Voice AI BenchmarksBy

SONIOXTEXT-TO-SPEECH6,339 SAMPLES / 30 DAYSLAST RUN OCT 14, 2026, 06:30 UTC

official resource

TTS RT v1 text-to-speech benchmarks

TTS RT v1, hosted by Soniox, measures mean 254 ms time to first audio (14th of 32) and 2.4% word error rate (29th of 32) among TTS systems. Results cover the last 30 days. Coval benchmarks hosted endpoints daily using a consistent evaluation methodology. Last measured .

TTS RT v1 is Soniox's first versioned real-time synthesis endpoint.

Time to First Audio#14 / 32
254ms
TTFA Network Roundtrip#19 / 32
179ms
TTFA Leading Silence#19 / 32
75ms
Word Error Rate#29 / 32
2.4%

Overview

Soniox provides the endpoint for streaming multilingual synthesis with voice cloning.

TTS RT 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
Soniox
Hosted by
Soniox
Source
Official API
Licensing
Proprietary
Deployment
Cloud
Region
US
Features
Multilingual, Voice cloning

How TTS RT 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 TTS RT v1 highlighted.
  1. #1vui60 ms
  2. #2Default63 ms
  3. #3Qwen3 TTS Fast68 ms
  4. #4TTS Flash 292 ms
  5. #5Qwen3 TTS 1.7b107 ms
  6. #6Simba 3.0111 ms
  7. #7Palabra TTS v1119 ms
  8. #8Simba 3.2126 ms
  9. #9drama3-preview161 ms
  10. #10Flash v2.5191 ms
  11. #11TTS 2192 ms
  12. #12Eleven v4 Turbo201 ms
  13. #13Flux TTS205 ms
  14. #14TTS RT v1254 ms
Show all 32 models
  1. #15TTS Rt v2256 ms
  2. #16Mist v3287 ms
  3. #17Sonic 3.5293 ms
  4. #18Phantom Z 3.4 conversational295 ms
  5. #19Aura 2297 ms
  6. #20Sonic 3.6299 ms
  7. #21Falcon 2303 ms
  8. #22Coda332 ms
  9. #23S2.1 Pro341 ms
  10. #24Grok TTS362 ms
  11. #25S1389 ms
  12. #26Lightning v3.1 Pro392 ms
  13. #27Daytona TTS486 ms
  14. #28Aura 2 En572 ms
  15. #29Chirp 3 HD598 ms
  16. #30Qwen3 TTS Flash Realtime718 ms
  17. #31S2.1 Pro Free850 ms
  18. #32GPT-4o mini TTS2583 ms
median of all models · 290 ms
TTS models over the last 30 days, ranked on Time to First Audio.
#ModelHostTTFAWERSamples
1vuiFluxions60 ms1,708
2Gradium TTS Beta 202609Gradium63 ms1,880
3Qwen3 TTS FastNari Labs68 ms1,880
4TTS Flash 2Inworld AI92 ms1,684
5Qwen3 TTS 1.7bBaseten107 ms1,248
6Simba 3.0SpeechifyAI111 ms1,879
7Palabra TTS v1Palabra119 ms1,545
8Simba 3.2SpeechifyAI126 ms1,876
9Drama 3 Preview Us EastFish Audio161 ms126
10Flash v2.5ElevenLabs191 ms1,871
11TTS 2Inworld AI192 ms1,684
12Eleven v4 TurboElevenLabs201 ms1,190
13Flux TTSDeepgram205 ms1,743
14TTS RT v1Soniox254 ms1,585
15TTS Rt v2Soniox256 ms1,583
16Mist v3Rime287 ms602
17Sonic 3.5Cartesia293 ms1,880
18Phantom Z 3.4 conversationalDeepdub295 ms1,615
19Aura 2Deepgram297 ms1,812
20Sonic 3.6Cartesia299 ms1,880
21Falcon 2Murf303 ms1,879
22CodaRime332 ms602
23S2.1 ProFish Audio341 ms1,880
24Grok TTSSpaceXAI362 ms1,875
25S1Fish Audio389 ms1,879
26Lightning v3.1 ProSmallest392 ms1,880
27Daytona TTSGuava486 ms1,152
28Aura 2 EnCloudflare572 ms1,879
29Chirp 3 HDGoogle598 ms1,880
30Qwen3 TTS Flash RealtimeAlibaba718 ms1,879
31S2.1 Pro FreeFish Audio850 ms1,873
32GPT-4o mini TTSOpenAI2583 ms1,816
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 · TTS RT v1 highlighted · 30-day averagesTime to First Audio against Word Error Rate for every measured TTS model, with TTS RT v1 highlighted.
vui — 60 ms, 2.1%Default — 63 ms, 1.9%Qwen3 TTS Fast — 68 ms, 1.8%TTS Flash 2 — 92 ms, 1.7%Qwen3 TTS 1.7b — 107 ms, 1.8%Simba 3.0 — 111 ms, 1.5%Palabra TTS v1 — 119 ms, 2.6%Simba 3.2 — 126 ms, 1.9%drama3-preview — 161 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 v2 — 256 ms, 2.4%Mist v3 — 287 ms, 2.1%Sonic 3.5 — 293 ms, 1.5%Phantom Z 3.4 conversational — 295 ms, 1.8%Aura 2 — 297 ms, 1.8%Sonic 3.6 — 299 ms, 1.5%Falcon 2 — 303 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%Daytona TTS — 486 ms, 1.6%Aura 2 En — 572 ms, 2.1%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 — 2583 ms, 1.8%TTS RT v1 — 254 ms, 2.4%

