Voice AI BenchmarksBy

GOOGLESPEECH-TO-TEXT133,190 SAMPLES / 30 DAYSLAST RUN OCT 14, 2026, 06:30 UTC

official resource

Chirp 3 speech-to-text benchmarks

Chirp 3, hosted by Google, measures mean 768 ms time to final segment (27th of 29) and 3.2% word error rate (7th of 31) among STT systems. Results cover the last 30 days. Coval benchmarks hosted endpoints daily using a consistent evaluation methodology. Last measured .

Chirp 3 is Google's newer Chirp speech recognition model for Cloud Speech-to-Text.

Time to Final Segment#27 / 29
768ms
Word Error Rate#7 / 31
3.2%
Time to First Token#26 / 27
5957ms

Overview

Chirp 3 is Google's latest multilingual foundation speech model, with voice-activity and keyterm support on the tested endpoint.

Chirp 3 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
Google
Source
Official API
Licensing
Proprietary
Deployment
On-prem
Region
US
Features
Keyterm biasing, Multilingual, VAD

How Chirp 3 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 Chirp 3 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
  26. #26GPT-4o mini Transcribe708 ms
  27. #27Chirp 3768 ms
Show all 29 models
  1. #28GPT-4o Transcribe783 ms
  2. #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: 7th of 31 on Word Error Rate.

Latency vs accuracy

TTFS vs WEREach point is one measured model · Chirp 3 highlighted · 30-day averagesTime to Final Segment against Word Error Rate for every measured STT model, with Chirp 3 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%Solaria 1 — 636 ms, 6.0%GPT-4o mini Transcribe — 708 ms, 3.9%GPT-4o Transcribe — 783 ms, 3.8%Chirp 2 — 908 ms, 3.9%Chirp 3 — 768 ms, 3.2%

Where the errors come from

WER compositionChirp 3's Word Error Rate split by error type · 30-day averageChirp 3's WER split into substitutions, deletions and insertions.
  • Chirp 33.2%
SubstitutionsDeletionsInsertions

Averages and tail latency

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

Chirp 3 latency distributionMilliseconds · shared axis across metrics · last 30 daysChirp 3's latency percentiles per metric: p25–p75 band, p50 tick, whisker to max.
  • Time to Final Segmentp50 758 ms · Max 25641 ms
  • Time to First Tokenp50 6342 ms · Max 25530 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 Segment768 ms668 ms758 ms840 ms906 ms949 ms25641 ms26,638
Word Error Rate3.2%0.0%0.0%4.5%11.1%16.7%106.3%26,638
Time to First Token5957 ms5632 ms6342 ms6553 ms6886 ms7244 ms25530 ms26,638

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 daysChirp 3's daily median Time to Final Segment over the last 30 days.
Chirp 3 · Sep 14: 721 msChirp 3 · Sep 15: 825 msChirp 3 · Sep 16: 774 msChirp 3 · Sep 17: 779 msChirp 3 · Sep 18: 779 msChirp 3 · Sep 19: 759 msChirp 3 · Sep 20: 736 msChirp 3 · Sep 21: 759 msChirp 3 · Sep 22: 759 msChirp 3 · Sep 23: 750 msChirp 3 · Sep 24: 813 msChirp 3 · Sep 25: 778 msChirp 3 · Sep 26: 758 msChirp 3 · Sep 27: 726 msChirp 3 · Sep 28: 733 msChirp 3 · Sep 29: 781 msChirp 3 · Sep 30: 758 msChirp 3 · Oct 1: 765 msChirp 3 · Oct 2: 758 msChirp 3 · Oct 3: 732 msChirp 3 · Oct 4: 731 msChirp 3 · Oct 5: 787 msChirp 3 · Oct 6: 698 msChirp 3 · Oct 7: 791 msChirp 3 · Oct 8: 763 msChirp 3 · Oct 9: 716 msChirp 3 · Oct 10: 726 msChirp 3 · Oct 11: 767 msChirp 3 · Oct 12: 692 msChirp 3 · Oct 13: 707 msChirp 3 · Oct 14: 776 ms
Word Error Rate — daily averageDaily average · UTC daysChirp 3's daily Word Error Rate over the last 30 days.
Chirp 3 · Sep 14: 3.6%Chirp 3 · Sep 15: 3.6%Chirp 3 · Sep 16: 4.5%Chirp 3 · Sep 17: 5.3%Chirp 3 · Sep 18: 4.9%Chirp 3 · Sep 19: 4.6%Chirp 3 · Sep 20: 4.9%Chirp 3 · Sep 21: 4.3%Chirp 3 · Sep 22: 5.2%Chirp 3 · Sep 23: 4.0%Chirp 3 · Sep 24: 5.2%Chirp 3 · Sep 25: 4.6%Chirp 3 · Sep 26: 5.1%Chirp 3 · Sep 27: 4.9%Chirp 3 · Sep 28: 3.2%Chirp 3 · Sep 29: 3.9%Chirp 3 · Sep 30: 4.8%Chirp 3 · Oct 1: 4.7%Chirp 3 · Oct 2: 4.2%Chirp 3 · Oct 3: 5.0%Chirp 3 · Oct 4: 4.7%Chirp 3 · Oct 5: 4.2%Chirp 3 · Oct 6: 5.3%Chirp 3 · Oct 7: 4.9%Chirp 3 · Oct 8: 4.2%Chirp 3 · Oct 9: 5.4%Chirp 3 · Oct 10: 3.2%Chirp 3 · Oct 11: 5.2%Chirp 3 · Oct 12: 4.5%Chirp 3 · Oct 13: 4.3%Chirp 3 · Oct 14: 4.4%

Time to Final Segment by dataset

Chirp 3 by test conditionMilliseconds · lower is better · best condition firstChirp 3's Time to Final Segment on each benchmark dataset.
  1. WildASR accents662 ms
  2. WildASR clipping744 ms
  3. WildASR clean764 ms
  4. WildASR far-field774 ms
  5. PipeCat (production)779 ms
  6. WildASR noise gaps782 ms
  7. WildASR phone codec787 ms
Time to Final Segment per dataset, with the number of samples behind each figure.
DatasetTTFSSamples
ProductionPipeCat779 ms14,014
AccentsWildASR662 ms1,403
CleanWildASR764 ms5,607
ClippingWildASR744 ms1,404
Far-fieldWildASR774 ms1,405
Noise gapsWildASR782 ms1,402
Phone codecWildASR787 ms1,403

Strongest condition: WildASR accents at 662 ms · weakest: WildASR phone codec at 787 ms.

How fast is Chirp 3?

On Google, Chirp 3 measures mean 768 ms time to final segment (27th of 29) and mean 5957 ms time to first token (26th of 27). Last measured 2026-10-14.

How accurate is Chirp 3?

On Google, Chirp 3 measures 3.2% word error rate (7th of 31). Last measured 2026-10-14.

Who hosts Chirp 3?

Chirp 3 is created by Google and served by Google. Coval measures each hosted endpoint separately.

Limits of this comparison

Coval reports transcript accuracy, time to first partial transcript and time to final transcript separately.

  • One benchmark configuration cannot represent every Chirp 3 language, Cloud region or recognizer option.

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