Voice AI BenchmarksBy

MISTRALSPEECH-TO-TEXT131,000 SAMPLES / 30 DAYSLAST RUN OCT 14, 2026, 06:00 UTC

official resource

Voxtral Mini Transcribe Realtime 2602 speech-to-text benchmarks

Voxtral Mini Transcribe Realtime 2602, hosted by Mistral, measures mean 410 ms time to final segment (23rd of 29) and 5.4% word error rate (21st of 31) among STT systems. Results cover the last 30 days. Coval benchmarks hosted endpoints daily using a consistent evaluation methodology. Last measured .

Voxtral Mini Transcribe Realtime 2602 is Mistral AI's compact real-time transcription release identified by its February 2026 suffix.

Time to Final Segment#23 / 29
410ms
Word Error Rate#21 / 31
5.4%
Time to First Token#20 / 27
1851ms

Overview

Voxtral Mini Transcribe belongs to Mistral's Voxtral audio family; the tested European endpoint is multilingual and open-weight.

Voxtral Mini Transcribe Realtime 2602 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
Mistral
Hosted by
Mistral
Source
Official API
Licensing
Open-weight
Deployment
Cloud
Region
Europe
Features
Multilingual

How Voxtral Mini Transcribe Realtime 2602 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 Voxtral Mini Transcribe Realtime 2602 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
  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 2602410 ms
Show all 29 models
  1. #24GPT Realtime Whisper599 ms
  2. #25Solaria 1636 ms
  3. #26GPT-4o mini Transcribe708 ms
  4. #27Chirp 3768 ms
  5. #28GPT-4o Transcribe783 ms
  6. #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: 21st of 31 on Word Error Rate.

Latency vs accuracy

TTFS vs WEREach point is one measured model · Voxtral Mini Transcribe Realtime 2602 highlighted · 30-day averagesTime to Final Segment against Word Error Rate for every measured STT model, with Voxtral Mini Transcribe Realtime 2602 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%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%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%Voxtral Mini Transcribe Realtime 2602 — 410 ms, 5.4%

Where the errors come from

WER compositionVoxtral Mini Transcribe Realtime 2602's Word Error Rate split by error type · 30-day averageVoxtral Mini Transcribe Realtime 2602's WER split into substitutions, deletions and insertions.
  • Voxtral Mini Transcribe Realtime 26025.4%
SubstitutionsDeletionsInsertions

Averages and tail latency

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

Voxtral Mini Transcribe Realtime 2602 latency distributionMilliseconds · shared axis across metrics · last 30 daysVoxtral Mini Transcribe Realtime 2602's latency percentiles per metric: p25–p75 band, p50 tick, whisker to max.
  • Time to Final Segmentp50 335 ms · Max 34706 ms
  • Time to First Tokenp50 1843 ms · Max 36932 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 Segment410 ms303 ms335 ms407 ms539 ms672 ms34706 ms26,200
Word Error Rate5.4%0.0%0.0%8.3%15.4%20.0%191.7%26,200
Time to First Token1851 ms1546 ms1843 ms2053 ms2433 ms2746 ms36932 ms26,200

