Voice AI BenchmarksBy

RIMETEXT-TO-SPEECH51,362 SAMPLES / 30 DAYSLAST RUN AUG 28, 2026, 21:30 UTC

official resource

Mist v3 text-to-speech benchmarks

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

Time to First Audio#7 / 30
256ms
TTFA Network Roundtrip#6 / 28
124ms
TTFA Leading Silence#22 / 28
132ms
Word Error Rate#26 / 30
6.3%

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. #1Palabra TTS v1116 ms
  2. #2vui124 ms
  3. #3TTS Flash 2128 ms
  4. #4TTS 2176 ms
  5. #5Blizzard235 ms
  6. #6Neural236 ms
  7. #7Mist v3256 ms
  8. #8TTS Rt v2262 ms
  9. #9Sonic 3.5274 ms
  10. #10TTS RT v1275 ms
  11. #11Dragon HD Latest310 ms
  12. #12Coda313 ms
Show all 30 models
  1. #13Aura 2328 ms
  2. #14S2.1 Pro374 ms
  3. #15Default384 ms
  4. #16Speech 2.8 Turbo411 ms
  5. #17Eleven v3 Conversational412 ms
  6. #18Grok TTS420 ms
  7. #19S1434 ms
  8. #20Flash v2.5455 ms
  9. #21Speech 2.8 HD460 ms
  10. #22Sonic 3.6466 ms
  11. #23Simba 3.2484 ms
  12. #24Chirp 3 HD512 ms
  13. #25Simba 3.0526 ms
  14. #26Falcon 2549 ms
  15. #27Lightning v3.1 Pro586 ms
  16. #28Qwen3 TTS Flash Realtime645 ms
  17. #29S2.1 Pro Free806 ms
  18. #30GPT-4o mini TTS1075 ms
median of all models · 397 ms
TTS models over the last 30 days, ranked on Time to First Audio.
#ModelHostTTFAWERSamples
1Palabra TTS v1Palabra116 ms5.9%14,396
2vuiFluxions124 ms8,624
3TTS Flash 2Inworld AI128 ms8,719
4TTS 2Inworld AI176 ms4.8%14,529
5BlizzardLmnt235 ms7.4%14,117
6NeuralAzure236 ms4.3%3,350
7Mist v3Rime256 ms6.3%14,524
8TTS Rt v2Soniox262 ms8,849
9Sonic 3.5Cartesia274 ms6.1%14,513
10TTS RT v1Soniox275 ms3.7%14,528
11Dragon HD LatestAzure310 ms5.1%3,350
12CodaRime313 ms5.2%14,523
13Aura 2Deepgram328 ms5.3%14,501
14S2.1 ProFish Audio374 ms10,222
15DefaultGradium384 ms4.6%14,002
16Speech 2.8 TurboMiniMax411 ms4.8%1,997
17Eleven v3 ConversationalElevenLabs412 ms6,750
18Grok TTSxAI420 ms4.7%14,524
19S1Fish Audio434 ms4.9%10,236
20Flash v2.5ElevenLabs455 ms6.7%9,259
21Speech 2.8 HDMiniMax460 ms1,995
22Sonic 3.6Cartesia466 ms560
23Simba 3.2Speechify484 ms4.7%14,525
24Chirp 3 HDGoogle512 ms5.2%14,530
25Simba 3.0Speechify526 ms5.3%14,526
26Falcon 2Murf549 ms10,229
27Lightning v3.1 ProSmallest586 ms4.4%14,515
28Qwen3 TTS Flash RealtimeAlibaba645 ms8.8%14,530
29S2.1 Pro FreeFish Audio806 ms4.7%14,464
30GPT-4o mini TTSOpenAI1075 ms4.8%14,517
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.
Palabra TTS v1 — 116 ms, 5.9%vui — 124 ms, 7.9%TTS Flash 2 — 128 ms, 4.9%TTS 2 — 176 ms, 4.8%Blizzard — 235 ms, 7.4%Neural — 236 ms, 4.3%TTS Rt v2 — 262 ms, 3.9%Sonic 3.5 — 274 ms, 6.1%TTS RT v1 — 275 ms, 3.7%Dragon HD Latest — 310 ms, 5.1%Coda — 313 ms, 5.2%Aura 2 — 328 ms, 5.3%S2.1 Pro — 374 ms, 4.6%Default — 384 ms, 4.6%Speech 2.8 Turbo — 411 ms, 4.8%Eleven v3 Conversational — 412 ms, 4.4%Grok TTS — 420 ms, 4.7%S1 — 434 ms, 4.9%Flash v2.5 — 455 ms, 6.7%Speech 2.8 HD — 460 ms, 4.7%Sonic 3.6 — 466 ms, 5.5%Simba 3.2 — 484 ms, 4.7%Chirp 3 HD — 512 ms, 5.2%Simba 3.0 — 526 ms, 5.3%Falcon 2 — 549 ms, 5.2%Lightning v3.1 Pro — 586 ms, 4.4%Qwen3 TTS Flash Realtime — 645 ms, 8.8%S2.1 Pro Free — 806 ms, 4.7%GPT-4o mini TTS — 1075 ms, 4.8%Mist v3 — 256 ms, 6.3%

