Voice AI BenchmarksBy

GOOGLESPEECH-TO-TEXT136,428 SAMPLES / 30 DAYSLAST RUN NOV 2, 2026, 09:00 UTC

Gemini 3.5 Transcribe Live speech-to-text benchmarks

Gemini 3.5 Transcribe Live, hosted by Gemini, measures mean 383 ms time to final segment (22nd of 28) and 2.9% word error rate (6th of 30) among STT systems. Results cover the last 30 days. Coval benchmarks hosted endpoints daily using a consistent evaluation methodology. Last measured .

Coval has active speech-to-text measurements for Gemini 3.5 Transcribe Live, created by Google and served on Gemini.

Time to Final Segment#22 / 28
383ms
Word Error Rate#6 / 30
2.9%
Time to First Token#15 / 28
1542ms

Overview

Gemini 3.5 Transcribe Live 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
Google
Hosted by
Gemini
Source
Official API
Licensing
Proprietary
Deployment
Cloud
Region
US
Features
Keyterm biasing, Multilingual, VAD

How Gemini 3.5 Transcribe Live 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 Gemini 3.5 Transcribe Live highlighted.
  1. #1Qwen3 ASR 1.7b35 ms
  2. #2STT RT v544 ms
  3. #3Qwen3 ASR Fast50 ms
  4. #4STT 170 ms
  5. #5Nova 385 ms
  6. #6Nova 287 ms
  7. #7Parakeet TDT 0.6B v388 ms
  8. #8Flux Multilingual100 ms
  9. #9Flux101 ms
  10. #10Universal 3.6 Pro114 ms
  11. #11Scribe v2 Realtime118 ms
  12. #12Whisper Large v3via Baseten126 ms
  13. #13Universal 3.5 Pro126 ms
  14. #14Ink 2146 ms
  15. #15Realtime Global159 ms
  16. #16Whisper Large v3via Together AI174 ms
  17. #17Grok STT180 ms
  18. #18Pulse203 ms
  19. #19resonant-1243 ms
  20. #20Linden 1254 ms
  21. #21Default261 ms
  22. #22Gemini 3.5 Transcribe Live383 ms
Show all 28 models
  1. #23Daytona STT384 ms
  2. #24Solaria 1414 ms
  3. #25Voxtral Mini Transcribe Realtime 2602436 ms
  4. #26GPT Realtime Whisper563 ms
  5. #27Chirp 3807 ms
  6. #28Chirp 2895 ms
median of all models · 152 ms
STT models over the last 30 days, ranked on Time to Final Segment.
#ModelHostTTFSWERTTFTSamples
1Qwen3 ASR 1.7bBaseten35 ms936 ms13,678
2STT RT v5Soniox44 ms1525 ms27,365
3Qwen3 ASR FastNari Labs50 ms1755 ms27,371
4STT 1Inworld AI70 ms1026 ms27,334
5Nova 3Deepgram85 ms1444 ms27,364
6Nova 2Deepgram87 ms1427 ms27,311
7Parakeet TDT 0.6B v3Together AI88 ms1197 ms15,445
8Flux MultilingualDeepgram100 ms1174 ms27,365
9FluxDeepgram101 ms1097 ms27,371
10Universal 3.6 ProAssemblyAI114 ms1079 ms27,335
11Scribe v2 RealtimeElevenLabs118 ms2151 ms27,366
12Whisper Large v3Baseten126 ms914 ms13,674
13Universal 3.5 ProAssemblyAI126 ms1019 ms27,373
14Ink 2Cartesia146 ms2034 ms27,369
15Realtime GlobalReson8159 ms2060 ms22,469
16Whisper Large v3Together AI174 ms1210 ms15,513
17Grok STTSpaceXAI180 ms—27,332
18PulseSmallest203 ms1988 ms27,366
19resonant-1Reson8243 ms—27,372
20Linden 1Speechmatics254 ms1528 ms27,368
21DefaultGradium261 ms2005 ms27,364
22Gemini 3.5 Transcribe LiveGemini383 ms1542 ms27,270
23Daytona STTGuava384 ms5651 ms13,133
24Solaria 1Gladia414 ms1608 ms27,306
25Voxtral Mini Transcribe Realtime 2602Mistral436 ms1867 ms20,731
26GPT Realtime WhisperOpenAI563 ms1822 ms26,862
27Chirp 3Google807 ms6007 ms27,330
28Chirp 2Google895 ms6097 ms27,368
—Nemotron 3.5 ASR StreamingTogether AI—1557 ms15,422
—Universal StreamingAssemblyAI—1516 ms27,339
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: 6th of 30 on Word Error Rate.

