Voice AI BenchmarksBy

PROVIDERLAST 30 DAYS

official resource

Modulate voice AI models and benchmarks

Modulate develops voice-safety technology and the Velma streaming speech recognition API.

Measured models
1
STT
Best STT model#11 / 24
191ms
Velma 2 STT Streaming

Overview

The measured endpoint is a first-party multilingual STT service with speaker diarization.

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
Velma 2 STT Streaming

Speech-to-Text

Full STT dashboard

Ranked on Time to Final Segment against 24 measured models.

Time to Final Segmentms · lower is better · Modulate models markedEvery measured STT model on Time to Final Segment, with Modulate'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. #11Velma 2 STT Streaming191 ms
leaders plus Modulate models · 16 other models in the full table
Word Error Rate% · lower is better · Modulate models markedEvery measured STT model on Word Error Rate, with Modulate'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. #19Velma 2 STT Streaming6.4%
leaders plus Modulate models · 20 other models in the full table
Time to First Tokenms · lower is better · Modulate models markedEvery measured STT model on Time to First Token, with Modulate'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. #14Velma 2 STT Streaming1576 ms
leaders plus Modulate models · 16 other models in the full table
TTFS vs WER — Modulate vs every measured modelEach point is one measured STT model · Modulate models highlighted · 30-day averagesTime to Final Segment against Word Error Rate for every measured STT model, with Modulate'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%Default via Azure — 155 ms, 5.3%Whisper Large v3 — 180 ms, 8.2%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%Velma 2 STT Streaming — 191 ms, 6.4%
Benchmarked models with their Time to Final Segment over the last 30 days.
ModelHostTTFSRank
Velma 2 STT StreamingModulate191 ms11th of 24

Limits of this comparison

Coval limits its provider comparison to Velma's transcription path.

  • Moderation, toxicity detection and other Modulate analysis products are outside Coval's current benchmark metrics.

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