Voice AI BenchmarksBy

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

official resource

Solaria 1 speech-to-text benchmarks

Solaria 1, hosted by Gladia, measures mean 636 ms time to final segment (25th of 29) and 6.0% word error rate (24th of 31) among STT systems. Results cover the last 30 days. Coval benchmarks hosted endpoints daily using a consistent evaluation methodology. Last measured .

Solaria 1 is Gladia's real-time speech recognition model.

Time to Final Segment#25 / 29
636ms
Word Error Rate#24 / 31
6%
Time to First Token#18 / 27
1780ms

Overview

Gladia's service combines multilingual transcription with translation and code switching; Coval's endpoint also includes voice activity and keyterm controls.

Solaria 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
Gladia
Hosted by
Gladia
Source
Official API
Licensing
Proprietary
Deployment
Cloud
Region
Europe
Features
Code switching, Keyterm biasing, Multilingual, Translation, VAD

How Solaria 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 Solaria 1 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
  24. #24GPT Realtime Whisper599 ms
  25. #25Solaria 1636 ms
Show all 29 models
  1. #26GPT-4o mini Transcribe708 ms
  2. #27Chirp 3768 ms
  3. #28GPT-4o Transcribe783 ms
  4. #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 ms1211 ms24,749
5Nova 3Deepgram85 ms1431 ms26,002
6Nova 2Deepgram87 ms1417 ms25,960
7Parakeet TDT 0.6B v3Together AI97 ms1228 ms26,461
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 ms24,223
13Ink 2Cartesia148 ms1966 ms26,652
14Universal 3.5 ProAssemblyAI168 ms1026 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 ms1780 ms26,200
26GPT-4o mini TranscribeOpenAI708 ms—26,621
27Chirp 3Google768 ms5957 ms26,638
28GPT-4o TranscribeOpenAI783 ms—26,625
29Chirp 2Google908 ms6098 ms26,650
—Nemotron 3.5 ASR StreamingTogether AI—1544 ms26,542
—Universal StreamingAssemblyAI—1509 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: 18th of 27 on Time to First Token.

Latency vs accuracy

TTFS vs WEREach point is one measured model · Solaria 1 highlighted · 30-day averagesTime to Final Segment against Word Error Rate for every measured STT model, with Solaria 1 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%Voxtral Mini Transcribe Realtime 2602 — 410 ms, 5.4%GPT Realtime Whisper — 599 ms, 4.0%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%Solaria 1 — 636 ms, 6.0%

Where the errors come from

WER compositionSolaria 1's Word Error Rate split by error type · 30-day averageSolaria 1's WER split into substitutions, deletions and insertions.
  • Solaria 16.0%
SubstitutionsDeletionsInsertions

