Voice AI BenchmarksBy

PROVIDERLAST 30 DAYS

official resource

Deepdub voice AI models and benchmarks

Deepdub lists 1 TTS model in Coval. Its fastest dated TTS result is Phantom Z 3.4 conversational at mean 241 ms time to first audio (14th of 32) among TTS systems, with 2.2% WER. Results cover the last 30 days. Last measured .

Deepdub builds emotive text-to-speech and voice technology, originally for localization and dubbing and now offered as a real-time voice API for agents.

Measured models
1
TTS
Best TTS model#14 / 32
241ms
Phantom Z 3.4 conversational

Overview

Deepdub creates and hosts the measured eTTS endpoint and exposes accent, tempo, variance and seed controls per request.

Every model below is measured daily on the same fixed inputs and ranked against the full field, never blended into a company score.

Model lineup

Text-to-Speech
Phantom Z 3.4 conversational

Text-to-Speech

Full TTS dashboard

Ranked on Time to First Audio against 32 measured models.

Time to First Audioms · lower is better · Deepdub models markedEvery measured TTS model on Time to First Audio, with Deepdub's models highlighted.
  1. #1vui56 ms
  2. #2Default63 ms
  3. #3Qwen3 TTS Fast68 ms
  4. #4TTS Flash 285 ms
  5. #5Qwen3 TTS 1.7b106 ms
  6. #6Simba 3.0110 ms
  7. #7Palabra TTS120 ms
  8. #14Phantom Z 3.4 conversational241 ms
leaders plus Deepdub models · 24 other models in the full table
Word Error Rate% · lower is better · Deepdub models markedEvery measured TTS model on Word Error Rate, with Deepdub's models highlighted.
  1. #1Sonic 3.61.5%
  2. #2Sonic 3.51.6%
  3. #3S2.1 Pro Free1.6%
  4. #4Lightning v3.1 Pro1.6%
  5. #5S2.1 Pro1.6%
  6. #6Simba 3.01.6%
  7. #7Chirp 3 HD1.6%
  8. #27Phantom Z 3.4 conversational2.2%
leaders plus Deepdub models · 24 other models in the full table
TTFA vs WER — Deepdub vs every measured modelEach point is one measured TTS model · Deepdub models highlighted · 30-day averagesTime to First Audio against Word Error Rate for every measured TTS model, with Deepdub's models highlighted.
vui — 56 ms, 2.1%Default — 63 ms, 1.9%Qwen3 TTS Fast — 68 ms, 1.9%TTS Flash 2 — 85 ms, 1.7%Qwen3 TTS 1.7b — 106 ms, 1.9%Simba 3.0 — 110 ms, 1.6%Palabra TTS — 120 ms, 2.7%Simba 3.2 — 129 ms, 2.0%drama3-preview — 175 ms, 1.8%TTS 2 — 181 ms, 1.7%Flash v2.5 — 194 ms, 1.9%Eleven v4 Turbo — 197 ms, 1.7%Flux TTS — 204 ms, 1.7%TTS RT v1 — 256 ms, 2.5%TTS Rt v2 — 257 ms, 2.4%Falcon 2 — 264 ms, 1.7%Airy TTS — 270 ms, 1.6%Mist v3 — 287 ms, 2.1%Sonic 3.5 — 290 ms, 1.6%Sonic 3.6 — 295 ms, 1.5%Aura 2 — 298 ms, 1.9%Coda — 332 ms, 9.5%S2.1 Pro — 347 ms, 1.6%Grok TTS — 356 ms, 1.7%Lightning v3.1 Pro — 394 ms, 1.6%Daytona TTS — 485 ms, 1.7%Aura 2 En — 559 ms, 2.1%Chirp 3 HD — 596 ms, 1.6%Qwen3 TTS Flash Realtime — 720 ms, 3.1%S2.1 Pro Free — 844 ms, 1.6%GPT-4o mini TTS — 2549 ms, 1.8%Phantom Z 3.4 conversational — 241 ms, 2.2%
Benchmarked models with their Time to First Audio over the last 30 days.
ModelHostTTFARank
Phantom Z 3.4 conversationalDeepdub241 ms14th of 32

How fast are Deepdub's TTS models?

Phantom Z 3.4 conversational measures mean 241 ms time to first audio (14th of 32) among TTS systems. Last measured 2026-10-19.

How accurate are Deepdub's TTS models?

Phantom Z 3.4 conversational measures 2.2% word error rate (27th of 32) among TTS systems. Last measured 2026-10-19.

Which Deepdub model is fastest?

Its fastest dated TTS result is Phantom Z 3.4 conversational at mean 241 ms time to first audio (14th of 32) among TTS systems, with 2.2% WER. Last measured 2026-10-19.

Limits of this comparison

Coval measures its TTS API within the TTS category only.

  • The results describe the measured TTS model only, not Deepdub's dubbing, voice conversion or localization products.

Official resources

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