Voice AI BenchmarksBy

INWORLD AITEXT-TO-SPEECH45,704 SAMPLES / 30 DAYSLAST RUN SEP 15, 2026, 08:00 UTC

official resource

TTS 2 text-to-speech benchmarks

TTS 2, hosted by Inworld AI, measures mean 181 ms time to first audio (6th of 28) and 4.6% word error rate (7th of 28) among TTS systems. Results cover the last 30 days. Coval benchmarks hosted endpoints daily using a consistent evaluation methodology. Last measured .

Inworld TTS 2 is Inworld's full synthesis model for interactive applications.

Time to First Audio#6 / 28
181ms
TTFA Network Roundtrip#8 / 28
125ms
TTFA Leading Silence#13 / 28
57ms
Word Error Rate#7 / 28
4.6%

Overview

Inworld offers multilingual voices, cloning and emotion controls. The standard and Flash endpoints are measured separately.

TTS 2 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
Inworld AI
Hosted by
Inworld AI
Source
Official API
Licensing
Proprietary
Deployment
Cloud
Region
US
Features
Emotion control, Multilingual, Voice cloning

How TTS 2 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 2 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
Show all 28 models
  1. #13Phantom Z 3.4 conversational286 ms
  2. #14Aura 2308 ms
  3. #15Coda312 ms
  4. #16S2.1 Pro335 ms
  5. #17Eleven v3 Conversational348 ms
  6. #18Lightning v3.1 Pro362 ms
  7. #19S1379 ms
  8. #20Grok TTS397 ms
  9. #21Sonic 3.6423 ms
  10. #22Simba 3.2451 ms
  11. #23Simba 3.0472 ms
  12. #24Chirp 3 HD535 ms
  13. #25Falcon 2545 ms
  14. #26Qwen3 TTS Flash Realtime753 ms
  15. #27S2.1 Pro Free964 ms
  16. #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 ms9,480
2Qwen3 TTS FastNari71 ms2,220
3TTS Flash 2Inworld AI91 ms11,431
4Qwen3 TTS 1.7bBaseten106 ms420
5Palabra TTS v1Palabra115 ms11,415
6TTS 2Inworld AI181 ms11,431
7Flash v2.5ElevenLabs194 ms9,148
8DefaultGradium235 ms9,157
9TTS Rt v2Soniox245 ms11,232
10TTS RT v1Soniox245 ms11,234
11Mist v3Rime258 ms11,417
12Sonic 3.5Cartesia276 ms11,430
13Phantom Z 3.4 conversationalDeepdub286 ms11,426
14Aura 2Deepgram308 ms11,416
15CodaRime312 ms11,422
16S2.1 ProFish Audio335 ms11,430
17Eleven v3 ConversationalElevenLabs348 ms11,419
18Lightning v3.1 ProSmallest362 ms11,431
19S1Fish Audio379 ms11,423
20Grok TTSxAI397 ms11,416
21Sonic 3.6Cartesia423 ms8,240
22Simba 3.2Speechify451 ms11,423
23Simba 3.0Speechify472 ms11,426
24Chirp 3 HDGoogle535 ms11,430
25Falcon 2Murf545 ms11,427
26Qwen3 TTS Flash RealtimeAlibaba753 ms11,256
27S2.1 Pro FreeFish Audio964 ms11,396
28GPT-4o mini TTSOpenAI1013 ms11,400
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 2 highlighted · 30-day averagesTime to First Audio against Word Error Rate for every measured TTS model, with TTS 2 highlighted.
vui — 66 ms, 5.4%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%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%S2.1 Pro — 335 ms, 4.8%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 — 451 ms, 4.4%Simba 3.0 — 472 ms, 5.2%Chirp 3 HD — 535 ms, 5.2%Falcon 2 — 545 ms, 5.2%Qwen3 TTS Flash Realtime — 753 ms, 8.9%S2.1 Pro Free — 964 ms, 4.7%GPT-4o mini TTS — 1013 ms, 4.8%TTS 2 — 181 ms, 4.6%

Where the errors come from

WER compositionTTS 2's Word Error Rate split by error type · 30-day averageTTS 2's WER split into substitutions, deletions and insertions.
  • TTS 24.6%
SubstitutionsDeletionsInsertions

Averages and tail latency

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

TTS 2 latency distributionMilliseconds · shared axis across metrics · last 30 daysTTS 2's latency percentiles per metric: p25–p75 band, p50 tick, whisker to p99.
  • Time to First Audiop50 167 ms · p99 311 ms
  • TTFA Network Roundtripp50 108 ms · p99 243 ms
  • TTFA Leading Silencep50 55 ms · p99 116 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 Audio181 ms151 ms167 ms187 ms213 ms240 ms311 ms11,431
TTFA Network Roundtrip125 ms100 ms108 ms121 ms140 ms171 ms243 ms11,431
TTFA Leading Silence57 ms43 ms55 ms69 ms81 ms93 ms116 ms11,431
Word Error Rate4.6%0.0%0.0%9.5%18.8%20.0%28.6%11,411

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 2's daily median Time to First Audio over the last 30 days.
TTS 2 · Sep 1: 180 msTTS 2 · Sep 2: 170 msTTS 2 · Sep 3: 170 msTTS 2 · Sep 4: 172 msTTS 2 · Sep 5: 166 msTTS 2 · Sep 6: 163 msTTS 2 · Sep 7: 163 msTTS 2 · Sep 8: 170 msTTS 2 · Sep 9: 163 msTTS 2 · Sep 10: 165 msTTS 2 · Sep 11: 165 msTTS 2 · Sep 12: 166 msTTS 2 · Sep 13: 165 msTTS 2 · Sep 14: 158 msTTS 2 · Sep 15: 163 ms
Word Error Rate — daily averageDaily average · UTC daysTTS 2's daily Word Error Rate over the last 30 days.
TTS 2 · Sep 1: 3.8%TTS 2 · Sep 2: 4.4%TTS 2 · Sep 3: 4.4%TTS 2 · Sep 4: 4.5%TTS 2 · Sep 5: 4.6%TTS 2 · Sep 6: 5.8%TTS 2 · Sep 7: 4.1%TTS 2 · Sep 8: 4.8%TTS 2 · Sep 9: 4.9%TTS 2 · Sep 10: 5.1%TTS 2 · Sep 11: 5.2%TTS 2 · Sep 12: 4.5%TTS 2 · Sep 13: 4.8%TTS 2 · Sep 14: 4.3%TTS 2 · Sep 15: 4.7%

Time to First Audio by dataset

TTS 2 by test conditionMilliseconds · lower is better · best condition firstTTS 2's Time to First Audio on each benchmark dataset.
  1. Text prompts181 ms
Time to First Audio per dataset, with the number of samples behind each figure.
DatasetTTFASamples
Text prompts181 ms11,431

Strongest condition: Text prompts at 181 ms · weakest: Text prompts at 181 ms.

How fast is TTS 2?

On Inworld AI, TTS 2 measures mean 181 ms time to first audio (6th of 28). Last measured 2026-09-15.

How accurate is TTS 2?

On Inworld AI, TTS 2 measures 4.6% word error rate (7th of 28). Last measured 2026-09-15.

Who hosts TTS 2?

TTS 2 is created by Inworld AI and served by Inworld AI. Coval measures each hosted endpoint separately.

Limits of this comparison

TTS 2 is shown beside TTS 2 Flash without assuming the faster-named variant makes the same tradeoffs.

  • The fixed prompt set does not score character consistency, emotional appropriateness or clone 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