Voice AI BenchmarksBy

OPENAISPEECH-TO-TEXT106,484 SAMPLES / 30 DAYSLAST RUN OCT 14, 2026, 10:30 UTC

official resource

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

GPT-4o mini Transcribe, hosted by OpenAI, measures mean 708 ms time to final segment (26th of 29) and 3.9% word error rate (11th of 31) among STT systems. Results cover the last 30 days. Coval benchmarks hosted endpoints daily using a consistent evaluation methodology. Last measured .

GPT-4o mini Transcribe is OpenAI's smaller GPT-4o-based transcription model.

Time to Final Segment#26 / 29
708ms
Word Error Rate#11 / 31
3.9%

Overview

OpenAI offers it as a dedicated Audio API transcription model with streaming output and prompt context for vocabulary guidance.

GPT-4o mini Transcribe is tested every day on fixed public audio — clean, accented, noisy, reverberant, far-field, clipped and phone-codec speech — for transcription accuracy and streaming latency.

Technical specifications

Made by
OpenAI
Hosted by
OpenAI
Source
Official API
Licensing
Proprietary
Deployment
Cloud
Region
US
Features
Keyterm biasing, Multilingual, VAD

How GPT-4o mini Transcribe ranks

Full STT dashboard
Time to Final Segment — every measured STT modelMilliseconds · lower is better · 30-day averageEvery STT model ranked on Time to Final Segment, with GPT-4o mini Transcribe highlighted.
  1. #1Qwen3 ASR 1.7b39 ms
  2. #2STT RT v545 ms
  3. #3Qwen3 ASR Fast47 ms
  4. #4STT 167 ms
  5. #5Nova 385 ms
  6. #6Nova 287 ms
  7. #7Parakeet TDT 0.6B v397 ms
  8. #8Flux Multilingual98 ms
  9. #9Flux99 ms
  10. #10Scribe v2 Realtime122 ms
  11. #11Whisper Large v3via Baseten131 ms
  12. #12Universal 3.6 Pro135 ms
  13. #13Ink 2149 ms
  14. #14Universal 3.5 Pro168 ms
  15. #15Whisper Large v3via Together AI199 ms
  16. #16Pulse205 ms
  17. #17Grok STT223 ms
  18. #18resonant-1252 ms
  19. #19Default258 ms
  20. #20Linden 1271 ms
  21. #21Gemini 3.5 Transcribe Live317 ms
  22. #22Daytona STT399 ms
  23. #23Voxtral Mini Transcribe Realtime 2602411 ms
  24. #24GPT Realtime Whisper599 ms
  25. #25Solaria 1626 ms
  26. #26GPT-4o mini Transcribe708 ms
Show all 29 models
  1. #27Chirp 3768 ms
  2. #28GPT-4o Transcribe784 ms
  3. #29Chirp 2908 ms
median of all models · 199 ms
STT models over the last 30 days, ranked on Time to Final Segment.
#ModelHostTTFSWERTTFTSamples
1Qwen3 ASR 1.7bBaseten39 ms946 ms13,669
2STT RT v5Soniox45 ms1518 ms23,533
3Qwen3 ASR FastNari Labs47 ms1752 ms26,652
4STT 1Inworld AI67 ms1209 ms24,749
5Nova 3Deepgram85 ms1432 ms26,002
6Nova 2Deepgram87 ms1417 ms25,960
7Parakeet TDT 0.6B v3Together AI97 ms1228 ms26,461
8Flux MultilingualDeepgram98 ms1165 ms26,007
9FluxDeepgram99 ms1092 ms26,005
10Scribe v2 RealtimeElevenLabs122 ms2157 ms26,640
11Whisper Large v3Baseten131 ms924 ms13,663
12Universal 3.6 ProAssemblyAI135 ms1072 ms24,375
13Ink 2Cartesia149 ms1967 ms26,653
14Universal 3.5 ProAssemblyAI168 ms1026 ms26,654
15Whisper Large v3Together AI199 ms1261 ms26,446
16PulseSmallest205 ms1976 ms26,654
17Grok STTSpaceXAI223 ms—26,576
18resonant-1Reson8252 ms—26,653
19DefaultGradium258 ms1987 ms26,632
20Linden 1Speechmatics271 ms1537 ms26,595
21Gemini 3.5 Transcribe LiveGemini317 ms1607 ms26,566
22Daytona STTGuava399 ms5695 ms5,225
23Voxtral Mini Transcribe Realtime 2602Mistral411 ms1851 ms26,168
24GPT Realtime WhisperOpenAI599 ms1824 ms26,622
25Solaria 1Gladia626 ms1775 ms26,215
26GPT-4o mini TranscribeOpenAI708 ms—26,621
27Chirp 3Google768 ms5957 ms26,638
28GPT-4o TranscribeOpenAI784 ms—26,625
29Chirp 2Google908 ms6099 ms26,650
—Nemotron 3.5 ASR StreamingTogether AI—1544 ms26,549
—Universal StreamingAssemblyAI—1509 ms26,625
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: 11th of 31 on Word Error Rate.

