Voice AI BenchmarksBy

INWORLD AITEXT-TO-SPEECH6,798 SAMPLES / 30 DAYSLAST RUN OCT 14, 2026, 10:30 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 (4th of 32) and 1.7% word error rate (11th of 32) 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#4 / 32
91ms
TTFA Network Roundtrip#5 / 32
87ms
TTFA Leading Silence#2 / 32
4ms
Word Error Rate#11 / 32
1.7%

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. #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 conversational293 ms
  7. #19Aura 2297 ms
  8. #20Sonic 3.6299 ms
  9. #21Falcon 2301 ms
  10. #22Coda332 ms
  11. #23S2.1 Pro341 ms
  12. #24Grok TTS362 ms
  13. #25S1389 ms
  14. #26Lightning v3.1 Pro393 ms
  15. #27Daytona TTS486 ms
  16. #28Aura 2 En570 ms
  17. #29Chirp 3 HD597 ms
  18. #30Qwen3 TTS Flash Realtime718 ms
  19. #31S2.1 Pro Free850 ms
  20. #32GPT-4o mini TTS2581 ms
median of all models · 290 ms
TTS models over the last 30 days, ranked on Time to First Audio.
#ModelHostTTFAWERSamples
1vuiFluxions60 ms1,724
2Gradium TTS Beta 202609Gradium63 ms1,896
3Qwen3 TTS FastNari Labs68 ms1,896
4TTS Flash 2Inworld AI91 ms1,700
5Qwen3 TTS 1.7bBaseten107 ms1,248
6Simba 3.0SpeechifyAI111 ms1,895
7Palabra TTS v1Palabra120 ms1,558
8Simba 3.2SpeechifyAI126 ms1,892
9Drama 3 Preview Us EastFish Audio169 ms142
10TTS 2Inworld AI191 ms1,700
11Flash v2.5ElevenLabs191 ms1,887
12Eleven v4 TurboElevenLabs201 ms1,206
13Flux TTSDeepgram205 ms1,759
14TTS RT v1Soniox254 ms1,599
15TTS Rt v2Soniox256 ms1,597
16Mist v3Rime287 ms602
17Sonic 3.5Cartesia293 ms1,896
18Phantom Z 3.4 conversationalDeepdub293 ms1,631
19Aura 2Deepgram297 ms1,828
20Sonic 3.6Cartesia299 ms1,896
21Falcon 2Murf301 ms1,895
22CodaRime332 ms602
23S2.1 ProFish Audio341 ms1,896
24Grok TTSSpaceXAI362 ms1,891
25S1Fish Audio389 ms1,895
26Lightning v3.1 ProSmallest393 ms1,896
27Daytona TTSGuava486 ms1,152
28Aura 2 EnCloudflare570 ms1,895
29Chirp 3 HDGoogle597 ms1,896
30Qwen3 TTS Flash RealtimeAlibaba718 ms1,895
31S2.1 Pro FreeFish Audio850 ms1,889
32GPT-4o mini TTSOpenAI2581 ms1,832
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 — 60 ms, 2.1%Default — 63 ms, 1.9%Qwen3 TTS Fast — 68 ms, 1.8%Qwen3 TTS 1.7b — 107 ms, 1.8%Simba 3.0 — 111 ms, 1.5%Palabra TTS v1 — 120 ms, 2.6%Simba 3.2 — 126 ms, 1.9%drama3-preview — 169 ms, 2.0%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 — 293 ms, 1.8%Aura 2 — 297 ms, 1.8%Sonic 3.6 — 299 ms, 1.5%Falcon 2 — 301 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 — 393 ms, 1.5%Daytona TTS — 486 ms, 1.6%Aura 2 En — 570 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 — 2581 ms, 1.8%TTS Flash 2 — 91 ms, 1.7%

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 21.7%
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 max.
  • Time to First Audiop50 61 ms · Max 44727 ms
  • TTFA Network Roundtripp50 57 ms · Max 44716 ms
  • TTFA Leading Silencep50 0 ms · Max 114 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 Audio91 ms54 ms61 ms68 ms81 ms94 ms44727 ms1,700
TTFA Network Roundtrip87 ms52 ms57 ms63 ms69 ms84 ms44716 ms1,700
TTFA Leading Silence4 ms0 ms0 ms6 ms16 ms18 ms114 ms1,700
Word Error Rate1.7%0.0%0.0%2.3%7.7%12.5%43.8%1,698

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 23: 62 msTTS Flash 2 · Sep 24: 67 msTTS Flash 2 · Sep 25: 65 msTTS Flash 2 · Sep 26: 65 msTTS Flash 2 · Sep 27: 57 msTTS Flash 2 · Sep 30: 89 msTTS Flash 2 · Oct 1: 60 msTTS Flash 2 · Oct 2: 67 msTTS Flash 2 · Oct 3: 64 msTTS Flash 2 · Oct 4: 59 msTTS Flash 2 · Oct 5: 64 msTTS Flash 2 · Oct 6: 62 msTTS Flash 2 · Oct 7: 62 msTTS Flash 2 · Oct 8: 68 msTTS Flash 2 · Oct 9: 59 msTTS Flash 2 · Oct 10: 61 msTTS Flash 2 · Oct 11: 64 msTTS Flash 2 · Oct 12: 56 msTTS Flash 2 · Oct 13: 63 msTTS Flash 2 · Oct 14: 59 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 23: 5.8%TTS Flash 2 · Sep 24: 3.8%TTS Flash 2 · Sep 25: 3.5%TTS Flash 2 · Sep 26: 3.0%TTS Flash 2 · Sep 27: 3.5%TTS Flash 2 · Sep 28: 1.9%TTS Flash 2 · Sep 30: 0.7%TTS Flash 2 · Oct 1: 5.9%TTS Flash 2 · Oct 2: 4.0%TTS Flash 2 · Oct 3: 4.5%TTS Flash 2 · Oct 4: 6.1%TTS Flash 2 · Oct 5: 3.0%TTS Flash 2 · Oct 6: 4.7%TTS Flash 2 · Oct 7: 5.2%TTS Flash 2 · Oct 8: 5.0%TTS Flash 2 · Oct 9: 2.9%TTS Flash 2 · Oct 10: 1.4%TTS Flash 2 · Oct 11: 3.1%TTS Flash 2 · Oct 12: 5.4%TTS Flash 2 · Oct 13: 3.6%TTS Flash 2 · Oct 14: 8.8%

How fast is TTS Flash 2?

On Inworld AI, TTS Flash 2 measures mean 91 ms time to first audio (4th of 32). Last measured 2026-10-14.

How accurate is TTS Flash 2?

On Inworld AI, TTS Flash 2 measures 1.7% word error rate (11th of 32). Last measured 2026-10-14.

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