Latency vs accuracy

TTFS vs WEREach point is one measured model · Gemini 3.5 Transcribe Live highlighted · 30-day averagesTime to Final Segment against Word Error Rate for every measured STT model, with Gemini 3.5 Transcribe Live highlighted.
Qwen3 ASR 1.7b — 35 ms, 2.9%STT RT v5 — 44 ms, 4.8%Qwen3 ASR Fast — 50 ms, 2.6%STT 1 — 70 ms, 4.4%Nova 3 — 85 ms, 5.2%Nova 2 — 87 ms, 6.6%Parakeet TDT 0.6B v3 — 88 ms, 10.9%Flux Multilingual — 100 ms, 7.4%Flux — 101 ms, 5.7%Universal 3.6 Pro — 114 ms, 2.2%Scribe v2 Realtime — 118 ms, 4.2%Whisper Large v3 via Baseten — 126 ms, 4.5%Universal 3.5 Pro — 126 ms, 2.4%Ink 2 — 146 ms, 3.4%Realtime Global — 159 ms, 2.6%Whisper Large v3 via Together AI — 174 ms, 7.2%Grok STT — 180 ms, 4.1%Pulse — 203 ms, 4.6%resonant-1 — 243 ms, 2.6%Linden 1 — 254 ms, 3.8%Default — 261 ms, 8.4%Daytona STT — 384 ms, 4.8%Solaria 1 — 414 ms, 6.2%Voxtral Mini Transcribe Realtime 2602 — 436 ms, 5.3%GPT Realtime Whisper — 563 ms, 4.0%Chirp 3 — 807 ms, 3.2%Chirp 2 — 895 ms, 3.9%Gemini 3.5 Transcribe Live — 383 ms, 2.9%

Where the errors come from

WER compositionGemini 3.5 Transcribe Live's Word Error Rate split by error type · 30-day averageGemini 3.5 Transcribe Live's WER split into substitutions, deletions and insertions.
  • Gemini 3.5 Transcribe Live2.9%
SubstitutionsDeletionsInsertions

Averages and tail latency

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

Gemini 3.5 Transcribe Live latency distributionMilliseconds · shared axis across metrics · last 30 daysGemini 3.5 Transcribe Live's latency percentiles per metric: p25–p75 band, p50 tick, whisker to max.
  • Time to Final Segmentp50 327 ms · Max 5018 ms
  • Time to First Tokenp50 1487 ms · Max 12993 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 Segment383 ms277 ms327 ms397 ms460 ms494 ms5018 ms27,270
Word Error Rate2.9%0.0%0.0%3.7%11.1%16.7%100.0%27,309
Time to First Token1542 ms1263 ms1487 ms1791 ms2122 ms2451 ms12993 ms27,309

