Voice AI BenchmarksBy

MURFTEXT-TO-SPEECH7,658 SAMPLES / 30 DAYSLAST RUN OCT 14, 2026, 15:30 UTC

official resource

Falcon 2 text-to-speech benchmarks

Falcon 2, hosted by Murf, measures mean 300 ms time to first audio (21st of 32) and 1.7% word error rate (14th of 32) among TTS systems. Results cover the last 30 days. Coval benchmarks hosted endpoints daily using a consistent evaluation methodology. Last measured .

Falcon 2 is Murf AI's text-to-speech model for streaming voice applications.

Time to First Audio#21 / 32
300ms
TTFA Network Roundtrip#6 / 32
97ms
TTFA Leading Silence#31 / 32
203ms
Word Error Rate#14 / 32
1.7%

Overview

Murf exposes Falcon through its developer synthesis API with multilingual voices and streaming output.

Falcon 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
Murf
Hosted by
Murf
Source
Official API
Licensing
Proprietary
Deployment
Cloud
Region
US
Features
Multilingual

How Falcon 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 Falcon 2 highlighted.
  1. #1vui59 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 TTS120 ms
  8. #8Simba 3.2126 ms
  9. #9drama3-preview167 ms
  10. #10TTS 2191 ms
  11. #11Flash v2.5192 ms
  12. #12Eleven v4 Turbo201 ms
  13. #13Flux TTS205 ms
  14. #14TTS RT v1255 ms
  15. #15TTS Rt v2256 ms
  16. #16Mist v3287 ms
  17. #17Phantom Z 3.4 conversational291 ms
  18. #18Sonic 3.5293 ms
  19. #19Aura 2297 ms
  20. #20Sonic 3.6299 ms
  21. #21Falcon 2300 ms
Show all 32 models
  1. #22Coda332 ms
  2. #23S2.1 Pro341 ms
  3. #24Grok TTS363 ms
  4. #25S1389 ms
  5. #26Lightning v3.1 Pro392 ms
  6. #27Daytona TTS486 ms
  7. #28Aura 2 En569 ms
  8. #29Chirp 3 HD597 ms
  9. #30Qwen3 TTS Flash Realtime718 ms
  10. #31S2.1 Pro Free850 ms
  11. #32GPT-4o mini TTS2585 ms
median of all models · 289 ms
TTS models over the last 30 days, ranked on Time to First Audio.
#ModelHostTTFAWERSamples
1vuiFluxions59 ms1,744
2Gradium TTS Beta 202609Gradium63 ms1,916
3Qwen3 TTS FastNari Labs68 ms1,916
4TTS Flash 2Inworld AI91 ms1,720
5Qwen3 TTS 1.7bBaseten107 ms1,248
6Simba 3.0SpeechifyAI111 ms1,915
7Palabra TTS v1Palabra120 ms1,576
8Simba 3.2SpeechifyAI126 ms1,912
9Drama 3 Preview Us EastFish Audio167 ms162
10TTS 2Inworld AI191 ms1,720
11Flash v2.5ElevenLabs192 ms1,906
12Eleven v4 TurboElevenLabs201 ms1,226
13Flux TTSDeepgram205 ms1,779
14TTS RT v1Soniox255 ms1,618
15TTS Rt v2Soniox256 ms1,615
16Mist v3Rime287 ms602
17Phantom Z 3.4 conversationalDeepdub291 ms1,651
18Sonic 3.5Cartesia293 ms1,916
19Aura 2Deepgram297 ms1,848
20Sonic 3.6Cartesia299 ms1,916
21Falcon 2Murf300 ms1,915
22CodaRime332 ms602
23S2.1 ProFish Audio341 ms1,916
24Grok TTSSpaceXAI363 ms1,911
25S1Fish Audio389 ms1,915
26Lightning v3.1 ProSmallest392 ms1,916
27Daytona TTSGuava486 ms1,152
28Aura 2 EnCloudflare569 ms1,915
29Chirp 3 HDGoogle597 ms1,916
30Qwen3 TTS Flash RealtimeAlibaba718 ms1,915
31S2.1 Pro FreeFish Audio850 ms1,909
32GPT-4o mini TTSOpenAI2585 ms1,846
Under-sampled models are excluded; tied models share a place. Dotted WER values split into substitutions, deletions and insertions on hover or tap.

Highest relative placement: 14th of 32 on Word Error Rate.