Averages and tail latency

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

Solaria 1 latency distributionMilliseconds · shared axis across metrics · last 30 daysSolaria 1's latency percentiles per metric: p25–p75 band, p50 tick, whisker to max.
  • Time to Final Segmentp50 384 ms · Max 18262 ms
  • Time to First Tokenp50 1599 ms · Max 26400 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 Segment636 ms322 ms384 ms496 ms872 ms1732 ms18262 ms26,200
Word Error Rate6.0%0.0%3.3%9.7%17.2%23.5%128.6%26,200
Time to First Token1780 ms1202 ms1599 ms1883 ms2508 ms3301 ms26400 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 daysSolaria 1's daily median Time to Final Segment over the last 30 days.
Solaria 1 · Sep 14: 811 msSolaria 1 · Sep 15: 706 msSolaria 1 · Sep 16: 574 msSolaria 1 · Sep 17: 555 msSolaria 1 · Sep 18: 384 msSolaria 1 · Sep 19: 388 msSolaria 1 · Sep 20: 375 msSolaria 1 · Sep 21: 437 msSolaria 1 · Sep 22: 422 msSolaria 1 · Sep 23: 406 msSolaria 1 · Sep 24: 472 msSolaria 1 · Sep 25: 373 msSolaria 1 · Sep 26: 358 msSolaria 1 · Sep 27: 330 msSolaria 1 · Sep 28: 356 msSolaria 1 · Sep 29: 391 msSolaria 1 · Sep 30: 445 msSolaria 1 · Oct 1: 371 msSolaria 1 · Oct 2: 448 msSolaria 1 · Oct 3: 329 msSolaria 1 · Oct 4: 355 msSolaria 1 · Oct 5: 378 msSolaria 1 · Oct 6: 396 msSolaria 1 · Oct 7: 398 msSolaria 1 · Oct 8: 362 msSolaria 1 · Oct 9: 400 msSolaria 1 · Oct 10: 325 msSolaria 1 · Oct 11: 342 msSolaria 1 · Oct 12: 319 msSolaria 1 · Oct 13: 353 msSolaria 1 · Oct 14: 352 ms
Word Error Rate — daily averageDaily average · UTC daysSolaria 1's daily Word Error Rate over the last 30 days.
Solaria 1 · Sep 14: 9.4%Solaria 1 · Sep 15: 6.4%Solaria 1 · Sep 16: 6.6%Solaria 1 · Sep 17: 7.0%Solaria 1 · Sep 18: 6.8%Solaria 1 · Sep 19: 6.5%Solaria 1 · Sep 20: 7.4%Solaria 1 · Sep 21: 8.0%Solaria 1 · Sep 22: 6.1%Solaria 1 · Sep 23: 7.2%Solaria 1 · Sep 24: 7.3%Solaria 1 · Sep 25: 7.0%Solaria 1 · Sep 26: 6.9%Solaria 1 · Sep 27: 6.5%Solaria 1 · Sep 28: 6.3%Solaria 1 · Sep 29: 6.5%Solaria 1 · Sep 30: 7.7%Solaria 1 · Oct 1: 7.1%Solaria 1 · Oct 2: 6.5%Solaria 1 · Oct 3: 7.4%Solaria 1 · Oct 4: 7.1%Solaria 1 · Oct 5: 8.2%Solaria 1 · Oct 6: 8.4%Solaria 1 · Oct 7: 6.5%Solaria 1 · Oct 8: 7.3%Solaria 1 · Oct 9: 6.6%Solaria 1 · Oct 10: 5.8%Solaria 1 · Oct 11: 6.1%Solaria 1 · Oct 12: 7.0%Solaria 1 · Oct 13: 6.8%Solaria 1 · Oct 14: 6.6%

Time to Final Segment by dataset

Solaria 1 by test conditionMilliseconds · lower is better · best condition firstSolaria 1's Time to Final Segment on each benchmark dataset.
  1. WildASR noise gaps587 ms
  2. WildASR phone codec609 ms
  3. WildASR clean616 ms
  4. WildASR far-field637 ms
  5. PipeCat (production)640 ms
  6. WildASR clipping669 ms
  7. WildASR accents708 ms
Time to Final Segment per dataset, with the number of samples behind each figure.
DatasetTTFSSamples
ProductionPipeCat640 ms13,790
AccentsWildASR708 ms1,375
CleanWildASR616 ms5,516
ClippingWildASR669 ms1,379
Far-fieldWildASR637 ms1,378
Noise gapsWildASR587 ms1,382
Phone codecWildASR609 ms1,380

Strongest condition: WildASR noise gaps at 587 ms · weakest: WildASR accents at 708 ms.

How fast is Solaria 1?

On Gladia, Solaria 1 measures mean 636 ms time to final segment (25th of 29) and mean 1780 ms time to first token (18th of 27). Last measured 2026-10-14.

How accurate is Solaria 1?

On Gladia, Solaria 1 measures 6.0% word error rate (24th of 31). Last measured 2026-10-14.

Who hosts Solaria 1?

Solaria 1 is created by Gladia and served by Gladia. Coval measures each hosted endpoint separately.

Limits of this comparison

Coval evaluates the official API on fixed inputs, including difficult acoustic conditions a clean-only score would hide.

  • Coval scores transcription accuracy and timing, not translation quality or a complete language matrix.

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