Voice AI BenchmarksBy

RESON8SPEECH-TO-TEXT91,549 SAMPLES / 30 DAYSLAST RUN SEP 15, 2026, 08:30 UTC

official resource

resonant-1 speech-to-text benchmarks

resonant-1, hosted by Reson8, measures mean 264 ms time to final segment (18th of 28) and 3.4% word error rate (3rd of 30) among STT systems. Results cover the last 30 days. Coval benchmarks hosted endpoints daily using a consistent evaluation methodology. Last measured .

Realtime is Reson8's streaming transcription endpoint.

Time to Final Segment#18 / 28
264ms
Word Error Rate#3 / 30
3.4%

Overview

The configured European service is multilingual and includes diarization plus keyterm controls.

resonant-1 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
Reson8
Hosted by
Reson8
Source
Official API
Licensing
Proprietary
Deployment
Cloud
Region
Europe
Features
Diarization, Keyterm biasing, Multilingual

How resonant-1 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 resonant-1 highlighted.
  1. #1Qwen3 ASR 1.7b39 ms
  2. #2Qwen3 ASR Fast46 ms
  3. #3STT RT v557 ms
  4. #4STT 165 ms
  5. #5Parakeet TDT 0.6B v381 ms
  6. #6Nova 389 ms
  7. #7Nova 292 ms
  8. #8Flux Multilingual98 ms
  9. #9Flux99 ms
  10. #10Ink 2122 ms
  11. #11Whisper Large v3via Baseten125 ms
  12. #12Scribe v2 Realtime133 ms
  13. #13Universal 3.5 Pro173 ms
  14. #14Grok STT207 ms
  15. #15Defaultvia Speechmatics209 ms
  16. #16Pulse212 ms
  17. #17Defaultvia Gradium246 ms
  18. #18resonant-1264 ms
Show all 28 models
  1. #19Whisper Large v3via Together AI295 ms
  2. #20Enhanced299 ms
  3. #21Gemini 3.5 Transcribe Live305 ms
  4. #22Voxtral Mini Transcribe Realtime 2602401 ms
  5. #23GPT Realtime Whisper551 ms
  6. #24GPT-4o mini Transcribe690 ms
  7. #25GPT-4o Transcribe754 ms
  8. #26Chirp 3776 ms
  9. #27Solaria 1805 ms
  10. #28Chirp 2873 ms
median of all models · 208 ms
STT models over the last 30 days, ranked on Time to Final Segment.
#ModelHostTTFSWERTTFTSamples
1Qwen3 ASR 1.7bBaseten39 ms931 ms1,256
2Qwen3 ASR FastNari46 ms1748 ms4,451
3STT RT v5Soniox57 ms1529 ms22,468
4STT 1Inworld AI65 ms1400 ms22,836
5Parakeet TDT 0.6B v3Together AI81 ms1215 ms22,488
6Nova 3Deepgram89 ms1419 ms22,855
7Nova 2Deepgram92 ms1420 ms22,733
8Flux MultilingualDeepgram98 ms1164 ms12,251
9FluxDeepgram99 ms1076 ms12,243
10Ink 2Cartesia122 ms1827 ms22,862
11Whisper Large v3Baseten125 ms912 ms1,252
12Scribe v2 RealtimeElevenLabs133 ms2175 ms22,866
13Universal 3.5 ProAssemblyAI173 ms1041 ms20,253
14Grok STTxAI207 ms—22,853
15DefaultSpeechmatics209 ms1428 ms22,876
16PulseSmallest212 ms2011 ms22,856
17DefaultGradium246 ms1980 ms22,839
18resonant-1Reson8264 ms—22,860
19Whisper Large v3Together AI295 ms1338 ms22,744
20EnhancedSpeechmatics299 ms1492 ms22,876
21Gemini 3.5 Transcribe LiveGemini305 ms1679 ms16,403
22Voxtral Mini Transcribe Realtime 2602Mistral401 ms1851 ms22,583
23GPT Realtime WhisperOpenAI551 ms1814 ms22,812
24GPT-4o mini TranscribeOpenAI690 ms—22,830
25GPT-4o TranscribeOpenAI754 ms—22,831
26Chirp 3Google776 ms5974 ms22,875
27Solaria 1Gladia805 ms1804 ms22,439
28Chirp 2Google873 ms6071 ms22,789
—Nemotron 3.5 ASR StreamingTogether AI—1548 ms22,747
—Universal StreamingAssemblyAI—1514 ms20,235
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: 3rd of 30 on Word Error Rate.