Latency vs accuracy

TTFA vs WEREach point is one measured model · Falcon 2 highlighted · 30-day averagesTime to First Audio against Word Error Rate for every measured TTS model, with Falcon 2 highlighted.
vui — 59 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 — 120 ms, 2.6%Simba 3.2 — 126 ms, 1.9%drama3-preview — 167 ms, 2.0%TTS 2 — 191 ms, 1.6%Flash v2.5 — 192 ms, 1.8%Eleven v4 Turbo — 201 ms, 1.7%Flux TTS — 205 ms, 1.7%TTS RT v1 — 255 ms, 2.4%TTS Rt v2 — 256 ms, 2.4%Mist v3 — 287 ms, 2.1%Phantom Z 3.4 conversational — 291 ms, 1.8%Sonic 3.5 — 293 ms, 1.5%Aura 2 — 297 ms, 1.8%Sonic 3.6 — 299 ms, 1.5%Coda — 332 ms, 9.5%S2.1 Pro — 341 ms, 1.5%Grok TTS — 363 ms, 1.6%S1 — 389 ms, 1.8%Lightning v3.1 Pro — 392 ms, 1.5%Daytona TTS — 486 ms, 1.6%Aura 2 En — 569 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 — 2585 ms, 1.8%Falcon 2 — 300 ms, 1.7%

Where the errors come from

WER compositionFalcon 2's Word Error Rate split by error type · 30-day averageFalcon 2's WER split into substitutions, deletions and insertions.
  • Falcon 21.7%
SubstitutionsDeletionsInsertions

Averages and tail latency

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

Falcon 2 latency distributionMilliseconds · shared axis across metrics · last 30 daysFalcon 2's latency percentiles per metric: p25–p75 band, p50 tick, whisker to max.
  • Time to First Audiop50 310 ms · Max 2014 ms
  • TTFA Network Roundtripp50 94 ms · Max 262 ms
  • TTFA Leading Silencep50 216 ms · Max 1928 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 Audio300 ms190 ms310 ms355 ms463 ms574 ms2014 ms1,915
TTFA Network Roundtrip97 ms89 ms94 ms100 ms111 ms123 ms262 ms1,915
TTFA Leading Silence203 ms96 ms216 ms259 ms370 ms475 ms1928 ms1,915
Word Error Rate1.7%0.0%0.0%2.5%7.1%12.2%100.0%1,913

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 daysFalcon 2's daily median Time to First Audio over the last 30 days.
Falcon 2 · Sep 23: 443 msFalcon 2 · Sep 24: 502 msFalcon 2 · Sep 25: 530 msFalcon 2 · Sep 26: 448 msFalcon 2 · Sep 27: 277 msFalcon 2 · Sep 28: 233 msFalcon 2 · Sep 29: 279 msFalcon 2 · Sep 30: 260 msFalcon 2 · Oct 1: 282 msFalcon 2 · Oct 2: 258 msFalcon 2 · Oct 3: 282 msFalcon 2 · Oct 4: 279 msFalcon 2 · Oct 5: 245 msFalcon 2 · Oct 6: 260 msFalcon 2 · Oct 7: 254 msFalcon 2 · Oct 8: 278 msFalcon 2 · Oct 9: 246 msFalcon 2 · Oct 10: 283 msFalcon 2 · Oct 11: 261 msFalcon 2 · Oct 12: 269 msFalcon 2 · Oct 13: 253 msFalcon 2 · Oct 14: 121 ms
Word Error Rate — daily averageDaily average · UTC daysFalcon 2's daily Word Error Rate over the last 30 days.
Falcon 2 · Sep 23: 5.8%Falcon 2 · Sep 24: 3.8%Falcon 2 · Sep 25: 3.0%Falcon 2 · Sep 26: 3.9%Falcon 2 · Sep 27: 4.8%Falcon 2 · Sep 28: 4.0%Falcon 2 · Sep 29: 4.2%Falcon 2 · Sep 30: 1.8%Falcon 2 · Oct 1: 4.6%Falcon 2 · Oct 2: 3.9%Falcon 2 · Oct 3: 4.9%Falcon 2 · Oct 4: 7.5%Falcon 2 · Oct 5: 1.8%Falcon 2 · Oct 6: 5.1%Falcon 2 · Oct 7: 6.8%Falcon 2 · Oct 8: 5.1%Falcon 2 · Oct 9: 2.9%Falcon 2 · Oct 10: 1.9%Falcon 2 · Oct 11: 3.3%Falcon 2 · Oct 12: 9.3%Falcon 2 · Oct 13: 4.4%Falcon 2 · Oct 14: 7.4%

How fast is Falcon 2?

On Murf, Falcon 2 measures mean 300 ms time to first audio (21st of 32). Last measured 2026-10-14.

How accurate is Falcon 2?

On Murf, Falcon 2 measures 1.7% word error rate (14th of 32). Last measured 2026-10-14.

Who hosts Falcon 2?

Falcon 2 is created by Murf and served by Murf. Coval measures each hosted endpoint separately.

Limits of this comparison

Coval uses fixed text so its first-audio timing is not confounded by shorter or easier prompts.

  • The benchmark does not rate Murf's voice catalogue, style controls or editing workflow.

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