Latency vs accuracy

TTFS vs WEREach point is one measured model · GPT-4o mini Transcribe highlighted · 30-day averagesTime to Final Segment against Word Error Rate for every measured STT model, with GPT-4o mini Transcribe highlighted.
Qwen3 ASR 1.7b — 39 ms, 2.9%STT RT v5 — 45 ms, 4.8%Qwen3 ASR Fast — 47 ms, 2.6%STT 1 — 67 ms, 7.1%Nova 3 — 85 ms, 5.3%Nova 2 — 87 ms, 6.7%Parakeet TDT 0.6B v3 — 97 ms, 11.1%Flux Multilingual — 98 ms, 7.5%Flux — 99 ms, 5.8%Scribe v2 Realtime — 122 ms, 4.4%Whisper Large v3 via Baseten — 131 ms, 4.5%Universal 3.6 Pro — 135 ms, 2.1%Ink 2 — 149 ms, 3.6%Universal 3.5 Pro — 168 ms, 2.3%Whisper Large v3 via Together AI — 199 ms, 7.4%Pulse — 205 ms, 4.6%Grok STT — 223 ms, 4.1%resonant-1 — 252 ms, 2.6%Default — 258 ms, 8.8%Linden 1 — 271 ms, 3.9%Gemini 3.5 Transcribe Live — 317 ms, 3.0%Daytona STT — 399 ms, 4.9%Voxtral Mini Transcribe Realtime 2602 — 411 ms, 5.3%GPT Realtime Whisper — 599 ms, 4.0%Solaria 1 — 626 ms, 6.0%Chirp 3 — 768 ms, 3.2%GPT-4o Transcribe — 784 ms, 3.7%Chirp 2 — 908 ms, 3.9%GPT-4o mini Transcribe — 708 ms, 3.9%

Where the errors come from

WER compositionGPT-4o mini Transcribe's Word Error Rate split by error type · 30-day averageGPT-4o mini Transcribe's WER split into substitutions, deletions and insertions.
  • GPT-4o mini Transcribe3.9%
SubstitutionsDeletionsInsertions

Averages and tail latency

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

GPT-4o mini Transcribe latency distributionMilliseconds · shared axis across metrics · last 30 daysGPT-4o mini Transcribe's latency percentiles per metric: p25–p75 band, p50 tick, whisker to max.
  • Time to Final Segmentp50 648 ms · Max 28470 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 Final Segment708 ms568 ms648 ms730 ms876 ms1055 ms28470 ms26,621
Word Error Rate3.9%0.0%0.0%6.3%12.5%20.0%125.0%26,621