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 daysGemini 3.5 Transcribe Live's daily median Time to Final Segment over the last 30 days.
Gemini 3.5 Transcribe Live · Oct 3: 320 msGemini 3.5 Transcribe Live · Oct 4: 301 msGemini 3.5 Transcribe Live · Oct 5: 279 msGemini 3.5 Transcribe Live · Oct 6: 273 msGemini 3.5 Transcribe Live · Oct 7: 289 msGemini 3.5 Transcribe Live · Oct 8: 312 msGemini 3.5 Transcribe Live · Oct 9: 323 msGemini 3.5 Transcribe Live · Oct 10: 308 msGemini 3.5 Transcribe Live · Oct 11: 325 msGemini 3.5 Transcribe Live · Oct 12: 307 msGemini 3.5 Transcribe Live · Oct 13: 319 msGemini 3.5 Transcribe Live · Oct 14: 318 msGemini 3.5 Transcribe Live · Oct 15: 341 msGemini 3.5 Transcribe Live · Oct 16: 329 msGemini 3.5 Transcribe Live · Oct 17: 349 msGemini 3.5 Transcribe Live · Oct 18: 339 msGemini 3.5 Transcribe Live · Oct 19: 336 msGemini 3.5 Transcribe Live · Oct 20: 355 msGemini 3.5 Transcribe Live · Oct 21: 358 msGemini 3.5 Transcribe Live · Oct 22: 338 msGemini 3.5 Transcribe Live · Oct 23: 345 msGemini 3.5 Transcribe Live · Oct 24: 392 msGemini 3.5 Transcribe Live · Oct 25: 382 msGemini 3.5 Transcribe Live · Oct 26: 393 msGemini 3.5 Transcribe Live · Oct 27: 367 msGemini 3.5 Transcribe Live · Oct 28: 335 msGemini 3.5 Transcribe Live · Oct 29: 349 msGemini 3.5 Transcribe Live · Oct 30: 302 msGemini 3.5 Transcribe Live · Oct 31: 268 msGemini 3.5 Transcribe Live · Nov 1: 289 msGemini 3.5 Transcribe Live · Nov 2: 291 ms
Word Error Rate — daily averageDaily average · UTC daysGemini 3.5 Transcribe Live's daily Word Error Rate over the last 30 days.
Gemini 3.5 Transcribe Live · Oct 3: 5.2%Gemini 3.5 Transcribe Live · Oct 4: 3.9%Gemini 3.5 Transcribe Live · Oct 5: 4.9%Gemini 3.5 Transcribe Live · Oct 6: 5.5%Gemini 3.5 Transcribe Live · Oct 7: 3.6%Gemini 3.5 Transcribe Live · Oct 8: 4.9%Gemini 3.5 Transcribe Live · Oct 9: 4.5%Gemini 3.5 Transcribe Live · Oct 10: 3.5%Gemini 3.5 Transcribe Live · Oct 11: 3.5%Gemini 3.5 Transcribe Live · Oct 12: 4.0%Gemini 3.5 Transcribe Live · Oct 13: 4.2%Gemini 3.5 Transcribe Live · Oct 14: 4.0%Gemini 3.5 Transcribe Live · Oct 15: 3.6%Gemini 3.5 Transcribe Live · Oct 16: 4.2%Gemini 3.5 Transcribe Live · Oct 17: 4.2%Gemini 3.5 Transcribe Live · Oct 18: 4.1%Gemini 3.5 Transcribe Live · Oct 19: 3.4%Gemini 3.5 Transcribe Live · Oct 20: 5.4%Gemini 3.5 Transcribe Live · Oct 21: 4.5%Gemini 3.5 Transcribe Live · Oct 22: 5.8%Gemini 3.5 Transcribe Live · Oct 23: 4.4%Gemini 3.5 Transcribe Live · Oct 24: 5.3%Gemini 3.5 Transcribe Live · Oct 25: 3.8%Gemini 3.5 Transcribe Live · Oct 26: 5.5%Gemini 3.5 Transcribe Live · Oct 27: 4.0%Gemini 3.5 Transcribe Live · Oct 28: 4.3%Gemini 3.5 Transcribe Live · Oct 29: 4.9%Gemini 3.5 Transcribe Live · Oct 30: 4.4%Gemini 3.5 Transcribe Live · Oct 31: 3.1%Gemini 3.5 Transcribe Live · Nov 1: 3.9%Gemini 3.5 Transcribe Live · Nov 2: 3.6%

Time to Final Segment by dataset

Gemini 3.5 Transcribe Live by test conditionMilliseconds · lower is better · best condition firstGemini 3.5 Transcribe Live's Time to Final Segment on each benchmark dataset.
  1. WildASR accents356 ms
  2. WildASR clipping372 ms
  3. WildASR phone codec378 ms
  4. WildASR far-field379 ms
  5. WildASR noise gaps381 ms
  6. PipeCat (production)387 ms
  7. WildASR clean387 ms
Time to Final Segment per dataset, with the number of samples behind each figure.
DatasetTTFSSamples
ProductionPipeCat387 ms14,381
AccentsWildASR356 ms1,439
CleanWildASR387 ms5,752
ClippingWildASR372 ms1,389
Far-fieldWildASR379 ms1,435
Noise gapsWildASR381 ms1,436
Phone codecWildASR378 ms1,438

Strongest condition: WildASR accents at 356 ms · weakest: WildASR clean at 387 ms.

How fast is Gemini 3.5 Transcribe Live?

On Gemini, Gemini 3.5 Transcribe Live measures mean 383 ms time to final segment (22nd of 28) and mean 1542 ms time to first token (15th of 28). Last measured 2026-11-02.

How accurate is Gemini 3.5 Transcribe Live?

On Gemini, Gemini 3.5 Transcribe Live measures 2.9% word error rate (6th of 30). Last measured 2026-11-02.

Who hosts Gemini 3.5 Transcribe Live?

Gemini 3.5 Transcribe Live is created by Google and served by Gemini. Coval measures each hosted endpoint separately.

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