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 315 ms
  • TTFA Network Roundtripp50 120 ms · p99 180 ms
  • TTFA Leading Silencep50 134 ms · p99 155 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 Audio256 ms246 ms255 ms266 ms277 ms287 ms315 ms14,524
TTFA Network Roundtrip124 ms118 ms120 ms124 ms135 ms149 ms180 ms11,157
TTFA Leading Silence132 ms125 ms134 ms141 ms147 ms150 ms155 ms11,157
Word Error Rate6.3%0.0%0.0%9.5%21.4%31.3%44.0%14,524

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 · Jul 31: 253 msMist v3 · Aug 1: 259 msMist v3 · Aug 2: 258 msMist v3 · Aug 3: 258 msMist v3 · Aug 4: 258 msMist v3 · Aug 5: 254 msMist v3 · Aug 6: 261 msMist v3 · Aug 7: 251 msMist v3 · Aug 8: 258 msMist v3 · Aug 9: 256 msMist v3 · Aug 10: 257 msMist v3 · Aug 11: 257 msMist v3 · Aug 12: 261 msMist v3 · Aug 13: 251 msMist v3 · Aug 14: 251 msMist v3 · Aug 15: 257 msMist v3 · Aug 16: 254 msMist v3 · Aug 17: 256 msMist v3 · Aug 18: 250 msMist v3 · Aug 19: 242 msMist v3 · Aug 20: 260 msMist v3 · Aug 21: 254 msMist v3 · Aug 22: 248 msMist v3 · Aug 23: 258 msMist v3 · Aug 24: 250 msMist v3 · Aug 25: 255 msMist v3 · Aug 26: 257 msMist v3 · Aug 27: 257 msMist v3 · Aug 28: 252 ms
Word Error Rate — daily averageDaily average · UTC daysMist v3's daily Word Error Rate over the last 30 days.
Mist v3 · Jul 31: 5.8%Mist v3 · Aug 1: 8.3%Mist v3 · Aug 2: 7.8%Mist v3 · Aug 3: 7.7%Mist v3 · Aug 4: 7.6%Mist v3 · Aug 5: 5.9%Mist v3 · Aug 6: 7.3%Mist v3 · Aug 7: 6.4%Mist v3 · Aug 8: 7.8%Mist v3 · Aug 9: 7.4%Mist v3 · Aug 10: 6.5%Mist v3 · Aug 11: 6.8%Mist v3 · Aug 12: 7.7%Mist v3 · Aug 13: 5.4%Mist v3 · Aug 14: 6.7%Mist v3 · Aug 15: 6.6%Mist v3 · Aug 16: 7.2%Mist v3 · Aug 17: 7.4%Mist v3 · Aug 18: 5.8%Mist v3 · Aug 19: 6.3%Mist v3 · Aug 20: 7.6%Mist v3 · Aug 21: 6.4%Mist v3 · Aug 22: 6.5%Mist v3 · Aug 23: 6.8%Mist v3 · Aug 24: 5.5%Mist v3 · Aug 25: 5.9%Mist v3 · Aug 26: 7.2%Mist v3 · Aug 27: 6.9%Mist v3 · Aug 28: 6.5%

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 prompts256 ms
Time to First Audio per dataset, with the number of samples behind each figure.
DatasetTTFASamples
Text prompts256 ms14,524

Strongest condition: Text prompts at 256 ms · weakest: Text prompts at 256 ms.

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