Last 30 days

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

Time to Final Segment — daily p50Line p50 · band p25–p75 · UTC daysGPT-4o mini Transcribe's daily median Time to Final Segment over the last 30 days.
GPT-4o mini Transcribe · Sep 14: 645 msGPT-4o mini Transcribe · Sep 15: 675 msGPT-4o mini Transcribe · Sep 16: 656 msGPT-4o mini Transcribe · Sep 17: 655 msGPT-4o mini Transcribe · Sep 18: 643 msGPT-4o mini Transcribe · Sep 19: 579 msGPT-4o mini Transcribe · Sep 20: 567 msGPT-4o mini Transcribe · Sep 21: 681 msGPT-4o mini Transcribe · Sep 22: 690 msGPT-4o mini Transcribe · Sep 23: 732 msGPT-4o mini Transcribe · Sep 24: 670 msGPT-4o mini Transcribe · Sep 25: 679 msGPT-4o mini Transcribe · Sep 26: 532 msGPT-4o mini Transcribe · Sep 27: 566 msGPT-4o mini Transcribe · Sep 28: 611 msGPT-4o mini Transcribe · Sep 29: 657 msGPT-4o mini Transcribe · Sep 30: 707 msGPT-4o mini Transcribe · Oct 1: 638 msGPT-4o mini Transcribe · Oct 2: 694 msGPT-4o mini Transcribe · Oct 3: 589 msGPT-4o mini Transcribe · Oct 4: 581 msGPT-4o mini Transcribe · Oct 5: 661 msGPT-4o mini Transcribe · Oct 6: 682 msGPT-4o mini Transcribe · Oct 7: 666 msGPT-4o mini Transcribe · Oct 8: 622 msGPT-4o mini Transcribe · Oct 9: 634 msGPT-4o mini Transcribe · Oct 10: 562 msGPT-4o mini Transcribe · Oct 11: 572 msGPT-4o mini Transcribe · Oct 12: 632 msGPT-4o mini Transcribe · Oct 13: 666 msGPT-4o mini Transcribe · Oct 14: 641 ms
Word Error Rate — daily averageDaily average · UTC daysGPT-4o mini Transcribe's daily Word Error Rate over the last 30 days.
GPT-4o mini Transcribe · Sep 14: 5.0%GPT-4o mini Transcribe · Sep 15: 5.0%GPT-4o mini Transcribe · Sep 16: 5.6%GPT-4o mini Transcribe · Sep 17: 5.9%GPT-4o mini Transcribe · Sep 18: 5.3%GPT-4o mini Transcribe · Sep 19: 5.0%GPT-4o mini Transcribe · Sep 20: 5.9%GPT-4o mini Transcribe · Sep 21: 4.6%GPT-4o mini Transcribe · Sep 22: 5.4%GPT-4o mini Transcribe · Sep 23: 4.6%GPT-4o mini Transcribe · Sep 24: 5.8%GPT-4o mini Transcribe · Sep 25: 5.9%GPT-4o mini Transcribe · Sep 26: 5.8%GPT-4o mini Transcribe · Sep 27: 4.9%GPT-4o mini Transcribe · Sep 28: 3.9%GPT-4o mini Transcribe · Sep 29: 5.3%GPT-4o mini Transcribe · Sep 30: 5.1%GPT-4o mini Transcribe · Oct 1: 3.8%GPT-4o mini Transcribe · Oct 2: 3.4%GPT-4o mini Transcribe · Oct 3: 6.3%GPT-4o mini Transcribe · Oct 4: 6.1%GPT-4o mini Transcribe · Oct 5: 5.6%GPT-4o mini Transcribe · Oct 6: 6.5%GPT-4o mini Transcribe · Oct 7: 5.0%GPT-4o mini Transcribe · Oct 8: 4.7%GPT-4o mini Transcribe · Oct 9: 4.2%GPT-4o mini Transcribe · Oct 10: 5.1%GPT-4o mini Transcribe · Oct 11: 3.7%GPT-4o mini Transcribe · Oct 12: 5.0%GPT-4o mini Transcribe · Oct 13: 4.4%GPT-4o mini Transcribe · Oct 14: 5.7%

Time to Final Segment by dataset

GPT-4o mini Transcribe by test conditionMilliseconds · lower is better · best condition firstGPT-4o mini Transcribe's Time to Final Segment on each benchmark dataset.
  1. WildASR accents649 ms
  2. PipeCat (production)706 ms
  3. WildASR clean708 ms
  4. WildASR noise gaps713 ms
  5. WildASR phone codec730 ms
  6. WildASR clipping733 ms
  7. WildASR far-field746 ms
Time to Final Segment per dataset, with the number of samples behind each figure.
DatasetTTFSSamples
ProductionPipeCat706 ms14,003
AccentsWildASR649 ms1,402
CleanWildASR708 ms5,605
ClippingWildASR733 ms1,403
Far-fieldWildASR746 ms1,405
Noise gapsWildASR713 ms1,401
Phone codecWildASR730 ms1,402

Strongest condition: WildASR accents at 649 ms · weakest: WildASR far-field at 746 ms.

How fast is GPT-4o mini Transcribe?

On OpenAI, GPT-4o mini Transcribe measures mean 708 ms time to final segment (26th of 29). Last measured 2026-10-14.

How accurate is GPT-4o mini Transcribe?

On OpenAI, GPT-4o mini Transcribe measures 3.9% word error rate (11th of 31). Last measured 2026-10-14.

Who hosts GPT-4o mini Transcribe?

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

Limits of this comparison

The mini model receives the same audio as GPT-4o Transcribe for a direct accuracy and latency comparison.

  • The results apply to this API model and Coval configuration, not every batch or Realtime transcription workflow.

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