msGPT-4o mini TTS · Sep 27: 2,188 msGPT-4o mini TTS · Sep 28: 2,637 msGPT-4o mini TTS · Sep 29: 2,929 msGPT-4o mini TTS · Sep 30: 2,435 msGPT-4o mini TTS · Oct 1: 1,970 msGPT-4o mini TTS · Oct 2: 2,298 msGPT-4o mini TTS · Oct 3: 2,265 msGPT-4o mini TTS · Oct 4: 2,192 msGPT-4o mini TTS · Oct 5: 1,973 msGPT-4o mini TTS · Oct 6: 2,860 msGPT-4o mini TTS · Oct 7: 2,334 msGPT-4o mini TTS · Oct 8: 2,399 msGPT-4o mini TTS · Oct 9: 2,324 msGPT-4o mini TTS · Oct 10: 1,999 msGPT-4o mini TTS · Oct 11: 2,443 msGPT-4o mini TTS · Oct 12: 1,915 msGPT-4o mini TTS · Oct 13: 2,126 msGPT-4o mini TTS · Oct 14: 4,836 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 · Sep 23: 4.7%GPT-4o mini TTS · Sep 24: 3.4%GPT-4o mini TTS · Sep 25: 3.0%GPT-4o mini TTS · Sep 26: 3.9%GPT-4o mini TTS · Sep 27: 4.2%GPT-4o mini TTS · Sep 28: 6.0%GPT-4o mini TTS · Sep 29: 4.2%GPT-4o mini TTS · Sep 30: 2.2%GPT-4o mini TTS · Oct 1: 5.1%GPT-4o mini TTS · Oct 2: 3.7%GPT-4o mini TTS · Oct 3: 5.4%GPT-4o mini TTS · Oct 4: 8.0%GPT-4o mini TTS · Oct 5: 2.3%GPT-4o mini TTS · Oct 6: 4.6%GPT-4o mini TTS · Oct 7: 5.4%GPT-4o mini TTS · Oct 8: 4.3%GPT-4o mini TTS · Oct 9: 3.3%GPT-4o mini TTS · Oct 10: 1.6%GPT-4o mini TTS · Oct 11: 3.0%GPT-4o mini TTS · Oct 12: 4.3%GPT-4o mini TTS · Oct 13: 5.4%GPT-4o mini TTS · Oct 14: 6.8%

How fast is GPT-4o mini TTS?

On OpenAI, GPT-4o mini TTS measures mean 2583 ms time to first audio (32nd of 32). Last measured 2026-10-14.

How accurate is GPT-4o mini TTS?

On OpenAI, GPT-4o mini TTS measures 1.8% word error rate (15th of 32). Last measured 2026-10-14.

Who hosts GPT-4o mini TTS?

GPT-4o mini TTS is created by OpenAI and served by OpenAI. Coval measures each hosted endpoint separately.

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