Voice AI BenchmarksBy

SPACEXAISPEECH-TO-TEXT106,305 SAMPLES / 30 DAYSLAST RUN OCT 14, 2026, 06:00 UTC

official resource

Grok STT speech-to-text benchmarks

Grok STT, hosted by SpaceXAI, measures mean 223 ms time to final segment (17th of 29) and 4.1% word error rate (14th of 31) among STT systems. Results cover the last 30 days. Coval benchmarks hosted endpoints daily using a consistent evaluation methodology. Last measured .

Grok STT is SpaceXAI's managed streaming speech-to-text offering.

Time to Final Segment#17 / 29
223ms
Word Error Rate#14 / 31
4.1%

Overview

The tested endpoint supports multilingual transcription, diarization and keyterm biasing.

Grok STT 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
SpaceXAI
Hosted by
SpaceXAI
Source
Official API
Licensing
Proprietary
Deployment
Cloud
Region
US
Features
Diarization, Keyterm biasing, Multilingual, VAD

How Grok STT 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 Grok STT highlighted.
  1. #1Qwen3 ASR 1.7b39 ms
  2. #2STT RT v545 ms
  3. #3Qwen3 ASR Fast47 ms
  4. #4STT 166 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 2148 ms
  14. #14Universal 3.5 Pro168 ms
  15. #15Whisper Large v3via Together AI200 ms
  16. #16Pulse205 ms
  17. #17Grok STT223 ms
Show all 29 models
  1. #18resonant-1252 ms
  2. #19Default258 ms
  3. #20Linden 1271 ms
  4. #21Gemini 3.5 Transcribe Live317 ms
  5. #22Daytona STT399 ms
  6. #23Voxtral Mini Transcribe Realtime 2602410 ms
  7. #24GPT Realtime Whisper599 ms
  8. #25Solaria 1636 ms
  9. #26GPT-4o mini Transcribe708 ms
  10. #27Chirp 3768 ms
  11. #28GPT-4o Transcribe783 ms
  12. #29Chirp 2908 ms
median of all models · 200 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 AI66 ms1212 ms24,749
5Nova 3Deepgram85 ms1431 ms26,002
6Nova 2Deepgram87 ms1417 ms25,960
7Parakeet TDT 0.6B v3Together AI97 ms1228 ms26,460
8Flux MultilingualDeepgram98 ms1165 ms26,007
9FluxDeepgram99 ms1091 ms26,005
10Scribe v2 RealtimeElevenLabs122 ms2158 ms26,640
11Whisper Large v3Baseten131 ms924 ms13,663
12Universal 3.6 ProAssemblyAI135 ms1071 ms24,185
13Ink 2Cartesia148 ms1966 ms26,652
14Universal 3.5 ProAssemblyAI168 ms1025 ms26,654
15Whisper Large v3Together AI200 ms1261 ms26,445
16PulseSmallest205 ms1976 ms26,654
17Grok STTSpaceXAI223 ms—26,576
18resonant-1Reson8252 ms—26,653
19DefaultGradium258 ms1986 ms26,632
20Linden 1Speechmatics271 ms1537 ms26,595
21Gemini 3.5 Transcribe LiveGemini317 ms1609 ms26,567
22Daytona STTGuava399 ms5695 ms5,225
23Voxtral Mini Transcribe Realtime 2602Mistral410 ms1851 ms26,200
24GPT Realtime WhisperOpenAI599 ms1824 ms26,622
25Solaria 1Gladia636 ms1781 ms26,198
26GPT-4o mini TranscribeOpenAI708 ms—26,621
27Chirp 3Google768 ms5956 ms26,638
28GPT-4o TranscribeOpenAI783 ms—26,625
29Chirp 2Google908 ms6098 ms26,650
—Nemotron 3.5 ASR StreamingTogether AI—1544 ms26,542
—Universal StreamingAssemblyAI—1508 ms26,624
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: 14th of 31 on Word Error Rate.

Latency vs accuracy

TTFS vs WEREach point is one measured model · Grok STT highlighted · 30-day averagesTime to Final Segment against Word Error Rate for every measured STT model, with Grok STT 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 — 66 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 — 148 ms, 3.6%Universal 3.5 Pro — 168 ms, 2.4%Whisper Large v3 via Together AI — 200 ms, 7.4%Pulse — 205 ms, 4.6%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 — 410 ms, 5.4%GPT Realtime Whisper — 599 ms, 4.0%Solaria 1 — 636 ms, 6.0%GPT-4o mini Transcribe — 708 ms, 3.9%Chirp 3 — 768 ms, 3.2%GPT-4o Transcribe — 783 ms, 3.8%Chirp 2 — 908 ms, 3.9%Grok STT — 223 ms, 4.1%

Where the errors come from

WER compositionGrok STT's Word Error Rate split by error type · 30-day averageGrok STT's WER split into substitutions, deletions and insertions.
  • Grok STT4.1%
SubstitutionsDeletionsInsertions

