Voice AI BenchmarksBy

RIMETEXT-TO-SPEECH45,728 SAMPLES / 30 DAYSLAST RUN SEP 15, 2026, 09:00 UTC

official resource

Mist v3 text-to-speech benchmarks

Mist v3, hosted by Rime, measures mean 258 ms time to first audio (11th of 28) and 5.6% word error rate (23rd of 28) among TTS systems. Results cover the last 30 days. Coval benchmarks hosted endpoints daily using a consistent evaluation methodology. Last measured .

Mist v3 is Rime's low-latency streaming text-to-speech model.

Time to First Audio#11 / 28
258ms
TTFA Network Roundtrip#9 / 28
126ms
TTFA Leading Silence#24 / 28
132ms
Word Error Rate#23 / 28
5.6%

Overview

Mist v3 runs on Rime's low-latency API, with multilingual and on-premises options.

Mist v3 is tested every day on a fixed set of text prompts, measuring how quickly audible speech starts and how intelligible the result is.

Technical specifications

Made by
Rime
Hosted by
Rime
Source
Official API
Licensing
Proprietary
Deployment
On-prem
Region
US
Features
Multilingual

How Mist v3 ranks

Full TTS dashboard
Time to First Audio — every measured TTS modelMilliseconds · lower is better · 30-day averageEvery TTS model ranked on Time to First Audio, with Mist v3 highlighted.
  1. #1vui66 ms
  2. #2Qwen3 TTS Fast71 ms
  3. #3TTS Flash 291 ms
  4. #4Qwen3 TTS 1.7b106 ms
  5. #5Palabra TTS v1115 ms
  6. #6TTS 2181 ms
  7. #7Flash v2.5194 ms
  8. #8Default235 ms
  9. #9TTS Rt v2245 ms
  10. #10TTS RT v1245 ms
  11. #11Mist v3258 ms
  12. #12Sonic 3.5276 ms
Show all 28 models
  1. #13Phantom Z 3.4 conversational286 ms
  2. #14Aura 2308 ms
  3. #15Coda312 ms
  4. #16S2.1 Pro335 ms
  5. #17Eleven v3 Conversational348 ms
  6. #18Lightning v3.1 Pro362 ms
  7. #19S1379 ms
  8. #20Grok TTS397 ms
  9. #21Sonic 3.6423 ms
  10. #22Simba 3.2451 ms
  11. #23Simba 3.0473 ms
  12. #24Chirp 3 HD535 ms
  13. #25Falcon 2545 ms
  14. #26Qwen3 TTS Flash Realtime753 ms
  15. #27S2.1 Pro Free963 ms
  16. #28GPT-4o mini TTS1014 ms
median of all models · 310 ms
TTS models over the last 30 days, ranked on Time to First Audio.
#ModelHostTTFAWERSamples
1vuiFluxions66 ms9,500
2Qwen3 TTS FastNari71 ms2,240
3TTS Flash 2Inworld AI91 ms11,451
4Qwen3 TTS 1.7bBaseten106 ms420
5Palabra TTS v1Palabra115 ms11,435
6TTS 2Inworld AI181 ms11,451
7Flash v2.5ElevenLabs194 ms9,168
8DefaultGradium235 ms9,177
9TTS Rt v2Soniox245 ms11,232
10TTS RT v1Soniox245 ms11,234
11Mist v3Rime258 ms11,437
12Sonic 3.5Cartesia276 ms11,450
13Phantom Z 3.4 conversationalDeepdub286 ms11,446
14Aura 2Deepgram308 ms11,436
15CodaRime312 ms11,442
16S2.1 ProFish Audio335 ms11,450
17Eleven v3 ConversationalElevenLabs348 ms11,439
18Lightning v3.1 ProSmallest362 ms11,451
19S1Fish Audio379 ms11,443
20Grok TTSxAI397 ms11,436
21Sonic 3.6Cartesia423 ms8,260
22Simba 3.2Speechify451 ms11,443
23Simba 3.0Speechify473 ms11,446
24Chirp 3 HDGoogle535 ms11,450
25Falcon 2Murf545 ms11,447
26Qwen3 TTS Flash RealtimeAlibaba753 ms11,276
27S2.1 Pro FreeFish Audio963 ms11,416
28GPT-4o mini TTSOpenAI1014 ms11,420
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

