Voice AI BenchmarksBy

INWORLD AITEXT-TO-SPEECH45,824 SAMPLES / 30 DAYSLAST RUN SEP 15, 2026, 09:30 UTC

official resource

TTS Flash 2 text-to-speech benchmarks

TTS Flash 2, hosted by Inworld AI, measures mean 91 ms time to first audio (3rd of 28) and 5.4% word error rate (20th 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 Flash is the latency-oriented member of Inworld's second-generation synthesis family.

Time to First Audio#3 / 28
91ms
TTFA Network Roundtrip#4 / 28
78ms
TTFA Leading Silence#4 / 28
12ms
Word Error Rate#20 / 28
5.4%

Overview

The endpoint retains multilingual, cloning and emotion-control capabilities while using its own API model name.

TTS Flash 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 Flash 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 Flash 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 3.5277 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 3.0473 ms
  12. #24Chirp 3 HD535 ms
  13. #25Falcon 2545 ms
  14. #26Qwen3 TTS Flash Realtime753 ms
  15. #27S2.1 Pro Free963 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 ms9,510
2Qwen3 TTS FastNari71 ms2,250
3TTS Flash 2Inworld AI91 ms11,461
4Qwen3 TTS 1.7bBaseten106 ms420
5Palabra TTS v1Palabra115 ms11,445
6TTS 2Inworld AI181 ms11,461
7Flash v2.5ElevenLabs194 ms9,178
8DefaultGradium235 ms9,187
9TTS Rt v2Soniox245 ms11,232
10TTS RT v1Soniox245 ms11,234
11Mist v3Rime258 ms11,447
12Sonic 3.5Cartesia277 ms11,460
13Phantom Z 3.4 conversationalDeepdub286 ms11,456
14Aura 2Deepgram308 ms11,446
15CodaRime312 ms11,452
16S2.1 ProFish Audio335 ms11,460
17Eleven v3 ConversationalElevenLabs348 ms11,449
18Lightning v3.1 ProSmallest362 ms11,461
19S1Fish Audio379 ms11,453
20Grok TTSxAI397 ms11,446
21Sonic 3.6Cartesia423 ms8,270
22Simba 3.2Speechify451 ms11,453
23Simba 3.0Speechify473 ms11,456
24Chirp 3 HDGoogle535 ms11,460
25Falcon 2Murf545 ms11,457
26Qwen3 TTS Flash RealtimeAlibaba753 ms11,286
27S2.1 Pro FreeFish Audio963 ms11,426
28GPT-4o mini TTSOpenAI1013 ms11,430
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 Flash 2 highlighted · 30-day averagesTime to First Audio against Word Error Rate for every measured TTS model, with TTS Flash 2 highlighted.
vui — 66 ms, 5.5%Qwen3 TTS Fast — 71 ms, 4.2%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 — 277 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 — 473 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 — 963 ms, 4.7%GPT-4o mini TTS — 1013 ms, 4.8%TTS Flash 2 — 91 ms, 5.4%

Where the errors come from

WER compositionTTS Flash 2's Word Error Rate split by error type · 30-day averageTTS Flash 2's WER split into substitutions, deletions and insertions.
  • TTS Flash 25.4%
SubstitutionsDeletionsInsertions

Averages and tail latency

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

TTS Flash 2 latency distributionMilliseconds · shared axis across metrics · last 30 daysTTS Flash 2's latency percentiles per metric: p25–p75 band, p50 tick, whisker to p99.
  • Time to First Audiop50 75 ms · p99 196 ms
  • TTFA Network Roundtripp50 68 ms · p99 177 ms
  • TTFA Leading Silencep50 3 ms · p99 96 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 Audio91 ms68 ms75 ms94 ms121 ms144 ms196 ms11,461
TTFA Network Roundtrip78 ms62 ms68 ms75 ms94 ms107 ms177 ms11,461
TTFA Leading Silence12 ms0 ms3 ms10 ms45 ms68 ms96 ms11,461
Word Error Rate5.4%0.0%0.0%9.5%19.0%22.2%35.7%11,441

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 Flash 2's daily median Time to First Audio over the last 30 days.
TTS Flash 2 · Sep 1: 82 msTTS Flash 2 · Sep 2: 77 msTTS Flash 2 · Sep 3: 80 msTTS Flash 2 · Sep 4: 77 msTTS Flash 2 · Sep 5: 74 msTTS Flash 2 · Sep 6: 72 msTTS Flash 2 · Sep 7: 75 msTTS Flash 2 · Sep 8: 72 msTTS Flash 2 · Sep 9: 72 msTTS Flash 2 · Sep 10: 69 msTTS Flash 2 · Sep 11: 70 msTTS Flash 2 · Sep 12: 70 msTTS Flash 2 · Sep 13: 71 msTTS Flash 2 · Sep 14: 70 msTTS Flash 2 · Sep 15: 64 ms
Word Error Rate — daily averageDaily average · UTC daysTTS Flash 2's daily Word Error Rate over the last 30 days.
TTS Flash 2 · Sep 1: 5.5%TTS Flash 2 · Sep 2: 5.3%TTS Flash 2 · Sep 3: 5.2%TTS Flash 2 · Sep 4: 5.6%TTS Flash 2 · Sep 5: 5.9%TTS Flash 2 · Sep 6: 6.3%TTS Flash 2 · Sep 7: 5.4%TTS Flash 2 · Sep 8: 5.7%TTS Flash 2 · Sep 9: 6.2%TTS Flash 2 · Sep 10: 5.4%TTS Flash 2 · Sep 11: 6.0%TTS Flash 2 · Sep 12: 5.4%TTS Flash 2 · Sep 13: 5.6%TTS Flash 2 · Sep 14: 5.0%TTS Flash 2 · Sep 15: 6.0%

Time to First Audio by dataset

TTS Flash 2 by test conditionMilliseconds · lower is better · best condition firstTTS Flash 2's Time to First Audio on each benchmark dataset.
  1. Text prompts91 ms
Time to First Audio per dataset, with the number of samples behind each figure.
DatasetTTFASamples
Text prompts91 ms11,461

Strongest condition: Text prompts at 91 ms · weakest: Text prompts at 91 ms.

How fast is TTS Flash 2?

On Inworld AI, TTS Flash 2 measures mean 91 ms time to first audio (3rd of 28). Last measured 2026-09-15.

How accurate is TTS Flash 2?

On Inworld AI, TTS Flash 2 measures 5.4% word error rate (20th of 28). Last measured 2026-09-15.

Who hosts TTS Flash 2?

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

Limits of this comparison

The Flash variant receives the same prompts as standard TTS 2 for a direct latency and intelligibility comparison.

  • A speed-oriented label is not treated as a result; only Coval's current measurements determine relative latency.

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