Voice AI BenchmarksBy

DEEPDUBTEXT-TO-SPEECH7,490 SAMPLES / 30 DAYSLAST RUN OCT 16, 2026, 23:00 UTC

official resource

Phantom Z 3.4 conversational text-to-speech benchmarks

Phantom Z 3.4 conversational, hosted by Deepdub, measures mean 267 ms time to first audio (16th of 32) and 1.9% word error rate (22nd of 32) among TTS systems. Results cover the last 30 days. Coval benchmarks hosted endpoints daily using a consistent evaluation methodology. Last measured .

Phantom Z 3.4 Conversational is Deepdub's multilingual text-to-speech model for voice agents, built on its eTTS emotive synthesis technology.

Time to First Audio#16 / 32
267ms
TTFA Network Roundtrip#23 / 32
228ms
TTFA Leading Silence#11 / 32
39ms
Word Error Rate#22 / 32
1.9%

Overview

Deepdub exposes per-request delivery controls for accent, tempo, variance and seed, and positions the model on emotionally adaptive speech across 100+ languages.

Phantom Z 3.4 conversational 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
Deepdub
Hosted by
Deepdub
Source
Official API
Licensing
Proprietary
Deployment
Cloud
Region
US
Features
Emotion control, Multilingual, Voice cloning