Averages and tail latency

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

Grok STT latency distributionMilliseconds · shared axis across metrics · last 30 daysGrok STT's latency percentiles per metric: p25–p75 band, p50 tick, whisker to max.
  • Time to Final Segmentp50 192 ms · Max 13563 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 Segment223 ms155 ms192 ms253 ms337 ms405 ms13563 ms26,576
Word Error Rate4.1%0.0%0.0%6.3%13.6%20.0%1220.0%26,577

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 daysGrok STT's daily median Time to Final Segment over the last 30 days.
Grok STT · Sep 14: 243 msGrok STT · Sep 15: 183 msGrok STT · Sep 16: 198 msGrok STT · Sep 17: 201 msGrok STT · Sep 18: 198 msGrok STT · Sep 19: 337 msGrok STT · Sep 20: 283 msGrok STT · Sep 21: 334 msGrok STT · Sep 22: 323 msGrok STT · Sep 23: 295 msGrok STT · Sep 24: 299 msGrok STT · Sep 25: 209 msGrok STT · Sep 26: 191 msGrok STT · Sep 27: 196 msGrok STT · Sep 28: 197 msGrok STT · Sep 29: 195 msGrok STT · Sep 30: 191 msGrok STT · Oct 1: 166 msGrok STT · Oct 2: 157 msGrok STT · Oct 3: 149 msGrok STT · Oct 4: 154 msGrok STT · Oct 5: 154 msGrok STT · Oct 6: 156 msGrok STT · Oct 7: 143 msGrok STT · Oct 8: 157 msGrok STT · Oct 9: 161 msGrok STT · Oct 10: 156 msGrok STT · Oct 11: 156 msGrok STT · Oct 12: 163 msGrok STT · Oct 13: 153 msGrok STT · Oct 14: 160 ms
Word Error Rate — daily averageDaily average · UTC daysGrok STT's daily Word Error Rate over the last 30 days.
Grok STT · Sep 14: 4.3%Grok STT · Sep 15: 4.0%Grok STT · Sep 16: 3.9%Grok STT · Sep 17: 12.2%Grok STT · Sep 18: 3.6%Grok STT · Sep 19: 5.8%Grok STT · Sep 20: 4.9%Grok STT · Sep 21: 5.8%Grok STT · Sep 22: 6.0%Grok STT · Sep 23: 5.7%Grok STT · Sep 24: 7.3%Grok STT · Sep 25: 4.9%Grok STT · Sep 26: 4.5%Grok STT · Sep 27: 4.8%Grok STT · Sep 28: 6.1%Grok STT · Sep 29: 4.4%Grok STT · Sep 30: 5.1%Grok STT · Oct 1: 5.3%Grok STT · Oct 2: 4.6%Grok STT · Oct 3: 5.0%Grok STT · Oct 4: 5.7%Grok STT · Oct 5: 6.2%Grok STT · Oct 6: 7.6%Grok STT · Oct 7: 4.5%Grok STT · Oct 8: 7.4%Grok STT · Oct 9: 6.3%Grok STT · Oct 10: 4.7%Grok STT · Oct 11: 4.9%Grok STT · Oct 12: 5.2%Grok STT · Oct 13: 6.2%Grok STT · Oct 14: 5.5%

Time to Final Segment by dataset

Grok STT by test conditionMilliseconds · lower is better · best condition firstGrok STT's Time to Final Segment on each benchmark dataset.
  1. WildASR phone codec195 ms
  2. WildASR accents208 ms
  3. WildASR noise gaps217 ms
  4. WildASR clean226 ms
  5. PipeCat (production)226 ms
  6. WildASR far-field226 ms
  7. WildASR clipping236 ms
Time to Final Segment per dataset, with the number of samples behind each figure.
DatasetTTFSSamples
ProductionPipeCat226 ms13,984
AccentsWildASR208 ms1,399
CleanWildASR226 ms5,593
ClippingWildASR236 ms1,399
Far-fieldWildASR226 ms1,402
Noise gapsWildASR217 ms1,397
Phone codecWildASR195 ms1,402

Strongest condition: WildASR phone codec at 195 ms · weakest: WildASR clipping at 236 ms.

How fast is Grok STT?

On SpaceXAI, Grok STT measures mean 223 ms time to final segment (17th of 29). Last measured 2026-10-14.

How accurate is Grok STT?

On SpaceXAI, Grok STT measures 4.1% word error rate (14th of 31). Last measured 2026-10-14.

Who hosts Grok STT?

Grok STT is created by SpaceXAI and served by SpaceXAI. Coval measures each hosted endpoint separately.

Limits of this comparison

Coval measures both the text it returns and how quickly its streaming results arrive through SpaceXAI's official API.

  • The service is evolving; SpaceXAI's official documentation remains the source for current languages, limits and feature availability.

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