Where the errors come from

WER compositionTTS RT v1's Word Error Rate split by error type · 30-day averageTTS RT v1's WER split into substitutions, deletions and insertions.
  • TTS RT v12.4%
SubstitutionsDeletionsInsertions

Averages and tail latency

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

TTS RT v1 latency distributionMilliseconds · shared axis across metrics · last 30 daysTTS RT v1's latency percentiles per metric: p25–p75 band, p50 tick, whisker to max.
  • Time to First Audiop50 258 ms · Max 598 ms
  • TTFA Network Roundtripp50 189 ms · Max 507 ms
  • TTFA Leading Silencep50 76 ms · Max 120 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 Audio254 ms218 ms258 ms288 ms304 ms314 ms598 ms1,585
TTFA Network Roundtrip179 ms142 ms189 ms210 ms224 ms234 ms507 ms1,585
TTFA Leading Silence75 ms65 ms76 ms86 ms92 ms95 ms120 ms1,585
Word Error Rate2.4%0.0%0.0%3.0%9.3%14.3%75.0%1,584

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 daysTTS RT v1's daily median Time to First Audio over the last 30 days.
TTS RT v1 · Sep 23: 259 msTTS RT v1 · Sep 24: 263 msTTS RT v1 · Sep 25: 228 msTTS RT v1 · Sep 26: 259 msTTS RT v1 · Sep 27: 224 msTTS RT v1 · Sep 28: 285 msTTS RT v1 · Sep 29: 280 msTTS RT v1 · Sep 30: 254 msTTS RT v1 · Oct 1: 219 msTTS RT v1 · Oct 2: 261 msTTS RT v1 · Oct 3: 251 msTTS RT v1 · Oct 4: 259 msTTS RT v1 · Oct 5: 251 msTTS RT v1 · Oct 6: 253 msTTS RT v1 · Oct 7: 231 msTTS RT v1 · Oct 8: 285 msTTS RT v1 · Oct 9: 254 msTTS RT v1 · Oct 10: 238 msTTS RT v1 · Oct 11: 250 msTTS RT v1 · Oct 12: 265 msTTS RT v1 · Oct 13: 258 msTTS RT v1 · Oct 14: 223 ms
Word Error Rate — daily averageDaily average · UTC daysTTS RT v1's daily Word Error Rate over the last 30 days.
TTS RT v1 · Sep 23: 3.1%TTS RT v1 · Sep 24: 3.5%TTS RT v1 · Sep 25: 4.6%TTS RT v1 · Sep 26: 3.6%TTS RT v1 · Sep 27: 6.7%TTS RT v1 · Sep 28: 6.7%TTS RT v1 · Sep 29: 7.0%TTS RT v1 · Sep 30: 4.3%TTS RT v1 · Oct 1: 4.7%TTS RT v1 · Oct 2: 3.2%TTS RT v1 · Oct 3: 5.2%TTS RT v1 · Oct 4: 7.7%TTS RT v1 · Oct 5: 3.6%TTS RT v1 · Oct 6: 5.1%TTS RT v1 · Oct 7: 4.9%TTS RT v1 · Oct 8: 6.2%TTS RT v1 · Oct 9: 3.3%TTS RT v1 · Oct 10: 2.3%TTS RT v1 · Oct 11: 3.7%TTS RT v1 · Oct 12: 5.6%TTS RT v1 · Oct 13: 5.4%TTS RT v1 · Oct 14: 15.5%

How fast is TTS RT v1?

On Soniox, TTS RT v1 measures mean 254 ms time to first audio (14th of 32). Last measured 2026-10-14.

How accurate is TTS RT v1?

On Soniox, TTS RT v1 measures 2.4% word error rate (29th of 32). Last measured 2026-10-14.

Who hosts TTS RT v1?

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

Limits of this comparison

RT v1 remains measured separately from v2 using the same prompts.

  • The benchmark uses one voice and does not rate clone fidelity or every supported language.

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