Voice AI BenchmarksBy

ELEVENLABSSPEECH-TO-TEXT133,184 SAMPLES / 30 DAYSLAST RUN OCT 14, 2026, 11:00 UTC

official resource

Scribe v2 Realtime speech-to-text benchmarks

Scribe v2 Realtime, hosted by ElevenLabs (Eleven Labs, 11Labs), measures mean 122 ms time to final segment (10th of 29) and 4.4% word error rate (15th of 31) among STT systems. Results cover the last 30 days. Last measured .

Scribe v2 Realtime is ElevenLabs' streaming speech recognition model.

Time to Final Segment#10 / 29
122ms
Word Error Rate#15 / 31
4.4%
Time to First Token#24 / 27
2157ms

Overview

ElevenLabs provides Scribe through a real-time transcription API with multilingual, voice-activity and keyterm support.

Scribe v2 Realtime 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
ElevenLabs
Hosted by
ElevenLabs
Source
Official API
Licensing
Proprietary
Deployment
Cloud
Region
US
Features
Keyterm biasing, Multilingual, VAD

How Scribe v2 Realtime 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 v2 Realtime highlighted.
  1. #1Qwen3 ASR 1.7b39 ms
  2. #2STT RT v545 ms
  3. #3Qwen3 ASR Fast47 ms
  4. #4STT 167 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
Show all 29 models
  1. #13Ink 2149 ms
  2. #14Universal 3.5 Pro168 ms
  3. #15Whisper Large v3via Together AI199 ms
  4. #16Pulse205 ms
  5. #17Grok STT223 ms
  6. #18resonant-1252 ms
  7. #19Default258 ms
  8. #20Linden 1271 ms
  9. #21Gemini 3.5 Transcribe Live317 ms
  10. #22Daytona STT399 ms
  11. #23Voxtral Mini Transcribe Realtime 2602411 ms
  12. #24GPT Realtime Whisper599 ms
  13. #25Solaria 1626 ms
  14. #26GPT-4o mini Transcribe708 ms
  15. #27Chirp 3768 ms
  16. #28GPT-4o Transcribe783 ms
  17. #29Chirp 2908 ms
median of all models · 199 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 ms26,653
4STT 1Inworld AI67 ms1208 ms24,749
5Nova 3Deepgram85 ms1432 ms26,002
6Nova 2Deepgram87 ms1417 ms25,960
7Parakeet TDT 0.6B v3Together AI97 ms1228 ms26,462
8Flux MultilingualDeepgram98 ms1165 ms26,007
9FluxDeepgram99 ms1091 ms26,005
10Scribe v2 RealtimeElevenLabs122 ms2157 ms26,640
11Whisper Large v3Baseten131 ms924 ms13,663
12Universal 3.6 ProAssemblyAI135 ms1072 ms24,394
13Ink 2Cartesia149 ms1967 ms26,653
14Universal 3.5 ProAssemblyAI168 ms1026 ms26,654
15Whisper Large v3Together AI199 ms1260 ms26,447
16PulseSmallest205 ms1976 ms26,654
17Grok STTSpaceXAI223 ms—26,576
18resonant-1Reson8252 ms—26,654
19DefaultGradium258 ms1986 ms26,632
20Linden 1Speechmatics271 ms1537 ms26,595
21Gemini 3.5 Transcribe LiveGemini317 ms1606 ms26,567
22Daytona STTGuava399 ms5695 ms5,225
23Voxtral Mini Transcribe Realtime 2602Mistral411 ms1851 ms26,158
24GPT Realtime WhisperOpenAI599 ms1824 ms26,622
25Solaria 1Gladia626 ms1775 ms26,215
26GPT-4o mini TranscribeOpenAI708 ms—26,621
27Chirp 3Google768 ms5956 ms26,638
28GPT-4o TranscribeOpenAI783 ms—26,625
29Chirp 2Google908 ms6099 ms26,650
—Nemotron 3.5 ASR StreamingTogether AI—1544 ms26,550
—Universal StreamingAssemblyAI—1509 ms26,625
Under-sampled models are excluded; tied models share a place. Dotted WER values split into substitutions, deletions and insertions on hover or tap.

Latency vs accuracy

TTFS vs WEREach point is one measured model · Scribe v2 Realtime highlighted · 30-day averagesTime to Final Segment against Word Error Rate for every measured STT model, with Scribe v2 Realtime 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 — 67 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%Whisper Large v3 via Baseten — 131 ms, 4.5%Universal 3.6 Pro — 135 ms, 2.1%Ink 2 — 149 ms, 3.6%Universal 3.5 Pro — 168 ms, 2.3%Whisper Large v3 via Together AI — 199 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 — 411 ms, 5.3%GPT Realtime Whisper — 599 ms, 4.0%Solaria 1 — 626 ms, 6.0%GPT-4o mini Transcribe — 708 ms, 3.9%Chirp 3 — 768 ms, 3.2%GPT-4o Transcribe — 783 ms, 3.7%Chirp 2 — 908 ms, 3.9%Scribe v2 Realtime — 122 ms, 4.4%

Where the errors come from

WER compositionScribe v2 Realtime's Word Error Rate split by error type · 30-day averageScribe v2 Realtime's WER split into substitutions, deletions and insertions.
  • Scribe v2 Realtime4.4%
SubstitutionsDeletionsInsertions

Averages and tail latency

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

Scribe v2 Realtime latency distributionMilliseconds · shared axis across metrics · last 30 daysScribe v2 Realtime's latency percentiles per metric: p25–p75 band, p50 tick, whisker to max.
  • Time to Final Segmentp50 115 ms · Max 5714 ms
  • Time to First Tokenp50 2112 ms · Max 5785 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 Segment122 ms87 ms115 ms145 ms173 ms193 ms5714 ms26,640
Word Error Rate4.4%0.0%0.0%6.9%13.6%21.1%110.0%26,640
Time to First Token2157 ms2045 ms2112 ms2124 ms2215 ms2917 ms5785 ms26,624