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 daysVoxtral Mini Transcribe Realtime 2602's daily median Time to Final Segment over the last 30 days.
Voxtral Mini Transcribe Realtime 2602 · Sep 14: 370 msVoxtral Mini Transcribe Realtime 2602 · Sep 15: 347 msVoxtral Mini Transcribe Realtime 2602 · Sep 16: 329 msVoxtral Mini Transcribe Realtime 2602 · Sep 17: 341 msVoxtral Mini Transcribe Realtime 2602 · Sep 18: 321 msVoxtral Mini Transcribe Realtime 2602 · Sep 19: 298 msVoxtral Mini Transcribe Realtime 2602 · Sep 20: 300 msVoxtral Mini Transcribe Realtime 2602 · Sep 21: 350 msVoxtral Mini Transcribe Realtime 2602 · Sep 22: 358 msVoxtral Mini Transcribe Realtime 2602 · Sep 23: 373 msVoxtral Mini Transcribe Realtime 2602 · Sep 24: 351 msVoxtral Mini Transcribe Realtime 2602 · Sep 25: 361 msVoxtral Mini Transcribe Realtime 2602 · Sep 26: 311 msVoxtral Mini Transcribe Realtime 2602 · Sep 27: 310 msVoxtral Mini Transcribe Realtime 2602 · Sep 28: 364 msVoxtral Mini Transcribe Realtime 2602 · Sep 29: 363 msVoxtral Mini Transcribe Realtime 2602 · Sep 30: 345 msVoxtral Mini Transcribe Realtime 2602 · Oct 1: 354 msVoxtral Mini Transcribe Realtime 2602 · Oct 2: 333 msVoxtral Mini Transcribe Realtime 2602 · Oct 3: 323 msVoxtral Mini Transcribe Realtime 2602 · Oct 4: 308 msVoxtral Mini Transcribe Realtime 2602 · Oct 5: 339 msVoxtral Mini Transcribe Realtime 2602 · Oct 6: 373 msVoxtral Mini Transcribe Realtime 2602 · Oct 7: 351 msVoxtral Mini Transcribe Realtime 2602 · Oct 8: 370 msVoxtral Mini Transcribe Realtime 2602 · Oct 9: 326 msVoxtral Mini Transcribe Realtime 2602 · Oct 10: 318 msVoxtral Mini Transcribe Realtime 2602 · Oct 11: 307 msVoxtral Mini Transcribe Realtime 2602 · Oct 12: 365 msVoxtral Mini Transcribe Realtime 2602 · Oct 13: 373 msVoxtral Mini Transcribe Realtime 2602 · Oct 14: 356 ms
Word Error Rate — daily averageDaily average · UTC daysVoxtral Mini Transcribe Realtime 2602's daily Word Error Rate over the last 30 days.
Voxtral Mini Transcribe Realtime 2602 · Sep 14: 6.2%Voxtral Mini Transcribe Realtime 2602 · Sep 15: 7.4%Voxtral Mini Transcribe Realtime 2602 · Sep 16: 5.5%Voxtral Mini Transcribe Realtime 2602 · Sep 17: 8.2%Voxtral Mini Transcribe Realtime 2602 · Sep 18: 6.8%Voxtral Mini Transcribe Realtime 2602 · Sep 19: 5.2%Voxtral Mini Transcribe Realtime 2602 · Sep 20: 6.5%Voxtral Mini Transcribe Realtime 2602 · Sep 21: 7.5%Voxtral Mini Transcribe Realtime 2602 · Sep 22: 7.4%Voxtral Mini Transcribe Realtime 2602 · Sep 23: 4.8%Voxtral Mini Transcribe Realtime 2602 · Sep 24: 7.5%Voxtral Mini Transcribe Realtime 2602 · Sep 25: 8.6%Voxtral Mini Transcribe Realtime 2602 · Sep 26: 6.4%Voxtral Mini Transcribe Realtime 2602 · Sep 27: 6.9%Voxtral Mini Transcribe Realtime 2602 · Sep 28: 7.6%Voxtral Mini Transcribe Realtime 2602 · Sep 29: 5.9%Voxtral Mini Transcribe Realtime 2602 · Sep 30: 6.7%Voxtral Mini Transcribe Realtime 2602 · Oct 1: 6.7%Voxtral Mini Transcribe Realtime 2602 · Oct 2: 6.8%Voxtral Mini Transcribe Realtime 2602 · Oct 3: 7.5%Voxtral Mini Transcribe Realtime 2602 · Oct 4: 7.1%Voxtral Mini Transcribe Realtime 2602 · Oct 5: 6.8%Voxtral Mini Transcribe Realtime 2602 · Oct 6: 7.8%Voxtral Mini Transcribe Realtime 2602 · Oct 7: 6.4%Voxtral Mini Transcribe Realtime 2602 · Oct 8: 7.0%Voxtral Mini Transcribe Realtime 2602 · Oct 9: 6.6%Voxtral Mini Transcribe Realtime 2602 · Oct 10: 4.1%Voxtral Mini Transcribe Realtime 2602 · Oct 11: 7.1%Voxtral Mini Transcribe Realtime 2602 · Oct 12: 7.0%Voxtral Mini Transcribe Realtime 2602 · Oct 13: 7.6%Voxtral Mini Transcribe Realtime 2602 · Oct 14: 9.4%

Time to Final Segment by dataset

Voxtral Mini Transcribe Realtime 2602 by test conditionMilliseconds · lower is better · best condition firstVoxtral Mini Transcribe Realtime 2602's Time to Final Segment on each benchmark dataset.
  1. WildASR accents400 ms
  2. WildASR noise gaps401 ms
  3. WildASR far-field406 ms
  4. PipeCat (production)409 ms
  5. WildASR clean412 ms
  6. WildASR phone codec427 ms
  7. WildASR clipping429 ms
Time to Final Segment per dataset, with the number of samples behind each figure.
DatasetTTFSSamples
ProductionPipeCat409 ms13,808
AccentsWildASR400 ms1,387
CleanWildASR412 ms5,518
ClippingWildASR429 ms1,344
Far-fieldWildASR406 ms1,381
Noise gapsWildASR401 ms1,382
Phone codecWildASR427 ms1,380

Strongest condition: WildASR accents at 400 ms · weakest: WildASR clipping at 429 ms.

How fast is Voxtral Mini Transcribe Realtime 2602?

On Mistral, Voxtral Mini Transcribe Realtime 2602 measures mean 410 ms time to final segment (23rd of 29) and mean 1851 ms time to first token (20th of 27). Last measured 2026-10-14.

How accurate is Voxtral Mini Transcribe Realtime 2602?

On Mistral, Voxtral Mini Transcribe Realtime 2602 measures 5.4% word error rate (21st of 31). Last measured 2026-10-14.

Who hosts Voxtral Mini Transcribe Realtime 2602?

Voxtral Mini Transcribe Realtime 2602 is created by Mistral and served by Mistral. Coval measures each hosted endpoint separately.

Limits of this comparison

Results remain attached to this version if a later release becomes available.

  • A dated identifier can be superseded, so results remain attached to 2602 rather than silently following a newer alias.

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