Voice AI BenchmarksBy

RIMETEXT-TO-SPEECH2,408 SAMPLES / 30 DAYSLAST RUN SEP 30, 2026, 23:00 UTC

official resource

Coda text-to-speech benchmarks

Coda, hosted by Rime, measures mean 332 ms time to first audio (22nd of 32) and 9.5% word error rate (32nd of 32) among TTS systems. Results cover the last 30 days. Coval benchmarks hosted endpoints daily using a consistent evaluation methodology. Last measured .

Coda is a Rime streaming text-to-speech model.

Time to First Audio#22 / 32
332ms
TTFA Network Roundtrip#22 / 32
208ms
TTFA Leading Silence#24 / 32
125ms
Word Error Rate#32 / 32
9.5%

Overview

Rime provides Coda through its real-time synthesis API and offers multilingual and on-premises options.

Coda 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
Rime
Hosted by
Rime
Source
Official API
Licensing
Proprietary
Deployment
On-prem
Region
US
Features
Multilingual

How Coda 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 Coda 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
  13. #13Flux TTS205 ms
  14. #14TTS RT v1254 ms
  15. #15TTS Rt v2256 ms
  16. #16Mist v3287 ms
  17. #17Sonic 3.5293 ms
  18. #18Phantom Z 3.4 conversational293 ms
  19. #19Aura 2297 ms
  20. #20Sonic 3.6299 ms
  21. #21Falcon 2301 ms
  22. #22Coda332 ms
Show all 32 models
  1. #23S2.1 Pro341 ms
  2. #24Grok TTS362 ms
  3. #25S1389 ms
  4. #26Lightning v3.1 Pro393 ms
  5. #27Daytona TTS486 ms
  6. #28Aura 2 En570 ms
  7. #29Chirp 3 HD597 ms
  8. #30Qwen3 TTS Flash Realtime718 ms
  9. #31S2.1 Pro Free850 ms
  10. #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 · Coda highlighted · 30-day averagesTime to First Audio against Word Error Rate for every measured TTS model, with Coda highlighted.
vui — 60 ms, 2.1%Default — 63 ms, 1.9%Qwen3 TTS Fast — 68 ms, 1.8%TTS Flash 2 — 91 ms, 1.7%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%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%Coda — 332 ms, 9.5%

Where the errors come from

WER compositionCoda's Word Error Rate split by error type · 30-day averageCoda's WER split into substitutions, deletions and insertions.
  • Coda9.5%
SubstitutionsDeletionsInsertions

Averages and tail latency

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

Coda latency distributionMilliseconds · shared axis across metrics · last 30 daysCoda's latency percentiles per metric: p25–p75 band, p50 tick, whisker to max.
  • Time to First Audiop50 324 ms · Max 524 ms
  • TTFA Network Roundtripp50 198 ms · Max 389 ms
  • TTFA Leading Silencep50 129 ms · Max 182 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 Audio332 ms289 ms324 ms372 ms414 ms437 ms524 ms602
TTFA Network Roundtrip208 ms162 ms198 ms240 ms283 ms300 ms389 ms602
TTFA Leading Silence125 ms116 ms129 ms138 ms146 ms150 ms182 ms602
Word Error Rate9.5%0.0%0.0%5.1%17.0%27.3%45.3%602

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 daysCoda's daily median Time to First Audio over the last 30 days.
Coda · Sep 23: 360 msCoda · Sep 24: 328 msCoda · Sep 25: 336 msCoda · Sep 26: 344 msCoda · Sep 27: 324 msCoda · Sep 28: 326 msCoda · Sep 29: 317 msCoda · Sep 30: 315 ms
Word Error Rate — daily averageDaily average · UTC daysCoda's daily Word Error Rate over the last 30 days.
Coda · Sep 23: 8.4%Coda · Sep 24: 5.1%Coda · Sep 25: 4.6%Coda · Sep 26: 3.3%Coda · Sep 27: 6.2%Coda · Sep 28: 6.1%Coda · Sep 29: 6.3%Coda · Sep 30: 5.7%

How fast is Coda?

On Rime, Coda measures mean 332 ms time to first audio (22nd of 32). Last measured 2026-09-30.

How accurate is Coda?

On Rime, Coda measures 9.5% word error rate (32nd of 32). Last measured 2026-09-30.

Who hosts Coda?

Coda is created by Rime and served by Rime. Coval measures each hosted endpoint separately.

Limits of this comparison

Coda remains separate from Mist v3 so two Rime generations can be compared on identical prompts without treating the provider as one model.

  • Coval does not score subjective naturalness or every Rime voice; it focuses on audible startup and intelligibility.

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