ZOOMSPEECH-TO-TEXT61,872 SAMPLES / 30 DAYSLAST RUN NOV 14, 2026, 01:30 UTC

Scribe Pro v2.1 speech-to-text benchmarks

Scribe Pro v2.1, hosted by Zoom, measures mean 241 ms time to final segment (23rd of 30) and 1.7% word error rate (1st of 31) 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 Scribe Pro v2.1, created by Zoom and served through Zoom's own API.

Word Error Rate#1 / 31
1.7%

Overview

Scribe Pro v2.1 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
Zoom
Hosted by
Zoom
Source
Official API
Licensing
Proprietary
Deployment
Cloud
Region
US
Features
VAD

How Scribe Pro v2.1 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 Scribe Pro v2.1 highlighted.
  1. #1Wire-129 ms
  2. #2Qwen3 ASR 1.7b35 ms
  3. #3STT RT v551 ms
  4. #5STT Rt v659 ms
  5. #6STT 170 ms
  6. #7Nova 395 ms
  7. #8Nova 297 ms
  8. #9Rumble-298 ms
  9. #14Flux112 ms
  10. #15Scribe112 ms
  11. #17Whisper Large v3125 ms
  12. #18Ink 2141 ms
  13. #19Grok STT163 ms
  14. #20Pulse169 ms
  15. #21resonant-1210 ms
  16. #22Linden 1229 ms
Show all 30 models
  1. #24Default284 ms
  2. #25Daytona STT348 ms
  3. #27Solaria 1390 ms
  4. #29Chirp 3842 ms
  5. #30Chirp 2909 ms
median of all models · 114 ms
STT models over the last 30 days, ranked on Time to Final Segment.
#ModelHostTTFSWERTTFTSamples
1Saidwire En 2026 10 30Saidwire29 ms768 ms9,441
2Qwen3 ASR 1.7bBaseten35 ms943 ms13,679
3STT RT v5Soniox51 ms1529 ms27,358
4Qwen3 ASR FastNari Labs53 ms1757 ms27,361
5STT Rt v6Soniox59 ms1893 ms12,188
6STT 1Inworld AI70 ms994 ms27,333
7Nova 3Deepgram95 ms1435 ms24,081
8Nova 2Deepgram97 ms1432 ms24,046
9Realtime GlobalReson898 ms1658 ms27,361
10Scribe v3 LiveElevenLabs98 ms1254 ms5,781
11Universal 3.5 ProAssemblyAI104 ms1013 ms27,361
12Universal 3.6 ProAssemblyAI110 ms1073 ms27,360
13Flux MultilingualDeepgram110 ms1173 ms24,079
14FluxDeepgram112 ms1095 ms24,085
15ScribeZoom112 ms—6,654
16Scribe v2 RealtimeElevenLabs116 ms2126 ms27,356
17Whisper Large v3Baseten125 ms920 ms13,221
18Ink 2Cartesia141 ms2030 ms18,412
19Grok STTSpaceXAI163 ms—27,343
20PulseSmallest169 ms1953 ms27,358
21resonant-1Reson8210 ms—27,353
22Linden 1Speechmatics229 ms1503 ms27,338
23Scribe Pro v2.1Zoom241 ms—6,823
24DefaultGradium284 ms2074 ms27,354
25Daytona STTGuava348 ms5609 ms13,376
26Gemini 3.5 Transcribe LiveGemini355 ms1520 ms27,282
27Solaria 1Gladia390 ms1534 ms27,318
28GPT Realtime WhisperOpenAI566 ms1813 ms26,878
29Chirp 3Google842 ms6035 ms27,311
30Chirp 2Google909 ms6101 ms27,359
—Universal StreamingAssemblyAI—1511 ms27,330
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: 1st of 31 on Word Error Rate.

Latency vs accuracy

Where the errors come from

WER compositionScribe Pro v2.1's Word Error Rate split by error type · 30-day averageScribe Pro v2.1's WER split into substitutions, deletions and insertions.
  • Scribe Pro v2.11.7%
SubstitutionsDeletionsInsertions

Averages and tail latency

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

Scribe Pro v2.1 latency distributionMilliseconds · shared axis across metrics · last 30 daysScribe Pro v2.1's latency percentiles per metric: p25–p75 band, p50 tick, whisker to max.
  • Time to Final Segmentp50 236 ms · Max 1427 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 Segment241 ms176 ms236 ms285 ms336 ms380 ms1427 ms6,823
Word Error Rate1.7%0.0%0.0%0.0%6.9%11.1%66.7%16,651

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 daysScribe Pro v2.1's daily median Time to Final Segment over the last 30 days.
Scribe Pro v2.1 · Oct 26: 878 msScribe Pro v2.1 · Nov 6: 262 msScribe Pro v2.1 · Nov 7: 239 msScribe Pro v2.1 · Nov 8: 229 msScribe Pro v2.1 · Nov 9: 223 msScribe Pro v2.1 · Nov 10: 226 msScribe Pro v2.1 · Nov 11: 232 msScribe Pro v2.1 · Nov 12: 229 msScribe Pro v2.1 · Nov 13: 236 msScribe Pro v2.1 · Nov 14: 261 ms
Word Error Rate — dailyDaily corpus-level · UTC daysScribe Pro v2.1's daily Word Error Rate over the last 30 days.
Scribe Pro v2.1 · Oct 26: 2.3%Scribe Pro v2.1 · Oct 27: 3.3%Scribe Pro v2.1 · Oct 28: 2.1%Scribe Pro v2.1 · Oct 29: 2.7%Scribe Pro v2.1 · Oct 30: 2.4%Scribe Pro v2.1 · Oct 31: 2.6%Scribe Pro v2.1 · Nov 1: 2.2%Scribe Pro v2.1 · Nov 2: 2.5%Scribe Pro v2.1 · Nov 3: 2.3%Scribe Pro v2.1 · Nov 4: 2.1%Scribe Pro v2.1 · Nov 5: 2.7%Scribe Pro v2.1 · Nov 6: 3.0%Scribe Pro v2.1 · Nov 7: 2.0%Scribe Pro v2.1 · Nov 8: 2.1%Scribe Pro v2.1 · Nov 9: 1.9%Scribe Pro v2.1 · Nov 10: 1.3%Scribe Pro v2.1 · Nov 11: 1.2%Scribe Pro v2.1 · Nov 12: 1.6%Scribe Pro v2.1 · Nov 13: 1.2%Scribe Pro v2.1 · Nov 14: 0.6%

Time to Final Segment by dataset

Scribe Pro v2.1 by test conditionMilliseconds · lower is better · best condition firstScribe Pro v2.1's Time to Final Segment on each benchmark dataset.
Time to Final Segment per dataset, with the number of samples behind each figure.
DatasetTTFSSamples
ProductionPipeCat249 ms3,587
AccentsWildASR253 ms360
CleanWildASR227 ms1,440
ClippingWildASR226 ms358
Far-fieldWildASR239 ms360
Noise gapsWildASR227 ms360
Phone codecWildASR237 ms358

Strongest condition: WildASR clipping at 226 ms · weakest: WildASR accents at 253 ms.

How fast is Scribe Pro v2.1?

On Zoom, Scribe Pro v2.1 measures mean 241 ms time to final segment (23rd of 30). Last measured 2026-11-14.

How accurate is Scribe Pro v2.1?

On Zoom, Scribe Pro v2.1 measures 1.7% word error rate (1st of 31). Last measured 2026-11-14.

Who hosts Scribe Pro v2.1?

Scribe Pro v2.1 is created by Zoom and served by Zoom. 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