Voice AI BenchmarksBy

FISH AUDIOTEXT-TO-SPEECH45,580 SAMPLES / 30 DAYSLAST RUN SEP 15, 2026, 06:30 UTC

official resource

S2.1 Pro text-to-speech benchmarks

S2.1 Pro, hosted by Fish Audio (FishAudio, fish.audio), measures mean 335 ms time to first audio (16th of 28) and 4.8% word error rate (9th of 28) among TTS systems. Results cover the last 30 days. Coval benchmarks hosted endpoints daily using a consistent evaluation methodology. Last measured .

S2.1 Pro is Fish Audio's production endpoint in the S2.1 synthesis family.

Time to First Audio#16 / 28
335ms
TTFA Network Roundtrip#22 / 28
316ms
TTFA Leading Silence#6 / 28
19ms
Word Error Rate#9 / 28
4.8%

Overview

Both S2.1 routes support multilingual synthesis, voice cloning and emotion control and receive identical benchmark prompts.

S2.1 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
Fish Audio
Hosted by
Fish Audio
Source
Official API
Licensing
Proprietary
Deployment
Cloud
Region
US
Features
Emotion control, Multilingual, Voice cloning

How S2.1 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 S2.1 Pro highlighted.
  1. #1vui66 ms
  2. #2Qwen3 TTS Fast71 ms
  3. #3TTS Flash 291 ms
  4. #4Qwen3 TTS 1.7b106 ms
  5. #5Palabra TTS v1115 ms
  6. #6TTS 2181 ms
  7. #7Flash v2.5194 ms
  8. #8Default235 ms
  9. #9TTS Rt v2245 ms
  10. #10TTS RT v1245 ms
  11. #11Mist v3258 ms
  12. #12Sonic 3.5276 ms
  13. #13Phantom Z 3.4 conversational286 ms
  14. #14Aura 2308 ms
  15. #15Coda312 ms
  16. #16S2.1 Pro335 ms
Show all 28 models
  1. #17Eleven v3 Conversational348 ms
  2. #18Lightning v3.1 Pro362 ms
  3. #19S1379 ms
  4. #20Grok TTS397 ms
  5. #21Sonic 3.6423 ms
  6. #22Simba 3.2452 ms
  7. #23Simba 3.0471 ms
  8. #24Chirp 3 HD535 ms
  9. #25Falcon 2545 ms
  10. #26Qwen3 TTS Flash Realtime754 ms
  11. #27S2.1 Pro Free965 ms
  12. #28GPT-4o mini TTS1013 ms
median of all models · 310 ms
TTS models over the last 30 days, ranked on Time to First Audio.
#ModelHostTTFAWERSamples
1vuiFluxions66 ms9,450
2Qwen3 TTS FastNari71 ms2,190
3TTS Flash 2Inworld AI91 ms11,401
4Qwen3 TTS 1.7bBaseten106 ms420
5Palabra TTS v1Palabra115 ms11,385
6TTS 2Inworld AI181 ms11,401
7Flash v2.5ElevenLabs194 ms9,118
8DefaultGradium235 ms9,127
9TTS Rt v2Soniox245 ms11,232
10TTS RT v1Soniox245 ms11,234
11Mist v3Rime258 ms11,387
12Sonic 3.5Cartesia276 ms11,400
13Phantom Z 3.4 conversationalDeepdub286 ms11,396
14Aura 2Deepgram308 ms11,386
15CodaRime312 ms11,392
16S2.1 ProFish Audio335 ms11,400
17Eleven v3 ConversationalElevenLabs348 ms11,389
18Lightning v3.1 ProSmallest362 ms11,401
19S1Fish Audio379 ms11,393
20Grok TTSxAI397 ms11,386
21Sonic 3.6Cartesia423 ms8,210
22Simba 3.2Speechify452 ms11,393
23Simba 3.0Speechify471 ms11,396
24Chirp 3 HDGoogle535 ms11,400
25Falcon 2Murf545 ms11,397
26Qwen3 TTS Flash RealtimeAlibaba754 ms11,226
27S2.1 Pro FreeFish Audio965 ms11,366
28GPT-4o mini TTSOpenAI1013 ms11,370
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: 9th of 28 on Word Error Rate.

