Voice AI BenchmarksBy

PALABRATEXT-TO-SPEECH6,223 SAMPLES / 30 DAYSLAST RUN OCT 14, 2026, 10:30 UTC

official resource

Palabra TTS v1 text-to-speech benchmarks

Palabra TTS v1, hosted by Palabra, measures mean 120 ms time to first audio (7th of 32) and 2.6% word error rate (30th of 32) among TTS systems. Results cover the last 30 days. Coval benchmarks hosted endpoints daily using a consistent evaluation methodology. Last measured .

Palabra TTS v1 is Palabra AI's synthesis API model.

Time to First Audio#7 / 32
120ms
TTFA Network Roundtrip#10 / 32
115ms
TTFA Leading Silence#3 / 32
5ms
Word Error Rate#30 / 32
2.6%

Overview

Palabra TTS v1 supports multilingual output, voice cloning and an on-premises deployment option.

Palabra TTS 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
Palabra
Hosted by
Palabra
Source
Official API
Licensing
Proprietary
Deployment
On-prem
Region
US
Features
Multilingual, Voice cloning

How Palabra TTS 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 Palabra TTS v1 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
Show all 32 models
  1. #13Flux TTS205 ms
  2. #14TTS RT v1254 ms
  3. #15TTS Rt v2256 ms
  4. #16Mist v3287 ms
  5. #17Sonic 3.5293 ms
  6. #18Phantom Z 3.4 conversational294 ms
  7. #19Aura 2297 ms
  8. #20Sonic 3.6299 ms
  9. #21Falcon 2302 ms
  10. #22Coda332 ms
  11. #23S2.1 Pro341 ms
  12. #24Grok TTS363 ms
  13. #25S1389 ms
  14. #26Lightning v3.1 Pro393 ms
  15. #27Daytona TTS486 ms
  16. #28Aura 2 En571 ms
  17. #29Chirp 3 HD597 ms
  18. #30Qwen3 TTS Flash Realtime718 ms
  19. #31S2.1 Pro Free850 ms
  20. #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 · Palabra TTS v1 highlighted · 30-day averagesTime to First Audio against Word Error Rate for every measured TTS model, with Palabra TTS v1 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%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%Mist v3 — 287 ms, 2.1%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%Palabra TTS v1 — 120 ms, 2.6%

Where the errors come from

WER compositionPalabra TTS v1's Word Error Rate split by error type · 30-day averagePalabra TTS v1's WER split into substitutions, deletions and insertions.
  • Palabra TTS v12.6%
SubstitutionsDeletionsInsertions

Averages and tail latency

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

Palabra TTS v1 latency distributionMilliseconds · shared axis across metrics · last 30 daysPalabra TTS v1's latency percentiles per metric: p25–p75 band, p50 tick, whisker to max.
  • Time to First Audiop50 107 ms · Max 2257 ms
  • TTFA Network Roundtripp50 102 ms · Max 2252 ms
  • TTFA Leading Silencep50 5 ms · Max 6 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 Audio120 ms96 ms107 ms123 ms145 ms203 ms2257 ms1,556
TTFA Network Roundtrip115 ms91 ms102 ms118 ms140 ms198 ms2252 ms1,556
TTFA Leading Silence5 ms5 ms5 ms5 ms5 ms5 ms6 ms1,556
Word Error Rate2.6%0.0%0.0%3.0%9.5%17.6%61.5%1,555

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 daysPalabra TTS v1's daily median Time to First Audio over the last 30 days.
Palabra TTS v1 · Sep 23: 358 msPalabra TTS v1 · Sep 24: 107 msPalabra TTS v1 · Sep 25: 106 msPalabra TTS v1 · Sep 26: 113 msPalabra TTS v1 · Sep 27: 97 msPalabra TTS v1 · Sep 28: 113 msPalabra TTS v1 · Sep 29: 112 msPalabra TTS v1 · Sep 30: 109 msPalabra TTS v1 · Oct 1: 113 msPalabra TTS v1 · Oct 2: 119 msPalabra TTS v1 · Oct 3: 112 msPalabra TTS v1 · Oct 4: 107 msPalabra TTS v1 · Oct 5: 95 msPalabra TTS v1 · Oct 6: 102 msPalabra TTS v1 · Oct 7: 125 msPalabra TTS v1 · Oct 8: 119 msPalabra TTS v1 · Oct 9: 132 msPalabra TTS v1 · Oct 10: 95 msPalabra TTS v1 · Oct 11: 161 msPalabra TTS v1 · Oct 12: 96 msPalabra TTS v1 · Oct 13: 147 msPalabra TTS v1 · Oct 14: 121 ms
Word Error Rate — daily averageDaily average · UTC daysPalabra TTS v1's daily Word Error Rate over the last 30 days.
Palabra TTS v1 · Sep 23: 3.1%Palabra TTS v1 · Sep 24: 4.4%Palabra TTS v1 · Sep 25: 4.7%Palabra TTS v1 · Sep 26: 4.3%Palabra TTS v1 · Sep 27: 6.4%Palabra TTS v1 · Sep 28: 8.0%Palabra TTS v1 · Sep 29: 4.2%Palabra TTS v1 · Sep 30: 5.0%Palabra TTS v1 · Oct 1: 7.5%Palabra TTS v1 · Oct 2: 4.6%Palabra TTS v1 · Oct 3: 6.3%Palabra TTS v1 · Oct 4: 8.1%Palabra TTS v1 · Oct 5: 3.6%Palabra TTS v1 · Oct 6: 6.1%Palabra TTS v1 · Oct 7: 6.6%Palabra TTS v1 · Oct 8: 5.8%Palabra TTS v1 · Oct 9: 4.0%Palabra TTS v1 · Oct 10: 2.2%Palabra TTS v1 · Oct 11: 9.2%Palabra TTS v1 · Oct 12: 5.5%Palabra TTS v1 · Oct 13: 6.3%Palabra TTS v1 · Oct 14: 9.6%

How fast is Palabra TTS v1?

On Palabra, Palabra TTS v1 measures mean 120 ms time to first audio (7th of 32). Last measured 2026-10-14.

How accurate is Palabra TTS v1?

On Palabra, Palabra TTS v1 measures 2.6% word error rate (30th of 32). Last measured 2026-10-14.

Who hosts Palabra TTS v1?

Palabra TTS v1 is created by Palabra and served by Palabra. Coval measures each hosted endpoint separately.

Limits of this comparison

Coval benchmarks it independently from Palabra's translation products, focusing on audible startup and intelligibility.

  • The benchmark does not measure live translation quality, dubbing alignment or speaker similarity.

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