Voice AI BenchmarksBy

PROVIDERLAST 30 DAYS

official resource

Mistral voice AI models and benchmarks

Mistral lists 1 STT model in Coval. Its fastest dated STT result is Voxtral Mini Transcribe Realtime 2602 at mean 416 ms time to final segment (23rd of 29) among STT systems, with 5.3% WER. Results cover the last 30 days. Last measured .

Mistral AI develops the Voxtral audio model family and hosts the measured real-time transcription endpoint in Europe.

Measured models
1
STT
Best STT model#23 / 29
416ms
Voxtral Mini Transcribe Realtime 2602

Overview

The full dated Voxtral model identifier remains visible, allowing later releases to coexist instead of silently replacing earlier measurements.

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
Voxtral Mini Transcribe Realtime 2602

Speech-to-Text

Full STT dashboard

Ranked on Time to Final Segment against 29 measured models.

Time to Final Segmentms · lower is better · Mistral models markedEvery measured STT model on Time to Final Segment, with Mistral's models highlighted.
  1. #1Qwen3 ASR 1.7b39 ms
  2. #2STT RT v544 ms
  3. #3Qwen3 ASR Fast47 ms
  4. #4STT 167 ms
  5. #5Nova 385 ms
  6. #6Nova 287 ms
  7. #7Parakeet TDT 0.6B v397 ms
  8. #23Voxtral Mini Transcribe Realtime 2602416 ms
leaders plus Mistral models · 21 other models in the full table
Word Error Rate% · lower is better · Mistral models markedEvery measured STT model on Word Error Rate, with Mistral's models highlighted.
  1. #1Universal 3.6 Pro2.1%
  2. #2Universal 3.5 Pro2.4%
  3. #3Qwen3 ASR Fast2.6%
  4. #4resonant-12.6%
  5. #5Qwen3 ASR 1.7b2.9%
  6. #6Gemini 3.5 Transcribe Live3.0%
  7. #7Chirp 33.2%
  8. #21Voxtral Mini Transcribe Realtime 26025.3%
leaders plus Mistral models · 23 other models in the full table
Time to First Tokenms · lower is better · Mistral models markedEvery measured STT model on Time to First Token, with Mistral's models highlighted.
  1. #1Whisper Large v3via Baseten924 ms
  2. #2Qwen3 ASR 1.7b946 ms
  3. #3Universal 3.5 Pro1025 ms
  4. #4Universal 3.6 Pro1071 ms
  5. #5Flux1091 ms
  6. #6Flux Multilingual1165 ms
  7. #7STT 11200 ms
  8. #20Voxtral Mini Transcribe Realtime 26021853 ms
leaders plus Mistral models · 19 other models in the full table
TTFS vs WER — Mistral vs every measured modelEach point is one measured STT model · Mistral models highlighted · 30-day averagesTime to Final Segment against Word Error Rate for every measured STT model, with Mistral's models highlighted.
Qwen3 ASR 1.7b — 39 ms, 2.9%STT RT v5 — 44 ms, 4.8%Qwen3 ASR Fast — 47 ms, 2.6%STT 1 — 67 ms, 7.1%Nova 3 — 85 ms, 5.3%Nova 2 — 87 ms, 6.7%Parakeet TDT 0.6B v3 — 97 ms, 11.1%Flux Multilingual — 98 ms, 7.5%Flux — 98 ms, 5.8%Scribe v2 Realtime — 121 ms, 4.4%Whisper Large v3 via Baseten — 131 ms, 4.5%Universal 3.6 Pro — 135 ms, 2.1%Ink 2 — 149 ms, 3.6%Universal 3.5 Pro — 170 ms, 2.4%Whisper Large v3 via Together AI — 197 ms, 7.4%Pulse — 205 ms, 4.6%Grok STT — 222 ms, 4.1%resonant-1 — 252 ms, 2.6%Default — 262 ms, 8.8%Linden 1 — 275 ms, 3.9%Gemini 3.5 Transcribe Live — 318 ms, 3.0%Daytona STT — 399 ms, 4.9%GPT Realtime Whisper — 599 ms, 4.0%Solaria 1 — 614 ms, 6.1%GPT-4o mini Transcribe — 710 ms, 3.9%Chirp 3 — 768 ms, 3.2%GPT-4o Transcribe — 784 ms, 3.7%Chirp 2 — 910 ms, 3.9%Voxtral Mini Transcribe Realtime 2602 — 416 ms, 5.3%
Benchmarked models with their Time to Final Segment over the last 30 days.
ModelHostTTFSRank
Voxtral Mini Transcribe Realtime 2602Mistral416 ms23rd of 29

How fast are Mistral's STT models?

Voxtral Mini Transcribe Realtime 2602 measures mean 416 ms time to final segment (23rd of 29) among STT systems. Last measured 2026-10-14.

How accurate are Mistral's STT models?

Voxtral Mini Transcribe Realtime 2602 measures 5.3% word error rate (21st of 31) among STT systems. Last measured 2026-10-14.

Which Mistral model is fastest?

Its fastest dated STT result is Voxtral Mini Transcribe Realtime 2602 at mean 416 ms time to final segment (23rd of 29) among STT systems, with 5.3% WER. Last measured 2026-10-14.

Limits of this comparison

  • The benchmark covers one Voxtral STT release, not every Voxtral or Mistral model.

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