Voice AI BenchmarksBy

PROVIDERLAST 30 DAYS

official resource

Together AI voice AI models and benchmarks

Together AI hosts the measured endpoints for open-weight speech recognition models created by NVIDIA and OpenAI.

Measured models
3
STT
Best STT model#2 / 24
70ms
Parakeet TDT 0.6B v3

Overview

Model accuracy depends on the weights and inference configuration, while latency also reflects Together's serving runtime, region and capacity.

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
serves Nemotron 3.5 ASR Streaming, Parakeet TDT 0.6B v3, Whisper Large v3

Speech-to-Text

Full STT dashboard

Ranked on Time to Final Segment against 24 measured models.

Time to Final Segmentms · lower is better · Together AI models markedEvery measured STT model on Time to Final Segment, with Together AI'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. #10Whisper Large v3180 ms
leaders plus Together AI models · 16 other models in the full table
Word Error Rate% · lower is better · Together AI models markedEvery measured STT model on Word Error Rate, with Together AI'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. #24Whisper Large v38.2%
  9. #27Parakeet TDT 0.6B v311.0%
  10. #28Nemotron 3.5 ASR Streaming15.7%
leaders plus Together AI models · 18 other models in the full table
Time to First Tokenms · lower is better · Together AI models markedEvery measured STT model on Time to First Token, with Together AI'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. #13Nemotron 3.5 ASR Streaming1540 ms
leaders plus Together AI models · 16 other models in the full table
TTFS vs WER — Together AI vs every measured modelEach point is one measured STT model · Together AI models highlighted · 30-day averagesTime to Final Segment against Word Error Rate for every measured STT model, with Together AI's models highlighted.
STT RT v5 — 64 ms, 5.8%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%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%Parakeet TDT 0.6B v3 — 70 ms, 11.0%Whisper Large v3 — 180 ms, 8.2%
Benchmarked models with their Time to Final Segment over the last 30 days.
ModelHostTTFSRank
Nemotron 3.5 ASR StreamingTogether AI——
Parakeet TDT 0.6B v3Together AI70 ms2nd of 24
Whisper Large v3Together AI180 ms10th of 24

Limits of this comparison

  • The displayed latency cannot be generalized to self-hosting, NVIDIA NIM or another provider serving the same 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