Voice AI BenchmarksBy

CARTESIATEXT-TO-SPEECH45,660 SAMPLES / 30 DAYSLAST RUN SEP 15, 2026, 08:00 UTC

official resource

Sonic 3.5 text-to-speech benchmarks

Sonic 3.5, hosted by Cartesia, measures mean 277 ms time to first audio (12th of 28) and 5.9% word error rate (25th of 28) among TTS systems. Results cover the last 30 days. Coval benchmarks hosted endpoints daily using a consistent evaluation methodology. Last measured .

Sonic 3.5 is Cartesia's streaming text-to-speech model.

Time to First Audio#12 / 28
277ms
TTFA Network Roundtrip#10 / 28
146ms
TTFA Leading Silence#23 / 28
131ms
Word Error Rate#25 / 28
5.9%

Overview

Sonic 3.5 offers multilingual synthesis with cloning, emotion controls and an on-premises deployment option.

Sonic 3.5 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
Cartesia
Hosted by
Cartesia
Source
Official API
Licensing
Proprietary
Deployment
On-prem
Region
US
Features
Emotion control, Multilingual, Voice cloning

How Sonic 3.5 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 Sonic 3.5 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 3.0472 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 ms9,470
2Qwen3 TTS FastNari71 ms2,210
3TTS Flash 2Inworld AI91 ms11,421
4Qwen3 TTS 1.7bBaseten106 ms420
5Palabra TTS v1Palabra115 ms11,405
6TTS 2Inworld AI181 ms11,421
7Flash v2.5ElevenLabs194 ms9,138
8DefaultGradium235 ms9,147
9TTS Rt v2Soniox245 ms11,232
10TTS RT v1Soniox245 ms11,234
11Mist v3Rime258 ms11,407
12Sonic 3.5Cartesia277 ms11,420
13Phantom Z 3.4 conversationalDeepdub286 ms11,416
14Aura 2Deepgram308 ms11,406
15CodaRime312 ms11,412
16S2.1 ProFish Audio335 ms11,420
17Eleven v3 ConversationalElevenLabs348 ms11,409
18Lightning v3.1 ProSmallest362 ms11,421
19S1Fish Audio379 ms11,413
20Grok TTSxAI397 ms11,406
21Sonic 3.6Cartesia423 ms8,230
22Simba 3.2Speechify451 ms11,413
23Simba 3.0Speechify472 ms11,416
24Chirp 3 HDGoogle535 ms11,420
25Falcon 2Murf545 ms11,417
26Qwen3 TTS Flash RealtimeAlibaba753 ms11,246
27S2.1 Pro FreeFish Audio964 ms11,386
28GPT-4o mini TTSOpenAI1013 ms11,390
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 · Sonic 3.5 highlighted · 30-day averagesTime to First Audio against Word Error Rate for every measured TTS model, with Sonic 3.5 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%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%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%Sonic 3.5 — 277 ms, 5.9%

Where the errors come from

WER compositionSonic 3.5's Word Error Rate split by error type · 30-day averageSonic 3.5's WER split into substitutions, deletions and insertions.
  • Sonic 3.55.9%
SubstitutionsDeletionsInsertions

Averages and tail latency

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

Sonic 3.5 latency distributionMilliseconds · shared axis across metrics · last 30 daysSonic 3.5's latency percentiles per metric: p25–p75 band, p50 tick, whisker to p99.
  • Time to First Audiop50 275 ms · p99 418 ms
  • TTFA Network Roundtripp50 143 ms · p99 218 ms
  • TTFA Leading Silencep50 132 ms · p99 255 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 Audio277 ms249 ms275 ms299 ms330 ms353 ms418 ms11,420
TTFA Network Roundtrip146 ms130 ms143 ms159 ms180 ms192 ms218 ms11,420
TTFA Leading Silence131 ms112 ms132 ms145 ms166 ms195 ms255 ms11,420
Word Error Rate5.9%0.0%0.0%10.5%20.0%25.0%35.7%11,400

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 daysSonic 3.5's daily median Time to First Audio over the last 30 days.
Sonic 3.5 · Sep 1: 293 msSonic 3.5 · Sep 2: 280 msSonic 3.5 · Sep 3: 271 msSonic 3.5 · Sep 4: 271 msSonic 3.5 · Sep 5: 264 msSonic 3.5 · Sep 6: 266 msSonic 3.5 · Sep 7: 274 msSonic 3.5 · Sep 8: 274 msSonic 3.5 · Sep 9: 287 msSonic 3.5 · Sep 10: 284 msSonic 3.5 · Sep 11: 277 msSonic 3.5 · Sep 12: 285 msSonic 3.5 · Sep 13: 278 msSonic 3.5 · Sep 14: 286 msSonic 3.5 · Sep 15: 267 ms
Word Error Rate — daily averageDaily average · UTC daysSonic 3.5's daily Word Error Rate over the last 30 days.
Sonic 3.5 · Sep 1: 8.0%Sonic 3.5 · Sep 2: 5.8%Sonic 3.5 · Sep 3: 5.2%Sonic 3.5 · Sep 4: 6.0%Sonic 3.5 · Sep 5: 6.4%Sonic 3.5 · Sep 6: 7.5%Sonic 3.5 · Sep 7: 5.6%Sonic 3.5 · Sep 8: 5.9%Sonic 3.5 · Sep 9: 6.5%Sonic 3.5 · Sep 10: 6.2%Sonic 3.5 · Sep 11: 6.6%Sonic 3.5 · Sep 12: 6.0%Sonic 3.5 · Sep 13: 5.9%Sonic 3.5 · Sep 14: 6.1%Sonic 3.5 · Sep 15: 5.8%

Time to First Audio by dataset

Sonic 3.5 by test conditionMilliseconds · lower is better · best condition firstSonic 3.5's Time to First Audio on each benchmark dataset.
  1. Text prompts277 ms
Time to First Audio per dataset, with the number of samples behind each figure.
DatasetTTFASamples
Text prompts277 ms11,420

Strongest condition: Text prompts at 277 ms · weakest: Text prompts at 277 ms.

How fast is Sonic 3.5?

On Cartesia, Sonic 3.5 measures mean 277 ms time to first audio (12th of 28). Last measured 2026-09-15.

How accurate is Sonic 3.5?

On Cartesia, Sonic 3.5 measures 5.9% word error rate (25th of 28). Last measured 2026-09-15.

Who hosts Sonic 3.5?

Sonic 3.5 is created by Cartesia and served by Cartesia. Coval measures each hosted endpoint separately.

Limits of this comparison

Coval measures the official endpoint on fixed prompts and separates it from Ink 2 recognition.

  • The benchmark does not score expressive quality, clone similarity or a combined Ink-and-Sonic agent.

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