Voice AI BenchmarksBy

SMALLESTTEXT-TO-SPEECH51,320 SAMPLES / 30 DAYSLAST RUN AUG 28, 2026, 21:30 UTC

official resource

Lightning v3.1 Pro text-to-speech benchmarks

Lightning v3.1 Pro is Smallest.ai's streaming text-to-speech model.

Time to First Audio#27 / 30
586ms
TTFA Network Roundtrip#15 / 28
236ms
TTFA Leading Silence#26 / 28
249ms
Word Error Rate#5 / 30
4.4%

Overview

Lightning is built for real-time multilingual synthesis and voice cloning.

Lightning v3.1 Pro 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
Smallest
Hosted by
Smallest
Source
Official API
Licensing
Proprietary
Deployment
Cloud
Region
US
Features
Multilingual, Voice cloning

How Lightning v3.1 Pro 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 Lightning v3.1 Pro 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
  13. #13Aura 2328 ms
  14. #14S2.1 Pro374 ms
  15. #15Default384 ms
  16. #16Speech 2.8 Turbo411 ms
  17. #17Eleven v3 Conversational412 ms
  18. #18Grok TTS420 ms
  19. #19S1434 ms
  20. #20Flash v2.5455 ms
  21. #21Speech 2.8 HD460 ms
  22. #22Sonic 3.6466 ms
  23. #23Simba 3.2484 ms
  24. #24Chirp 3 HD512 ms
  25. #25Simba 3.0526 ms
  26. #26Falcon 2549 ms
  27. #27Lightning v3.1 Pro586 ms
Show all 30 models
  1. #28Qwen3 TTS Flash Realtime645 ms
  2. #29S2.1 Pro Free806 ms
  3. #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: 5th of 30 on Word Error Rate.

Latency vs accuracy

TTFA vs WEREach point is one measured model · Lightning v3.1 Pro highlighted · 30-day averagesTime to First Audio against Word Error Rate for every measured TTS model, with Lightning v3.1 Pro 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%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%Qwen3 TTS Flash Realtime — 645 ms, 8.8%S2.1 Pro Free — 806 ms, 4.7%GPT-4o mini TTS — 1075 ms, 4.8%Lightning v3.1 Pro — 586 ms, 4.4%

Averages and tail latency

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

Lightning v3.1 Pro latency distributionMilliseconds · shared axis across metrics · last 30 daysLightning v3.1 Pro's latency percentiles per metric: p25–p75 band, p50 tick, whisker to p99.
  • Time to First Audiop50 427 ms · p99 1165 ms
  • TTFA Network Roundtripp50 227 ms · p99 433 ms
  • TTFA Leading Silencep50 124 ms · p99 900 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 Audio586 ms323 ms427 ms883 ms1020 ms1084 ms1165 ms14,515
TTFA Network Roundtrip236 ms216 ms227 ms242 ms262 ms284 ms433 ms11,145
TTFA Leading Silence249 ms80 ms124 ms381 ms717 ms797 ms900 ms11,145
Word Error Rate4.4%0.0%0.0%6.3%20.0%20.0%30.0%14,515

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 daysLightning v3.1 Pro's daily median Time to First Audio over the last 30 days.
Lightning v3.1 Pro · Jul 30: 919 msLightning v3.1 Pro · Jul 31: 880 msLightning v3.1 Pro · Aug 1: 1,005 msLightning v3.1 Pro · Aug 2: 930 msLightning v3.1 Pro · Aug 3: 949 msLightning v3.1 Pro · Aug 4: 936 msLightning v3.1 Pro · Aug 5: 924 msLightning v3.1 Pro · Aug 6: 924 msLightning v3.1 Pro · Aug 7: 930 msLightning v3.1 Pro · Aug 8: 948 msLightning v3.1 Pro · Aug 9: 935 msLightning v3.1 Pro · Aug 10: 960 msLightning v3.1 Pro · Aug 11: 352 msLightning v3.1 Pro · Aug 12: 307 msLightning v3.1 Pro · Aug 13: 337 msLightning v3.1 Pro · Aug 14: 325 msLightning v3.1 Pro · Aug 15: 362 msLightning v3.1 Pro · Aug 16: 331 msLightning v3.1 Pro · Aug 17: 338 msLightning v3.1 Pro · Aug 18: 368 msLightning v3.1 Pro · Aug 19: 301 msLightning v3.1 Pro · Aug 20: 317 msLightning v3.1 Pro · Aug 21: 327 msLightning v3.1 Pro · Aug 22: 295 msLightning v3.1 Pro · Aug 23: 346 msLightning v3.1 Pro · Aug 24: 346 msLightning v3.1 Pro · Aug 25: 328 msLightning v3.1 Pro · Aug 26: 361 msLightning v3.1 Pro · Aug 27: 325 msLightning v3.1 Pro · Aug 28: 363 ms
Word Error Rate — daily averageDaily average · UTC daysLightning v3.1 Pro's daily Word Error Rate over the last 30 days.
Lightning v3.1 Pro · Jul 30: 6.7%Lightning v3.1 Pro · Jul 31: 4.0%Lightning v3.1 Pro · Aug 1: 6.1%Lightning v3.1 Pro · Aug 2: 4.4%Lightning v3.1 Pro · Aug 3: 4.3%Lightning v3.1 Pro · Aug 4: 5.2%Lightning v3.1 Pro · Aug 5: 4.9%Lightning v3.1 Pro · Aug 6: 4.6%Lightning v3.1 Pro · Aug 7: 4.6%Lightning v3.1 Pro · Aug 8: 4.9%Lightning v3.1 Pro · Aug 9: 5.1%Lightning v3.1 Pro · Aug 10: 4.5%Lightning v3.1 Pro · Aug 11: 5.0%Lightning v3.1 Pro · Aug 12: 4.9%Lightning v3.1 Pro · Aug 13: 3.8%Lightning v3.1 Pro · Aug 14: 5.0%Lightning v3.1 Pro · Aug 15: 3.6%Lightning v3.1 Pro · Aug 16: 4.7%Lightning v3.1 Pro · Aug 17: 4.8%Lightning v3.1 Pro · Aug 18: 4.1%Lightning v3.1 Pro · Aug 19: 4.9%Lightning v3.1 Pro · Aug 20: 4.0%Lightning v3.1 Pro · Aug 21: 5.2%Lightning v3.1 Pro · Aug 22: 4.8%Lightning v3.1 Pro · Aug 23: 3.9%Lightning v3.1 Pro · Aug 24: 4.8%Lightning v3.1 Pro · Aug 25: 4.4%Lightning v3.1 Pro · Aug 26: 4.8%Lightning v3.1 Pro · Aug 27: 4.1%Lightning v3.1 Pro · Aug 28: 4.2%

Time to First Audio by dataset

Lightning v3.1 Pro by test conditionMilliseconds · lower is better · best condition firstLightning v3.1 Pro's Time to First Audio on each benchmark dataset.
  1. Text prompts586 ms
Time to First Audio per dataset, with the number of samples behind each figure.
DatasetTTFASamples
Text prompts586 ms14,515

Strongest condition: Text prompts at 586 ms · weakest: Text prompts at 586 ms.

Limits of this comparison

Lightning is measured separately from the company's Pulse speech-to-text model.

  • Coval does not score cloning fidelity, naturalness or the latency of a combined Smallest.ai agent. Pulse and Lightning measurements cannot simply be added because a production pipeline also adds endpointing, orchestration and network overhead.

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