Voice AI BenchmarksBy

RIMETEXT-TO-SPEECH2,408 SAMPLES / 30 DAYSLAST RUN SEP 30, 2026, 23:00 UTC

official resource

Mist v3 text-to-speech benchmarks

Mist v3, hosted by Rime, measures mean 287 ms time to first audio (16th of 32) and 2.1% word error rate (26th of 32) 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#16 / 32
287ms
TTFA Network Roundtrip#16 / 32
152ms
TTFA Leading Silence#26 / 32
134ms
Word Error Rate#26 / 32
2.1%

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. #1vui60 ms
  2. #2Default63 ms
  3. #3Qwen3 TTS Fast68 ms
  4. #4TTS Flash 291 ms
  5. #5Qwen3 TTS 1.7b107 ms
  6. #6Simba 3.0111 ms
  7. #7Palabra TTS v1120 ms
  8. #8Simba 3.2126 ms
  9. #9drama3-preview169 ms
  10. #10TTS 2191 ms
  11. #11Flash v2.5191 ms
  12. #12Eleven v4 Turbo201 ms
  13. #13Flux TTS205 ms
  14. #14TTS RT v1254 ms
  15. #15TTS Rt v2256 ms
  16. #16Mist v3287 ms
Show all 32 models
  1. #17Sonic 3.5293 ms
  2. #18Phantom Z 3.4 conversational294 ms
  3. #19Aura 2297 ms
  4. #20Sonic 3.6299 ms
  5. #21Falcon 2302 ms
  6. #22Coda332 ms
  7. #23S2.1 Pro341 ms
  8. #24Grok TTS363 ms
  9. #25S1389 ms
  10. #26Lightning v3.1 Pro393 ms
  11. #27Daytona TTS486 ms
  12. #28Aura 2 En571 ms
  13. #29Chirp 3 HD597 ms
  14. #30Qwen3 TTS Flash Realtime718 ms
  15. #31S2.1 Pro Free850 ms
  16. #32GPT-4o mini TTS2582 ms
median of all models · 290 ms
TTS models over the last 30 days, ranked on Time to First Audio.
#ModelHostTTFAWERSamples
1vuiFluxions60 ms1,722
2Gradium TTS Beta 202609Gradium63 ms1,894
3Qwen3 TTS FastNari Labs68 ms1,894
4TTS Flash 2Inworld AI91 ms1,698
5Qwen3 TTS 1.7bBaseten107 ms1,248
6Simba 3.0SpeechifyAI111 ms1,893
7Palabra TTS v1Palabra120 ms1,556
8Simba 3.2SpeechifyAI126 ms1,890
9Drama 3 Preview Us EastFish Audio169 ms140
10TTS 2Inworld AI191 ms1,698
11Flash v2.5ElevenLabs191 ms1,885
12Eleven v4 TurboElevenLabs201 ms1,204
13Flux TTSDeepgram205 ms1,757
14TTS RT v1Soniox254 ms1,597
15TTS Rt v2Soniox256 ms1,595
16Mist v3Rime287 ms602
17Sonic 3.5Cartesia293 ms1,894
18Phantom Z 3.4 conversationalDeepdub294 ms1,629
19Aura 2Deepgram297 ms1,826
20Sonic 3.6Cartesia299 ms1,894
21Falcon 2Murf302 ms1,893
22CodaRime332 ms602
23S2.1 ProFish Audio341 ms1,894
24Grok TTSSpaceXAI363 ms1,889
25S1Fish Audio389 ms1,893
26Lightning v3.1 ProSmallest393 ms1,894
27Daytona TTSGuava486 ms1,152
28Aura 2 EnCloudflare571 ms1,893
29Chirp 3 HDGoogle597 ms1,894
30Qwen3 TTS Flash RealtimeAlibaba718 ms1,893
31S2.1 Pro FreeFish Audio850 ms1,887
32GPT-4o mini TTSOpenAI2582 ms1,830
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 — 60 ms, 2.1%Default — 63 ms, 1.9%Qwen3 TTS Fast — 68 ms, 1.8%TTS Flash 2 — 91 ms, 1.7%Qwen3 TTS 1.7b — 107 ms, 1.8%Simba 3.0 — 111 ms, 1.5%Palabra TTS v1 — 120 ms, 2.6%Simba 3.2 — 126 ms, 1.9%drama3-preview — 169 ms, 2.1%TTS 2 — 191 ms, 1.6%Flash v2.5 — 191 ms, 1.8%Eleven v4 Turbo — 201 ms, 1.7%Flux TTS — 205 ms, 1.7%TTS RT v1 — 254 ms, 2.4%TTS Rt v2 — 256 ms, 2.4%Sonic 3.5 — 293 ms, 1.5%Phantom Z 3.4 conversational — 294 ms, 1.8%Aura 2 — 297 ms, 1.8%Sonic 3.6 — 299 ms, 1.5%Falcon 2 — 302 ms, 1.7%Coda — 332 ms, 9.5%S2.1 Pro — 341 ms, 1.5%Grok TTS — 363 ms, 1.6%S1 — 389 ms, 1.8%Lightning v3.1 Pro — 393 ms, 1.5%Daytona TTS — 486 ms, 1.6%Aura 2 En — 571 ms, 2.1%Chirp 3 HD — 597 ms, 1.5%Qwen3 TTS Flash Realtime — 718 ms, 3.0%S2.1 Pro Free — 850 ms, 1.5%GPT-4o mini TTS — 2582 ms, 1.8%Mist v3 — 287 ms, 2.1%

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 v32.1%
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 max.
  • Time to First Audiop50 273 ms · Max 492 ms
  • TTFA Network Roundtripp50 134 ms · Max 348 ms
  • TTFA Leading Silencep50 135 ms · Max 166 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 First Audio287 ms253 ms273 ms323 ms347 ms360 ms492 ms602
TTFA Network Roundtrip152 ms119 ms134 ms193 ms207 ms228 ms348 ms602
TTFA Leading Silence134 ms129 ms135 ms142 ms148 ms152 ms166 ms602
Word Error Rate2.1%0.0%0.0%3.0%8.3%16.6%43.8%602

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 23: 283 msMist v3 · Sep 24: 279 msMist v3 · Sep 25: 290 msMist v3 · Sep 26: 278 msMist v3 · Sep 27: 285 msMist v3 · Sep 28: 264 msMist v3 · Sep 29: 291 msMist v3 · Sep 30: 290 ms
Word Error Rate — daily averageDaily average · UTC daysMist v3's daily Word Error Rate over the last 30 days.
Mist v3 · Sep 23: 4.7%Mist v3 · Sep 24: 2.9%Mist v3 · Sep 25: 2.5%Mist v3 · Sep 26: 3.4%Mist v3 · Sep 27: 3.4%Mist v3 · Sep 28: 3.9%Mist v3 · Sep 29: 3.7%Mist v3 · Sep 30: 3.1%

How fast is Mist v3?

On Rime, Mist v3 measures mean 287 ms time to first audio (16th of 32). Last measured 2026-09-30.

How accurate is Mist v3?

On Rime, Mist v3 measures 2.1% word error rate (26th of 32). Last measured 2026-09-30.

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