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 v2 Realtime's daily median Time to Final Segment over the last 30 days.
Scribe v2 Realtime · Sep 14: 134 msScribe v2 Realtime · Sep 15: 130 msScribe v2 Realtime · Sep 16: 125 msScribe v2 Realtime · Sep 17: 137 msScribe v2 Realtime · Sep 18: 131 msScribe v2 Realtime · Sep 19: 92 msScribe v2 Realtime · Sep 20: 93 msScribe v2 Realtime · Sep 21: 127 msScribe v2 Realtime · Sep 22: 126 msScribe v2 Realtime · Sep 23: 107 msScribe v2 Realtime · Sep 24: 118 msScribe v2 Realtime · Sep 25: 111 msScribe v2 Realtime · Sep 26: 84 msScribe v2 Realtime · Sep 27: 82 msScribe v2 Realtime · Sep 28: 108 msScribe v2 Realtime · Sep 29: 123 msScribe v2 Realtime · Sep 30: 118 msScribe v2 Realtime · Oct 1: 115 msScribe v2 Realtime · Oct 2: 130 msScribe v2 Realtime · Oct 3: 82 msScribe v2 Realtime · Oct 4: 74 msScribe v2 Realtime · Oct 5: 122 msScribe v2 Realtime · Oct 6: 130 msScribe v2 Realtime · Oct 7: 120 msScribe v2 Realtime · Oct 8: 130 msScribe v2 Realtime · Oct 9: 122 msScribe v2 Realtime · Oct 10: 86 msScribe v2 Realtime · Oct 11: 91 msScribe v2 Realtime · Oct 12: 111 msScribe v2 Realtime · Oct 13: 123 msScribe v2 Realtime · Oct 14: 132 ms
Word Error Rate — daily averageDaily average · UTC daysScribe v2 Realtime's daily Word Error Rate over the last 30 days.
Scribe v2 Realtime · Sep 14: 5.6%Scribe v2 Realtime · Sep 15: 6.0%Scribe v2 Realtime · Sep 16: 5.1%Scribe v2 Realtime · Sep 17: 6.8%Scribe v2 Realtime · Sep 18: 5.5%Scribe v2 Realtime · Sep 19: 5.2%Scribe v2 Realtime · Sep 20: 5.0%Scribe v2 Realtime · Sep 21: 6.3%Scribe v2 Realtime · Sep 22: 5.1%Scribe v2 Realtime · Sep 23: 5.5%Scribe v2 Realtime · Sep 24: 7.0%Scribe v2 Realtime · Sep 25: 5.6%Scribe v2 Realtime · Sep 26: 6.9%Scribe v2 Realtime · Sep 27: 5.8%Scribe v2 Realtime · Sep 28: 10.7%Scribe v2 Realtime · Sep 29: 5.2%Scribe v2 Realtime · Sep 30: 5.8%Scribe v2 Realtime · Oct 1: 5.3%Scribe v2 Realtime · Oct 2: 4.4%Scribe v2 Realtime · Oct 3: 6.7%Scribe v2 Realtime · Oct 4: 6.0%Scribe v2 Realtime · Oct 5: 5.1%Scribe v2 Realtime · Oct 6: 7.3%Scribe v2 Realtime · Oct 7: 4.5%Scribe v2 Realtime · Oct 8: 6.3%Scribe v2 Realtime · Oct 9: 5.7%Scribe v2 Realtime · Oct 10: 4.8%Scribe v2 Realtime · Oct 11: 5.8%Scribe v2 Realtime · Oct 12: 5.8%Scribe v2 Realtime · Oct 13: 5.7%Scribe v2 Realtime · Oct 14: 5.1%

Time to Final Segment by dataset

Scribe v2 Realtime by test conditionMilliseconds · lower is better · best condition firstScribe v2 Realtime's Time to Final Segment on each benchmark dataset.
  1. WildASR accents119 ms
  2. PipeCat (production)121 ms
  3. WildASR clean121 ms
  4. WildASR noise gaps123 ms
  5. WildASR phone codec123 ms
  6. WildASR far-field124 ms
  7. WildASR clipping131 ms
Time to Final Segment per dataset, with the number of samples behind each figure.
DatasetTTFSSamples
ProductionPipeCat121 ms14,013
AccentsWildASR119 ms1,402
CleanWildASR121 ms5,610
ClippingWildASR131 ms1,404
Far-fieldWildASR124 ms1,405
Noise gapsWildASR123 ms1,402
Phone codecWildASR123 ms1,404

Strongest condition: WildASR accents at 119 ms · weakest: WildASR clipping at 131 ms.

How fast is Scribe v2 Realtime?

On ElevenLabs, Scribe v2 Realtime measures mean 122 ms time to final segment (10th of 29) and mean 2157 ms time to first token (24th of 27). Last measured 2026-10-14.

How accurate is Scribe v2 Realtime?

On ElevenLabs, Scribe v2 Realtime measures 4.4% word error rate (15th of 31). Last measured 2026-10-14.

Who hosts Scribe v2 Realtime?

Scribe v2 Realtime is created by ElevenLabs and served by ElevenLabs. Coval measures each hosted endpoint separately.

Limits of this comparison

Scribe is measured separately from ElevenLabs synthesis models, focusing on transcript errors and streaming timing.

  • The benchmark does not score every language, speaker-labeling mode or event type offered by Scribe.

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