Voice AI BenchmarksBy

SONIOXTEXT-TO-SPEECH51,376 SAMPLES / 30 DAYSLAST RUN AUG 28, 2026, 21:30 UTC

official resource

TTS RT v1 text-to-speech benchmarks

TTS RT v1 is Soniox's first versioned real-time synthesis endpoint.

Time to First Audio#10 / 30
275ms
TTFA Network Roundtrip#12 / 28
195ms
TTFA Leading Silence#10 / 28
75ms
Word Error Rate#1 / 30
3.7%

Overview

Soniox provides the endpoint for streaming multilingual synthesis with voice cloning.

TTS RT v1 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
Soniox
Hosted by
Soniox
Source
Official API
Licensing
Proprietary
Deployment
Cloud
Region
US
Features
Multilingual, Voice cloning

How TTS RT v1 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 TTS RT v1 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.

Highest relative placement: 1st of 30 on Word Error Rate.

Latency vs accuracy

TTFA vs WEREach point is one measured model · TTS RT v1 highlighted · 30-day averagesTime to First Audio against Word Error Rate for every measured TTS model, with TTS RT v1 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%Mist v3 — 256 ms, 6.3%TTS Rt v2 — 262 ms, 3.9%Sonic 3.5 — 274 ms, 6.1%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%TTS RT v1 — 275 ms, 3.7%

Averages and tail latency

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

TTS RT v1 latency distributionMilliseconds · shared axis across metrics · last 30 daysTTS RT v1's latency percentiles per metric: p25–p75 band, p50 tick, whisker to p99.
  • Time to First Audiop50 280 ms · p99 363 ms
  • TTFA Network Roundtripp50 204 ms · p99 274 ms
  • TTFA Leading Silencep50 75 ms · p99 113 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 Audio275 ms244 ms280 ms299 ms315 ms326 ms363 ms14,528
TTFA Network Roundtrip195 ms156 ms204 ms219 ms230 ms241 ms274 ms11,160
TTFA Leading Silence75 ms64 ms75 ms86 ms94 ms99 ms113 ms11,160
Word Error Rate3.7%0.0%0.0%5.9%14.3%20.0%28.6%14,528

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 daysTTS RT v1's daily median Time to First Audio over the last 30 days.
TTS RT v1 · Jul 31: 296 msTTS RT v1 · Aug 1: 278 msTTS RT v1 · Aug 2: 289 msTTS RT v1 · Aug 3: 294 msTTS RT v1 · Aug 4: 279 msTTS RT v1 · Aug 5: 303 msTTS RT v1 · Aug 6: 291 msTTS RT v1 · Aug 7: 292 msTTS RT v1 · Aug 8: 280 msTTS RT v1 · Aug 9: 286 msTTS RT v1 · Aug 10: 291 msTTS RT v1 · Aug 11: 285 msTTS RT v1 · Aug 12: 301 msTTS RT v1 · Aug 13: 286 msTTS RT v1 · Aug 14: 302 msTTS RT v1 · Aug 15: 291 msTTS RT v1 · Aug 16: 287 msTTS RT v1 · Aug 17: 295 msTTS RT v1 · Aug 18: 263 msTTS RT v1 · Aug 19: 217 msTTS RT v1 · Aug 20: 220 msTTS RT v1 · Aug 21: 235 msTTS RT v1 · Aug 22: 217 msTTS RT v1 · Aug 23: 225 msTTS RT v1 · Aug 24: 231 msTTS RT v1 · Aug 25: 247 msTTS RT v1 · Aug 26: 239 msTTS RT v1 · Aug 27: 241 msTTS RT v1 · Aug 28: 251 ms
Word Error Rate — daily averageDaily average · UTC daysTTS RT v1's daily Word Error Rate over the last 30 days.
TTS RT v1 · Jul 31: 3.8%TTS RT v1 · Aug 1: 4.4%TTS RT v1 · Aug 2: 3.7%TTS RT v1 · Aug 3: 4.1%TTS RT v1 · Aug 4: 3.6%TTS RT v1 · Aug 5: 3.5%TTS RT v1 · Aug 6: 3.8%TTS RT v1 · Aug 7: 3.7%TTS RT v1 · Aug 8: 4.9%TTS RT v1 · Aug 9: 3.8%TTS RT v1 · Aug 10: 4.0%TTS RT v1 · Aug 11: 4.4%TTS RT v1 · Aug 12: 4.4%TTS RT v1 · Aug 13: 3.0%TTS RT v1 · Aug 14: 4.5%TTS RT v1 · Aug 15: 3.3%TTS RT v1 · Aug 16: 4.3%TTS RT v1 · Aug 17: 3.7%TTS RT v1 · Aug 18: 3.7%TTS RT v1 · Aug 19: 3.7%TTS RT v1 · Aug 20: 4.5%TTS RT v1 · Aug 21: 3.3%TTS RT v1 · Aug 22: 4.2%TTS RT v1 · Aug 23: 3.7%TTS RT v1 · Aug 24: 3.8%TTS RT v1 · Aug 25: 4.4%TTS RT v1 · Aug 26: 4.1%TTS RT v1 · Aug 27: 3.5%TTS RT v1 · Aug 28: 3.9%

Time to First Audio by dataset

TTS RT v1 by test conditionMilliseconds · lower is better · best condition firstTTS RT v1's Time to First Audio on each benchmark dataset.
  1. Text prompts275 ms
Time to First Audio per dataset, with the number of samples behind each figure.
DatasetTTFASamples
Text prompts275 ms14,528

Strongest condition: Text prompts at 275 ms · weakest: Text prompts at 275 ms.

Limits of this comparison

RT v1 remains measured separately from v2 using the same prompts.

  • The benchmark uses one voice and does not rate clone fidelity or every supported language.

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