How Phantom Z 3.4 conversational 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 Phantom Z 3.4 conversational highlighted.
  1. #1vui57 ms
  2. #2Default63 ms
  3. #3Qwen3 TTS Fast67 ms
  4. #4TTS Flash 288 ms
  5. #5Qwen3 TTS 1.7b107 ms
  6. #6Simba 3.0110 ms
  7. #7Palabra TTS121 ms
  8. #8Simba 3.2125 ms
  9. #9drama3-preview185 ms
  10. #10TTS 2186 ms
  11. #11Flash v2.5193 ms
  12. #12Eleven v4 Turbo199 ms
  13. #13Flux TTS204 ms
  14. #14TTS RT v1255 ms
  15. #15TTS Rt v2257 ms
  16. #16Phantom Z 3.4 conversational267 ms
Show all 32 models
  1. #17Falcon 2282 ms
  2. #18Mist v3287 ms
  3. #19Sonic 3.5292 ms
  4. #20Aura 2297 ms
  5. #21Sonic 3.6297 ms
  6. #22Coda332 ms
  7. #23S2.1 Pro343 ms
  8. #24Grok TTS361 ms
  9. #25S1391 ms
  10. #26Lightning v3.1 Pro392 ms
  11. #27Daytona TTS485 ms
  12. #28Aura 2 En565 ms
  13. #29Chirp 3 HD599 ms
  14. #30Qwen3 TTS Flash Realtime719 ms
  15. #31S2.1 Pro Free849 ms
  16. #32GPT-4o mini TTS2568 ms
median of all models · 274 ms
TTS models over the last 30 days, ranked on Time to First Audio.
#ModelHostTTFAWERSamples
1vuiFluxions57 ms1,966
2Gradium TTS Beta 202609Gradium63 ms2,138
3Qwen3 TTS FastNari Labs67 ms2,138
4TTS Flash 2Inworld AI88 ms1,942
5Qwen3 TTS 1.7bBaseten107 ms1,440
6Simba 3.0SpeechifyAI110 ms2,135
7Palabra TTS v1Palabra121 ms1,761
8Simba 3.2SpeechifyAI125 ms2,132
9Drama 3 Preview Us EastFish Audio185 ms384
10TTS 2Inworld AI186 ms1,942
11Flash v2.5ElevenLabs193 ms2,128
12Eleven v4 TurboElevenLabs199 ms1,448
13Flux TTSDeepgram204 ms1,993
14TTS RT v1Soniox255 ms1,806
15TTS Rt v2Soniox257 ms1,803
16Phantom Z 3.4 conversationalDeepdub267 ms1,873
17Falcon 2Murf282 ms2,137
18Mist v3Rime287 ms602
19Sonic 3.5Cartesia292 ms2,138
20Aura 2Deepgram297 ms2,070
21Sonic 3.6Cartesia297 ms2,138
22CodaRime332 ms602
23S2.1 ProFish Audio343 ms2,138
24Grok TTSSpaceXAI361 ms2,133
25S1Fish Audio391 ms2,137
26Lightning v3.1 ProSmallest392 ms2,138
27Daytona TTSGuava485 ms1,344
28Aura 2 EnCloudflare565 ms2,137
29Chirp 3 HDGoogle599 ms2,138
30Qwen3 TTS Flash RealtimeAlibaba719 ms2,137
31S2.1 Pro FreeFish Audio849 ms2,131
32GPT-4o mini TTSOpenAI2568 ms2,016
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 · Phantom Z 3.4 conversational highlighted · 30-day averagesTime to First Audio against Word Error Rate for every measured TTS model, with Phantom Z 3.4 conversational highlighted.
vui — 57 ms, 2.1%Default — 63 ms, 1.9%Qwen3 TTS Fast — 67 ms, 1.8%TTS Flash 2 — 88 ms, 1.7%Qwen3 TTS 1.7b — 107 ms, 1.8%Simba 3.0 — 110 ms, 1.6%Palabra TTS — 121 ms, 2.7%Simba 3.2 — 125 ms, 2.0%drama3-preview — 185 ms, 1.9%TTS 2 — 186 ms, 1.6%Flash v2.5 — 193 ms, 1.9%Eleven v4 Turbo — 199 ms, 1.7%Flux TTS — 204 ms, 1.7%TTS RT v1 — 255 ms, 2.5%TTS Rt v2 — 257 ms, 2.4%Falcon 2 — 282 ms, 1.7%Mist v3 — 287 ms, 2.1%Sonic 3.5 — 292 ms, 1.6%Aura 2 — 297 ms, 1.9%Sonic 3.6 — 297 ms, 1.5%Coda — 332 ms, 9.5%S2.1 Pro — 343 ms, 1.6%Grok TTS — 361 ms, 1.6%S1 — 391 ms, 1.8%Lightning v3.1 Pro — 392 ms, 1.6%Daytona TTS — 485 ms, 1.7%Aura 2 En — 565 ms, 2.1%Chirp 3 HD — 599 ms, 1.6%Qwen3 TTS Flash Realtime — 719 ms, 3.0%S2.1 Pro Free — 849 ms, 1.5%GPT-4o mini TTS — 2568 ms, 1.8%Phantom Z 3.4 conversational — 267 ms, 1.9%

Where the errors come from

WER compositionPhantom Z 3.4 conversational's Word Error Rate split by error type · 30-day averagePhantom Z 3.4 conversational's WER split into substitutions, deletions and insertions.
  • Phantom Z 3.4 conversational1.9%
SubstitutionsDeletionsInsertions

Averages and tail latency

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

Phantom Z 3.4 conversational latency distributionMilliseconds · shared axis across metrics · last 30 daysPhantom Z 3.4 conversational's latency percentiles per metric: p25–p75 band, p50 tick, whisker to max.
  • Time to First Audiop50 239 ms · Max 15164 ms
  • TTFA Network Roundtripp50 208 ms · Max 15157 ms
  • TTFA Leading Silencep50 24 ms · Max 679 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 Audio267 ms194 ms239 ms298 ms421 ms466 ms15164 ms1,873
TTFA Network Roundtrip228 ms113 ms208 ms262 ms389 ms434 ms15157 ms1,873
TTFA Leading Silence39 ms10 ms24 ms60 ms100 ms114 ms679 ms1,873
Word Error Rate1.9%0.0%0.0%2.5%7.7%12.5%132.0%1,871

