Voice AI BenchmarksBy

GUAVATEXT-TO-SPEECH4,224 SAMPLES / 30 DAYSLAST RUN OCT 13, 2026, 00:00 UTC

Daytona TTS text-to-speech benchmarks

Daytona TTS, hosted by Guava, measures mean 486 ms time to first audio (27th of 32) and 1.6% word error rate (10th of 32) among TTS systems. Results cover the last 30 days. Coval benchmarks hosted endpoints daily using a consistent evaluation methodology. Last measured .

Coval has active text-to-speech measurements for Daytona TTS, created by Guava and served through Guava's own API.

Time to First Audio#27 / 32
486ms
TTFA Network Roundtrip#29 / 32
429ms
TTFA Leading Silence#16 / 32
57ms
Word Error Rate#10 / 32
1.6%

Overview

Daytona TTS 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
Guava
Hosted by
Guava
Source
Shared inference
Licensing
Open-weight
Deployment
On-prem

How Daytona TTS 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 Daytona TTS highlighted.
  1. #1vui60 ms
  2. #2Default63 ms
  3. #3Qwen3 TTS Fast68 ms
  4. #4TTS Flash 292 ms
  5. #5Qwen3 TTS 1.7b106 ms
  6. #6Simba 3.0111 ms
  7. #7Palabra TTS v1119 ms
  8. #8Simba 3.2126 ms
  9. #9drama3-preview160 ms
  10. #10Flash v2.5191 ms
  11. #11TTS 2192 ms
  12. #12Eleven v4 Turbo201 ms
  13. #13Flux TTS205 ms
  14. #14TTS RT v1254 ms
  15. #15TTS Rt v2256 ms
  16. #16Mist v3287 ms
  17. #17Sonic 3.5293 ms
  18. #18Phantom Z 3.4 conversational296 ms
  19. #19Aura 2297 ms
  20. #20Sonic 3.6299 ms
  21. #21Falcon 2304 ms
  22. #22Coda332 ms
  23. #23S2.1 Pro341 ms
  24. #24Grok TTS362 ms
  25. #25S1389 ms
  26. #26Lightning v3.1 Pro392 ms
  27. #27Daytona TTS486 ms
Show all 32 models
  1. #28Aura 2 En573 ms
  2. #29Chirp 3 HD598 ms
  3. #30Qwen3 TTS Flash Realtime718 ms
  4. #31S2.1 Pro Free850 ms
  5. #32GPT-4o mini TTS2584 ms
median of all models · 290 ms
TTS models over the last 30 days, ranked on Time to First Audio.
#ModelHostTTFAWERSamples
1vuiFluxions60 ms1,698
2Gradium TTS Beta 202609Gradium63 ms1,870
3Qwen3 TTS FastNari Labs68 ms1,870
4TTS Flash 2Inworld AI92 ms1,674
5Qwen3 TTS 1.7bBaseten106 ms1,152
6Simba 3.0SpeechifyAI111 ms1,869
7Palabra TTS v1Palabra119 ms1,537
8Simba 3.2SpeechifyAI126 ms1,866
9Drama 3 Preview Us EastFish Audio160 ms116
10Flash v2.5ElevenLabs191 ms1,861
11TTS 2Inworld AI192 ms1,674
12Eleven v4 TurboElevenLabs201 ms1,180
13Flux TTSDeepgram205 ms1,733
14TTS RT v1Soniox254 ms1,576
15TTS Rt v2Soniox256 ms1,574
16Mist v3Rime287 ms602
17Sonic 3.5Cartesia293 ms1,870
18Phantom Z 3.4 conversationalDeepdub296 ms1,605
19Aura 2Deepgram297 ms1,802
20Sonic 3.6Cartesia299 ms1,870
21Falcon 2Murf304 ms1,869
22CodaRime332 ms602
23S2.1 ProFish Audio341 ms1,870
24Grok TTSSpaceXAI362 ms1,865
25S1Fish Audio389 ms1,869
26Lightning v3.1 ProSmallest392 ms1,870
27Daytona TTSGuava486 ms1,056
28Aura 2 EnCloudflare573 ms1,869
29Chirp 3 HDGoogle598 ms1,870
30Qwen3 TTS Flash RealtimeAlibaba718 ms1,869
31S2.1 Pro FreeFish Audio850 ms1,863
32GPT-4o mini TTSOpenAI2584 ms1,806
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: 10th of 32 on Word Error Rate.

