Voice AI BenchmarksBy

PROVIDERLAST 30 DAYS

official resource

Microsoft voice AI models and benchmarks

Microsoft creates the measured speech recognition and synthesis models, and Azure serves the endpoints used for Coval's results.

Measured models
3
STTTTS
Best STT model#9 / 24
155ms
Default
Best TTS model#6 / 30
236ms
Neural

Overview

Microsoft builds the models; Azure operates the serving infrastructure behind the measured endpoints.

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

Speech-to-Text
Default
Text-to-Speech
Neural, Dragon HD Latest

Speech-to-Text

Full STT dashboard

Ranked on Time to Final Segment against 24 measured models.

Time to Final Segmentms · lower is better · Microsoft models markedEvery measured STT model on Time to Final Segment, with Microsoft's models highlighted.
  1. #1STT RT v564 ms
  2. #2Parakeet TDT 0.6B v370 ms
  3. #3STT 183 ms
  4. #4Nova 399 ms
  5. #5Nova 2101 ms
  6. #6Ink 2108 ms
  7. #7Scribe v2 Realtime120 ms
  8. #9Defaultvia Azure155 ms
leaders plus Microsoft models · 16 other models in the full table
Word Error Rate% · lower is better · Microsoft models markedEvery measured STT model on Word Error Rate, with Microsoft's models highlighted.
  1. #1Universal 3.5 Pro3.2%
  2. #2resonant-13.4%
  3. #3Chirp 34.1%
  4. #4Enhanced4.3%
  5. #5GPT-4o Transcribe4.7%
  6. #6Grok STT4.8%
  7. #7STT 14.8%
  8. #13Defaultvia Azure5.3%
leaders plus Microsoft models · 20 other models in the full table
Time to First Tokenms · lower is better · Microsoft models markedEvery measured STT model on Time to First Token, with Microsoft's models highlighted.
  1. #1Universal 3.5 Pro1030 ms
  2. #2Flux1089 ms
  3. #3Flux Multilingual1175 ms
  4. #4Parakeet TDT 0.6B v31210 ms
  5. #5Whisper Large v31241 ms
  6. #6Nova 31434 ms
  7. #7Nova 21436 ms
  8. #16Defaultvia Azure1792 ms
leaders plus Microsoft models · 16 other models in the full table
TTFS vs WER — Microsoft vs every measured modelEach point is one measured STT model · Microsoft models highlighted · 30-day averagesTime to Final Segment against Word Error Rate for every measured STT model, with Microsoft's models highlighted.
STT RT v5 — 64 ms, 5.8%Parakeet TDT 0.6B v3 — 70 ms, 11.0%STT 1 — 83 ms, 4.8%Nova 3 — 99 ms, 6.3%Nova 2 — 101 ms, 7.9%Ink 2 — 108 ms, 4.9%Scribe v2 Realtime — 120 ms, 5.5%Universal 3.5 Pro — 146 ms, 3.2%Whisper Large v3 — 180 ms, 8.2%Velma 2 STT Streaming — 191 ms, 6.4%Grok STT — 199 ms, 4.8%Pulse — 205 ms, 5.3%Default via Speechmatics — 223 ms, 5.5%Default via Gradium — 249 ms, 10.0%resonant-1 — 288 ms, 3.4%Enhanced — 341 ms, 4.3%Voxtral Mini Transcribe Realtime 2602 — 356 ms, 6.2%GPT Realtime Whisper — 559 ms, 5.2%GPT-4o mini Transcribe — 623 ms, 5.1%Solaria 1 — 680 ms, 7.1%GPT-4o Transcribe — 742 ms, 4.7%Chirp 2 — 811 ms, 5.0%Chirp 3 — 813 ms, 4.1%Default via Azure — 155 ms, 5.3%
Benchmarked models with their Time to Final Segment over the last 30 days.
ModelHostTTFSRank
DefaultAzure155 ms9th of 24

Text-to-Speech

Full TTS dashboard

Ranked on Time to First Audio against 30 measured models.

Time to First Audioms · lower is better · Microsoft models markedEvery measured TTS model on Time to First Audio, with Microsoft's models highlighted.
  1. #1Palabra TTS v1116 ms
  2. #2vui124 ms
  3. #3TTS Flash 2128 ms
  4. #4TTS 2176 ms
  5. #5Blizzard235 ms
  6. #6Neural236 ms
  7. #7Mist v3256 ms
  8. #11Dragon HD Latest310 ms
leaders plus Microsoft models · 22 other models in the full table
Word Error Rate% · lower is better · Microsoft models markedEvery measured TTS model on Word Error Rate, with Microsoft's models highlighted.
  1. #1TTS RT v13.7%
  2. #2TTS Rt v23.9%
  3. #3Neural4.3%
  4. #4Eleven v3 Conversational4.4%
  5. #5Lightning v3.1 Pro4.4%
  6. #6Default4.6%
  7. #7S2.1 Pro4.6%
  8. #17Dragon HD Latest5.1%
leaders plus Microsoft models · 22 other models in the full table
TTFA vs WER — Microsoft vs every measured modelEach point is one measured TTS model · Microsoft models highlighted · 30-day averagesTime to First Audio against Word Error Rate for every measured TTS model, with Microsoft's models highlighted.
Palabra TTS v1 — 116 ms, 5.9%vui — 124 ms, 7.9%TTS Flash 2 — 128 ms, 4.9%TTS 2 — 176 ms, 4.8%Blizzard — 235 ms, 7.4%Mist v3 — 256 ms, 6.3%TTS Rt v2 — 262 ms, 3.9%Sonic 3.5 — 274 ms, 6.1%TTS RT v1 — 275 ms, 3.7%Coda — 313 ms, 5.2%Aura 2 — 328 ms, 5.3%S2.1 Pro — 374 ms, 4.6%Default — 384 ms, 4.6%Speech 2.8 Turbo — 411 ms, 4.8%Eleven v3 Conversational — 412 ms, 4.4%Grok TTS — 420 ms, 4.7%S1 — 434 ms, 4.9%Flash v2.5 — 455 ms, 6.7%Speech 2.8 HD — 460 ms, 4.7%Sonic 3.6 — 466 ms, 5.5%Simba 3.2 — 484 ms, 4.7%Chirp 3 HD — 512 ms, 5.2%Simba 3.0 — 526 ms, 5.3%Falcon 2 — 549 ms, 5.2%Lightning v3.1 Pro — 586 ms, 4.4%Qwen3 TTS Flash Realtime — 645 ms, 8.8%S2.1 Pro Free — 806 ms, 4.7%GPT-4o mini TTS — 1075 ms, 4.8%Neural — 236 ms, 4.3%Dragon HD Latest — 310 ms, 5.1%
Benchmarked models with their Time to First Audio over the last 30 days.
ModelHostTTFARank
NeuralAzure236 ms6th of 30
Dragon HD LatestAzure310 ms11th of 30

Limits of this comparison

  • The benchmark covers the measured Microsoft speech models, not every model or service in Azure AI Speech.

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