Latency vs accuracy

TTFS vs WEREach point is one measured model · resonant-1 highlighted · 30-day averagesTime to Final Segment against Word Error Rate for every measured STT model, with resonant-1 highlighted.
Qwen3 ASR 1.7b — 39 ms, 4.1%Qwen3 ASR Fast — 46 ms, 3.2%STT RT v5 — 57 ms, 5.7%STT 1 — 65 ms, 4.4%Parakeet TDT 0.6B v3 — 81 ms, 11.2%Nova 3 — 89 ms, 6.2%Nova 2 — 92 ms, 7.9%Flux Multilingual — 98 ms, 8.8%Flux — 99 ms, 6.7%Ink 2 — 122 ms, 4.8%Whisper Large v3 via Baseten — 125 ms, 5.6%Scribe v2 Realtime — 133 ms, 5.5%Universal 3.5 Pro — 173 ms, 3.1%Grok STT — 207 ms, 4.6%Default via Speechmatics — 209 ms, 5.4%Pulse — 212 ms, 5.3%Default via Gradium — 246 ms, 10.0%Whisper Large v3 via Together AI — 295 ms, 8.5%Enhanced — 299 ms, 4.3%Gemini 3.5 Transcribe Live — 305 ms, 3.9%Voxtral Mini Transcribe Realtime 2602 — 401 ms, 6.2%GPT Realtime Whisper — 551 ms, 5.1%GPT-4o mini Transcribe — 690 ms, 4.9%GPT-4o Transcribe — 754 ms, 4.6%Chirp 3 — 776 ms, 4.1%Solaria 1 — 805 ms, 7.1%Chirp 2 — 873 ms, 4.9%resonant-1 — 264 ms, 3.4%

Where the errors come from

WER compositionresonant-1's Word Error Rate split by error type · 30-day averageresonant-1's WER split into substitutions, deletions and insertions.
  • resonant-13.4%
SubstitutionsDeletionsInsertions

Averages and tail latency

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

resonant-1 latency distributionMilliseconds · shared axis across metrics · last 30 daysresonant-1's latency percentiles per metric: p25–p75 band, p50 tick, whisker to p99.
  • Time to Final Segmentp50 264 ms · p99 324 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 Final Segment264 ms248 ms264 ms278 ms288 ms299 ms324 ms22,860
Word Error Rate3.4%0.0%0.0%4.5%10.0%15.4%32.2%22,896

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 daysresonant-1's daily median Time to Final Segment over the last 30 days.
resonant-1 · Sep 1: 257 msresonant-1 · Sep 2: 259 msresonant-1 · Sep 3: 261 msresonant-1 · Sep 4: 264 msresonant-1 · Sep 5: 260 msresonant-1 · Sep 6: 268 msresonant-1 · Sep 7: 264 msresonant-1 · Sep 8: 266 msresonant-1 · Sep 9: 264 msresonant-1 · Sep 10: 263 msresonant-1 · Sep 11: 264 msresonant-1 · Sep 12: 251 msresonant-1 · Sep 13: 263 msresonant-1 · Sep 14: 267 msresonant-1 · Sep 15: 260 ms
Word Error Rate — daily averageDaily average · UTC daysresonant-1's daily Word Error Rate over the last 30 days.
resonant-1 · Sep 1: 4.9%resonant-1 · Sep 2: 4.1%resonant-1 · Sep 3: 3.8%resonant-1 · Sep 4: 3.7%resonant-1 · Sep 5: 3.6%resonant-1 · Sep 6: 4.1%resonant-1 · Sep 7: 3.7%resonant-1 · Sep 8: 4.0%resonant-1 · Sep 9: 3.9%resonant-1 · Sep 10: 3.2%resonant-1 · Sep 11: 3.8%resonant-1 · Sep 12: 3.3%resonant-1 · Sep 13: 4.6%resonant-1 · Sep 14: 4.4%resonant-1 · Sep 15: 3.6%

Time to Final Segment by dataset

resonant-1 by test conditionMilliseconds · lower is better · best condition firstresonant-1's Time to Final Segment on each benchmark dataset.
  1. WildASR accents247 ms
  2. WildASR reverb261 ms
  3. WildASR clipping262 ms
  4. WildASR phone codec262 ms
  5. WildASR noise gaps264 ms
  6. WildASR far-field264 ms
  7. WildASR clean265 ms
  8. PipeCat (production)266 ms
Time to Final Segment per dataset, with the number of samples behind each figure.
DatasetTTFSSamples
LibriSpeech303 ms1
ProductionPipeCat266 ms11,520
AccentsWildASR247 ms1,117
CleanWildASR265 ms4,579
ClippingWildASR262 ms1,140
Far-fieldWildASR264 ms1,143
Noise gapsWildASR264 ms1,143
Phone codecWildASR262 ms1,138
ReverbWildASR261 ms1,079

Strongest condition: WildASR accents at 247 ms · weakest: LibriSpeech at 303 ms.

How fast is resonant-1?

On Reson8, resonant-1 measures mean 264 ms time to final segment (18th of 28). Last measured 2026-09-15.

How accurate is resonant-1?

On Reson8, resonant-1 measures 3.4% word error rate (3rd of 30). Last measured 2026-09-15.

Who hosts resonant-1?

resonant-1 is created by Reson8 and served by Reson8. Coval measures each hosted endpoint separately.

Limits of this comparison

Because the model name is generic, these results refer specifically to the endpoint served by Reson8.

  • These results do not apply to similarly named real-time transcription endpoints from other providers.

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