Latency vs accuracy

TTFA vs WEREach point is one measured model · S2.1 Pro highlighted · 30-day averagesTime to First Audio against Word Error Rate for every measured TTS model, with S2.1 Pro highlighted.
vui — 66 ms, 5.5%Qwen3 TTS Fast — 71 ms, 4.2%TTS Flash 2 — 91 ms, 5.4%Qwen3 TTS 1.7b — 106 ms, 5.5%Palabra TTS v1 — 115 ms, 5.8%TTS 2 — 181 ms, 4.6%Flash v2.5 — 194 ms, 6.7%Default — 235 ms, 5.3%TTS Rt v2 — 245 ms, 4.2%TTS RT v1 — 245 ms, 3.9%Mist v3 — 258 ms, 5.6%Sonic 3.5 — 276 ms, 5.9%Phantom Z 3.4 conversational — 286 ms, 6.0%Aura 2 — 308 ms, 5.2%Coda — 312 ms, 5.0%Eleven v3 Conversational — 348 ms, 4.4%Lightning v3.1 Pro — 362 ms, 4.4%S1 — 379 ms, 4.9%Grok TTS — 397 ms, 4.9%Sonic 3.6 — 423 ms, 5.3%Simba 3.2 — 452 ms, 4.4%Simba 3.0 — 471 ms, 5.2%Chirp 3 HD — 535 ms, 5.2%Falcon 2 — 545 ms, 5.2%Qwen3 TTS Flash Realtime — 754 ms, 8.9%S2.1 Pro Free — 965 ms, 4.7%GPT-4o mini TTS — 1013 ms, 4.8%S2.1 Pro — 335 ms, 4.8%

Where the errors come from

WER compositionS2.1 Pro's Word Error Rate split by error type · 30-day averageS2.1 Pro's WER split into substitutions, deletions and insertions.
  • S2.1 Pro4.8%
SubstitutionsDeletionsInsertions

Averages and tail latency

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

S2.1 Pro latency distributionMilliseconds · shared axis across metrics · last 30 daysS2.1 Pro's latency percentiles per metric: p25–p75 band, p50 tick, whisker to p99.
  • Time to First Audiop50 299 ms · p99 868 ms
  • TTFA Network Roundtripp50 283 ms · p99 838 ms
  • TTFA Leading Silencep50 7 ms · p99 106 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 Audio335 ms274 ms299 ms337 ms397 ms580 ms868 ms11,400
TTFA Network Roundtrip316 ms263 ms283 ms309 ms353 ms560 ms838 ms11,400
TTFA Leading Silence19 ms2 ms7 ms27 ms57 ms80 ms106 ms11,400
Word Error Rate4.8%0.0%0.0%7.7%18.8%21.4%30.0%11,380

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 daysS2.1 Pro's daily median Time to First Audio over the last 30 days.
S2.1 Pro · Sep 1: 303 msS2.1 Pro · Sep 2: 294 msS2.1 Pro · Sep 3: 287 msS2.1 Pro · Sep 4: 299 msS2.1 Pro · Sep 5: 300 msS2.1 Pro · Sep 6: 297 msS2.1 Pro · Sep 7: 300 msS2.1 Pro · Sep 8: 282 msS2.1 Pro · Sep 9: 298 msS2.1 Pro · Sep 10: 301 msS2.1 Pro · Sep 11: 298 msS2.1 Pro · Sep 12: 300 msS2.1 Pro · Sep 13: 287 msS2.1 Pro · Sep 14: 295 msS2.1 Pro · Sep 15: 302 ms
Word Error Rate — daily averageDaily average · UTC daysS2.1 Pro's daily Word Error Rate over the last 30 days.
S2.1 Pro · Sep 1: 4.2%S2.1 Pro · Sep 2: 4.4%S2.1 Pro · Sep 3: 4.5%S2.1 Pro · Sep 4: 4.8%S2.1 Pro · Sep 5: 5.0%S2.1 Pro · Sep 6: 5.8%S2.1 Pro · Sep 7: 4.6%S2.1 Pro · Sep 8: 5.0%S2.1 Pro · Sep 9: 5.0%S2.1 Pro · Sep 10: 5.3%S2.1 Pro · Sep 11: 5.0%S2.1 Pro · Sep 12: 4.8%S2.1 Pro · Sep 13: 4.8%S2.1 Pro · Sep 14: 4.9%S2.1 Pro · Sep 15: 5.4%

Time to First Audio by dataset

S2.1 Pro by test conditionMilliseconds · lower is better · best condition firstS2.1 Pro's Time to First Audio on each benchmark dataset.
  1. Text prompts335 ms
Time to First Audio per dataset, with the number of samples behind each figure.
DatasetTTFASamples
Text prompts335 ms11,400

Strongest condition: Text prompts at 335 ms · weakest: Text prompts at 335 ms.

How fast is S2.1 Pro?

On Fish Audio, S2.1 Pro measures mean 335 ms time to first audio (16th of 28). Last measured 2026-09-15.

How accurate is S2.1 Pro?

On Fish Audio, S2.1 Pro measures 4.8% word error rate (9th of 28). Last measured 2026-09-15.

Who hosts S2.1 Pro?

S2.1 Pro is created by Fish Audio and served by Fish Audio. Coval measures each hosted endpoint separately.

Limits of this comparison

Coval reports it separately from S2.1 Pro Free so service-tier behavior is not averaged together.

  • Tier labels do not guarantee a performance ordering; the current measurements determine relative rank.

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