TTFA vs WEREach point is one measured model · Mist v3 highlighted · 30-day averagesTime to First Audio against Word Error Rate for every measured TTS model, with Mist v3 highlighted.
vui — 66 ms, 5.5%Qwen3 TTS Fast — 71 ms, 4.2%TTS Flash 2 — 91 ms, 5.4%Qwen3 TTS 1.7b — 106 ms, 5.5%Palabra TTS v1 — 115 ms, 5.8%TTS 2 — 181 ms, 4.6%Flash v2.5 — 194 ms, 6.7%Default — 235 ms, 5.3%TTS Rt v2 — 245 ms, 4.2%TTS RT v1 — 245 ms, 3.9%Sonic 3.5 — 276 ms, 5.9%Phantom Z 3.4 conversational — 286 ms, 6.0%Aura 2 — 308 ms, 5.2%Coda — 312 ms, 5.0%S2.1 Pro — 335 ms, 4.8%Eleven v3 Conversational — 348 ms, 4.4%Lightning v3.1 Pro — 362 ms, 4.4%S1 — 379 ms, 4.9%Grok TTS — 397 ms, 4.9%Sonic 3.6 — 423 ms, 5.3%Simba 3.2 — 451 ms, 4.4%Simba 3.0 — 473 ms, 5.2%Chirp 3 HD — 535 ms, 5.2%Falcon 2 — 545 ms, 5.2%Qwen3 TTS Flash Realtime — 753 ms, 8.9%S2.1 Pro Free — 963 ms, 4.7%GPT-4o mini TTS — 1014 ms, 4.8%Mist v3 — 258 ms, 5.6%

Where the errors come from

WER compositionMist v3's Word Error Rate split by error type · 30-day averageMist v3's WER split into substitutions, deletions and insertions.
  • Mist v35.6%
SubstitutionsDeletionsInsertions

Averages and tail latency

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

Mist v3 latency distributionMilliseconds · shared axis across metrics · last 30 daysMist v3's latency percentiles per metric: p25–p75 band, p50 tick, whisker to p99.
  • Time to First Audiop50 255 ms · p99 352 ms
  • TTFA Network Roundtripp50 120 ms · p99 218 ms
  • TTFA Leading Silencep50 134 ms · p99 154 ms
band p25–p75 · tick p50 · whisker to p99 with p90 and p95 stops
Average and percentile values per metric, with the number of samples behind each row.
MetricAveragep25p50p75p90p95p99Samples
Time to First Audio258 ms246 ms255 ms266 ms280 ms295 ms352 ms11,437
TTFA Network Roundtrip126 ms118 ms120 ms125 ms142 ms160 ms218 ms11,437
TTFA Leading Silence132 ms125 ms134 ms141 ms147 ms150 ms154 ms11,437
Word Error Rate5.6%0.0%0.0%7.7%20.0%28.6%35.7%11,417

Last 30 days

Daily medians from the same measurement runs · gaps are days without qualifying runs.

Time to First Audio — daily p50Line p50 · band p25–p75 · UTC daysMist v3's daily median Time to First Audio over the last 30 days.
Mist v3 · Sep 1: 263 msMist v3 · Sep 2: 253 msMist v3 · Sep 3: 255 msMist v3 · Sep 4: 254 msMist v3 · Sep 5: 254 msMist v3 · Sep 6: 256 msMist v3 · Sep 7: 256 msMist v3 · Sep 8: 256 msMist v3 · Sep 9: 259 msMist v3 · Sep 10: 255 msMist v3 · Sep 11: 255 msMist v3 · Sep 12: 255 msMist v3 · Sep 13: 257 msMist v3 · Sep 14: 259 msMist v3 · Sep 15: 255 ms
Word Error Rate — daily averageDaily average · UTC daysMist v3's daily Word Error Rate over the last 30 days.
Mist v3 · Sep 1: 3.2%Mist v3 · Sep 2: 4.8%Mist v3 · Sep 3: 5.0%Mist v3 · Sep 4: 5.6%Mist v3 · Sep 5: 6.6%Mist v3 · Sep 6: 6.5%Mist v3 · Sep 7: 4.4%Mist v3 · Sep 8: 5.4%Mist v3 · Sep 9: 6.1%Mist v3 · Sep 10: 5.9%Mist v3 · Sep 11: 6.6%Mist v3 · Sep 12: 5.3%Mist v3 · Sep 13: 5.9%Mist v3 · Sep 14: 5.8%Mist v3 · Sep 15: 6.6%

Time to First Audio by dataset

Mist v3 by test conditionMilliseconds · lower is better · best condition firstMist v3's Time to First Audio on each benchmark dataset.
  1. Text prompts258 ms
Time to First Audio per dataset, with the number of samples behind each figure.
DatasetTTFASamples
Text prompts258 ms11,437

Strongest condition: Text prompts at 258 ms · weakest: Text prompts at 258 ms.

How fast is Mist v3?

On Rime, Mist v3 measures mean 258 ms time to first audio (11th of 28). Last measured 2026-09-15.

How accurate is Mist v3?

On Rime, Mist v3 measures 5.6% word error rate (23rd of 28). Last measured 2026-09-15.

Who hosts Mist v3?

Mist v3 is created by Rime and served by Rime. Coval measures each hosted endpoint separately.

Limits of this comparison

Coval treats it as a separate generation from Coda and sends both models the same text manifest.

  • The benchmark does not compare every Rime speaker or independently score naturalness and prosody.

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