Latency vs accuracy

TTFA vs WEREach point is one measured model · Daytona TTS highlighted · 30-day averagesTime to First Audio against Word Error Rate for every measured TTS model, with Daytona TTS highlighted.
vui — 60 ms, 2.1%Default — 63 ms, 1.9%Qwen3 TTS Fast — 68 ms, 1.8%TTS Flash 2 — 92 ms, 1.6%Qwen3 TTS 1.7b — 106 ms, 1.7%Simba 3.0 — 111 ms, 1.5%Palabra TTS v1 — 119 ms, 2.6%Simba 3.2 — 126 ms, 1.9%drama3-preview — 160 ms, 2.1%Flash v2.5 — 191 ms, 1.8%TTS 2 — 192 ms, 1.6%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%Mist v3 — 287 ms, 2.1%Sonic 3.5 — 293 ms, 1.5%Phantom Z 3.4 conversational — 296 ms, 1.8%Aura 2 — 297 ms, 1.8%Sonic 3.6 — 299 ms, 1.5%Falcon 2 — 304 ms, 1.7%Coda — 332 ms, 9.5%S2.1 Pro — 341 ms, 1.5%Grok TTS — 362 ms, 1.6%S1 — 389 ms, 1.8%Lightning v3.1 Pro — 392 ms, 1.5%Aura 2 En — 573 ms, 2.0%Chirp 3 HD — 598 ms, 1.5%Qwen3 TTS Flash Realtime — 718 ms, 3.0%S2.1 Pro Free — 850 ms, 1.5%GPT-4o mini TTS — 2584 ms, 1.8%Daytona TTS — 486 ms, 1.6%

Where the errors come from

WER compositionDaytona TTS's Word Error Rate split by error type · 30-day averageDaytona TTS's WER split into substitutions, deletions and insertions.
  • Daytona TTS1.6%
SubstitutionsDeletionsInsertions

Averages and tail latency

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

Daytona TTS latency distributionMilliseconds · shared axis across metrics · last 30 daysDaytona TTS's latency percentiles per metric: p25–p75 band, p50 tick, whisker to max.
  • Time to First Audiop50 477 ms · Max 1693 ms
  • TTFA Network Roundtripp50 434 ms · Max 1201 ms
  • TTFA Leading Silencep50 52 ms · Max 837 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 Audio486 ms433 ms477 ms517 ms566 ms603 ms1693 ms1,056
TTFA Network Roundtrip429 ms376 ms434 ms456 ms479 ms498 ms1201 ms1,056
TTFA Leading Silence57 ms20 ms52 ms76 ms113 ms139 ms837 ms1,056
Word Error Rate1.6%0.0%0.0%1.9%6.6%12.2%43.8%1,056

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 daysDaytona TTS's daily median Time to First Audio over the last 30 days.
Daytona TTS · Oct 3: 481 msDaytona TTS · Oct 4: 493 msDaytona TTS · Oct 5: 488 msDaytona TTS · Oct 6: 467 msDaytona TTS · Oct 7: 472 msDaytona TTS · Oct 8: 488 msDaytona TTS · Oct 9: 488 msDaytona TTS · Oct 10: 468 msDaytona TTS · Oct 11: 465 msDaytona TTS · Oct 12: 465 msDaytona TTS · Oct 13: 471 ms
Word Error Rate — daily averageDaily average · UTC daysDaytona TTS's daily Word Error Rate over the last 30 days.
Daytona TTS · Oct 3: 2.0%Daytona TTS · Oct 4: 3.9%Daytona TTS · Oct 5: 2.0%Daytona TTS · Oct 6: 1.8%Daytona TTS · Oct 7: 2.6%Daytona TTS · Oct 8: 1.3%Daytona TTS · Oct 9: 2.3%Daytona TTS · Oct 10: 2.7%Daytona TTS · Oct 11: 2.1%Daytona TTS · Oct 12: 2.1%Daytona TTS · Oct 13: 2.7%

How fast is Daytona TTS?

On Guava, Daytona TTS measures mean 486 ms time to first audio (27th of 32). Last measured 2026-10-13.

How accurate is Daytona TTS?

On Guava, Daytona TTS measures 1.6% word error rate (10th of 32). Last measured 2026-10-13.

Who hosts Daytona TTS?

Daytona TTS is created by Guava and served by Guava. Coval measures each hosted endpoint separately.

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