Voice AI BenchmarksBy

GOOGLETEXT-TO-SPEECH51,380 SAMPLES / 30 DAYSLAST RUN AUG 28, 2026, 21:30 UTC

official resource

Chirp 3 HD text-to-speech benchmarks

Chirp 3 HD is Google Cloud's high-definition generative text-to-speech family.

Time to First Audio#24 / 30
512ms
TTFA Network Roundtrip#10 / 28
163ms
TTFA Leading Silence#27 / 28
350ms
Word Error Rate#18 / 30
5.2%

Overview

Chirp 3 HD voices ship in Cloud Text-to-Speech with multilingual coverage and first-party hosting.

Chirp 3 HD 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
Google
Hosted by
Google
Source
Official API
Licensing
Proprietary
Deployment
Cloud
Region
US
Features
Multilingual

How Chirp 3 HD 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 Chirp 3 HD 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
Show all 30 models
  1. #25Simba 3.0526 ms
  2. #26Falcon 2549 ms
  3. #27Lightning v3.1 Pro586 ms
  4. #28Qwen3 TTS Flash Realtime645 ms
  5. #29S2.1 Pro Free806 ms
  6. #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: 18th of 30 on Word Error Rate.

Latency vs accuracy

TTFA vs WEREach point is one measured model · Chirp 3 HD highlighted · 30-day averagesTime to First Audio against Word Error Rate for every measured TTS model, with Chirp 3 HD 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%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%Chirp 3 HD — 512 ms, 5.2%

Averages and tail latency

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

Chirp 3 HD latency distributionMilliseconds · shared axis across metrics · last 30 daysChirp 3 HD's latency percentiles per metric: p25–p75 band, p50 tick, whisker to p99.
  • Time to First Audiop50 491 ms · p99 1161 ms
  • TTFA Network Roundtripp50 134 ms · p99 792 ms
  • TTFA Leading Silencep50 343 ms · p99 758 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 Audio512 ms398 ms491 ms589 ms777 ms868 ms1161 ms14,530
TTFA Network Roundtrip163 ms122 ms134 ms152 ms196 ms314 ms792 ms11,160
TTFA Leading Silence350 ms254 ms343 ms423 ms582 ms671 ms758 ms11,160
Word Error Rate5.2%0.0%0.0%6.3%20.0%28.0%37.5%14,530

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 daysChirp 3 HD's daily median Time to First Audio over the last 30 days.
Chirp 3 HD · Jul 30: 452 msChirp 3 HD · Jul 31: 475 msChirp 3 HD · Aug 1: 455 msChirp 3 HD · Aug 2: 475 msChirp 3 HD · Aug 3: 454 msChirp 3 HD · Aug 4: 550 msChirp 3 HD · Aug 5: 484 msChirp 3 HD · Aug 6: 531 msChirp 3 HD · Aug 7: 516 msChirp 3 HD · Aug 8: 485 msChirp 3 HD · Aug 9: 464 msChirp 3 HD · Aug 10: 433 msChirp 3 HD · Aug 11: 488 msChirp 3 HD · Aug 12: 483 msChirp 3 HD · Aug 13: 484 msChirp 3 HD · Aug 14: 479 msChirp 3 HD · Aug 15: 496 msChirp 3 HD · Aug 16: 463 msChirp 3 HD · Aug 17: 447 msChirp 3 HD · Aug 18: 487 msChirp 3 HD · Aug 19: 481 msChirp 3 HD · Aug 20: 434 msChirp 3 HD · Aug 21: 537 msChirp 3 HD · Aug 22: 459 msChirp 3 HD · Aug 23: 526 msChirp 3 HD · Aug 24: 531 msChirp 3 HD · Aug 25: 460 msChirp 3 HD · Aug 26: 507 msChirp 3 HD · Aug 27: 497 msChirp 3 HD · Aug 28: 482 ms
Word Error Rate — daily averageDaily average · UTC daysChirp 3 HD's daily Word Error Rate over the last 30 days.
Chirp 3 HD · Jul 30: 7.1%Chirp 3 HD · Jul 31: 4.9%Chirp 3 HD · Aug 1: 6.8%Chirp 3 HD · Aug 2: 5.1%Chirp 3 HD · Aug 3: 5.8%Chirp 3 HD · Aug 4: 6.0%Chirp 3 HD · Aug 5: 5.8%Chirp 3 HD · Aug 6: 5.2%Chirp 3 HD · Aug 7: 5.1%Chirp 3 HD · Aug 8: 5.3%Chirp 3 HD · Aug 9: 6.6%Chirp 3 HD · Aug 10: 5.9%Chirp 3 HD · Aug 11: 5.8%Chirp 3 HD · Aug 12: 5.8%Chirp 3 HD · Aug 13: 4.4%Chirp 3 HD · Aug 14: 6.3%Chirp 3 HD · Aug 15: 5.2%Chirp 3 HD · Aug 16: 6.7%Chirp 3 HD · Aug 17: 5.5%Chirp 3 HD · Aug 18: 5.0%Chirp 3 HD · Aug 19: 5.7%Chirp 3 HD · Aug 20: 5.3%Chirp 3 HD · Aug 21: 5.7%Chirp 3 HD · Aug 22: 4.8%Chirp 3 HD · Aug 23: 5.5%Chirp 3 HD · Aug 24: 5.2%Chirp 3 HD · Aug 25: 4.8%Chirp 3 HD · Aug 26: 7.0%Chirp 3 HD · Aug 27: 4.8%Chirp 3 HD · Aug 28: 4.9%

Time to First Audio by dataset

Chirp 3 HD by test conditionMilliseconds · lower is better · best condition firstChirp 3 HD's Time to First Audio on each benchmark dataset.
  1. Text prompts512 ms
Time to First Audio per dataset, with the number of samples behind each figure.
DatasetTTFASamples
Text prompts512 ms14,530

Strongest condition: Text prompts at 512 ms · weakest: Text prompts at 512 ms.

Limits of this comparison

Coval measures a configured Cloud voice as a distinct endpoint and compares it with other managed synthesis APIs.

  • The family contains multiple voices and languages; these results apply to Coval's configured voice, not every Chirp 3 HD voice.

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