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 daysPhantom Z 3.4 conversational's daily median Time to First Audio over the last 30 days.
Phantom Z 3.4 conversational · Sep 23: 250 msPhantom Z 3.4 conversational · Sep 24: 380 msPhantom Z 3.4 conversational · Sep 27: 324 msPhantom Z 3.4 conversational · Sep 28: 394 msPhantom Z 3.4 conversational · Sep 29: 330 msPhantom Z 3.4 conversational · Sep 30: 312 msPhantom Z 3.4 conversational · Oct 1: 292 msPhantom Z 3.4 conversational · Oct 2: 285 msPhantom Z 3.4 conversational · Oct 3: 300 msPhantom Z 3.4 conversational · Oct 4: 251 msPhantom Z 3.4 conversational · Oct 5: 351 msPhantom Z 3.4 conversational · Oct 6: 316 msPhantom Z 3.4 conversational · Oct 7: 345 msPhantom Z 3.4 conversational · Oct 8: 245 msPhantom Z 3.4 conversational · Oct 9: 216 msPhantom Z 3.4 conversational · Oct 10: 218 msPhantom Z 3.4 conversational · Oct 11: 229 msPhantom Z 3.4 conversational · Oct 12: 207 msPhantom Z 3.4 conversational · Oct 13: 184 msPhantom Z 3.4 conversational · Oct 14: 105 msPhantom Z 3.4 conversational · Oct 15: 120 msPhantom Z 3.4 conversational · Oct 16: 59 ms
Word Error Rate — daily averageDaily average · UTC daysPhantom Z 3.4 conversational's daily Word Error Rate over the last 30 days.
Phantom Z 3.4 conversational · Sep 23: 1.6%Phantom Z 3.4 conversational · Sep 24: 3.8%Phantom Z 3.4 conversational · Sep 27: 4.4%Phantom Z 3.4 conversational · Sep 28: 9.3%Phantom Z 3.4 conversational · Sep 29: 4.3%Phantom Z 3.4 conversational · Sep 30: 1.8%Phantom Z 3.4 conversational · Oct 1: 11.5%Phantom Z 3.4 conversational · Oct 2: 5.3%Phantom Z 3.4 conversational · Oct 3: 4.4%Phantom Z 3.4 conversational · Oct 4: 6.8%Phantom Z 3.4 conversational · Oct 5: 2.1%Phantom Z 3.4 conversational · Oct 6: 8.3%Phantom Z 3.4 conversational · Oct 7: 7.6%Phantom Z 3.4 conversational · Oct 8: 5.8%Phantom Z 3.4 conversational · Oct 9: 2.8%Phantom Z 3.4 conversational · Oct 10: 1.4%Phantom Z 3.4 conversational · Oct 11: 2.8%Phantom Z 3.4 conversational · Oct 12: 5.3%Phantom Z 3.4 conversational · Oct 13: 4.9%Phantom Z 3.4 conversational · Oct 14: 8.9%Phantom Z 3.4 conversational · Oct 15: 7.6%Phantom Z 3.4 conversational · Oct 16: 6.7%

How fast is Phantom Z 3.4 conversational?

On Deepdub, Phantom Z 3.4 conversational measures mean 267 ms time to first audio (16th of 32). Last measured 2026-10-16.

How accurate is Phantom Z 3.4 conversational?

On Deepdub, Phantom Z 3.4 conversational measures 1.9% word error rate (22nd of 32). Last measured 2026-10-16.

Who hosts Phantom Z 3.4 conversational?

Phantom Z 3.4 conversational is created by Deepdub and served by Deepdub. Coval measures each hosted endpoint separately.

Limits of this comparison

Coval measures it through Deepdub's API on fixed prompts.

  • Deepdub's published latency figure is a vendor measurement on its own infrastructure and is not comparable to Coval's perceived time to first audio, which also counts leading silence.
  • The benchmark does not score emotional expressiveness, accent blending or dubbing workflows.

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