Voice AI BenchmarksBy

PROVIDERLAST 30 DAYS

Nari voice AI models and benchmarks

Nari lists 2 STT and TTS models in Coval. Fastest dated mean latency over 30 days: STT: Qwen3 ASR Fast at 46 ms TTFS, with 3.2% WER. TTS: Qwen3 TTS Fast at 70 ms TTFA, with 4.2% WER. Last measured .

Coval measures voice models created or hosted by Nari.

Measured models
2
STTTTS
Best STT model#2 / 27
46ms
Qwen3 ASR Fast
Best TTS model#2 / 28
70ms
Qwen3 TTS Fast

Overview

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 Qwen3 ASR Fast
Text-to-Speech
serves Qwen3 TTS Fast

Speech-to-Text

Full STT dashboard

Ranked on Time to Final Segment against 27 measured models.

Time to Final Segmentms · lower is better · Nari models markedEvery measured STT model on Time to Final Segment, with Nari's models highlighted.
  1. #1Qwen3 ASR 1.7b39 ms
  2. #2Qwen3 ASR Fast46 ms
  3. #3STT RT v557 ms
  4. #4STT 165 ms
  5. #5Parakeet TDT 0.6B v382 ms
  6. #6Nova 388 ms
  7. #7Nova 292 ms
leaders plus Nari models · 20 other models in the full table
Word Error Rate% · lower is better · Nari models markedEvery measured STT model on Word Error Rate, with Nari's models highlighted.
  1. #1Universal 3.5 Pro3.2%
  2. #2Qwen3 ASR Fast3.2%
  3. #3resonant-13.4%
  4. #4Gemini 3.5 Transcribe Live3.9%
  5. #5Qwen3 ASR 1.7b3.9%
  6. #6Chirp 34.1%
  7. #7GPT-4o Transcribe4.6%
leaders plus Nari models · 22 other models in the full table
Time to First Tokenms · lower is better · Nari models markedEvery measured STT model on Time to First Token, with Nari's models highlighted.
  1. #1Whisper Large v3via Baseten915 ms
  2. #2Qwen3 ASR 1.7b935 ms
  3. #3Universal 3.5 Pro1038 ms
  4. #4Flux1076 ms
  5. #5Flux Multilingual1162 ms
  6. #6Parakeet TDT 0.6B v31215 ms
  7. #7Whisper Large v3via Together AI1337 ms
  8. #16Qwen3 ASR Fast1748 ms
leaders plus Nari models · 17 other models in the full table
TTFS vs WER — Nari vs every measured modelEach point is one measured STT model · Nari models highlighted · 30-day averagesTime to Final Segment against Word Error Rate for every measured STT model, with Nari's models highlighted.
Qwen3 ASR 1.7b — 39 ms, 3.9%STT RT v5 — 57 ms, 5.7%STT 1 — 65 ms, 7.5%Parakeet TDT 0.6B v3 — 82 ms, 11.2%Nova 3 — 88 ms, 6.2%Nova 2 — 92 ms, 7.9%Flux Multilingual — 97 ms, 8.9%Flux — 99 ms, 6.7%Ink 2 — 124 ms, 4.8%Whisper Large v3 via Baseten — 127 ms, 5.5%Scribe v2 Realtime — 134 ms, 5.5%Universal 3.5 Pro — 176 ms, 3.2%Grok STT — 208 ms, 4.6%Pulse — 211 ms, 5.4%Linden 1 — 232 ms, 5.0%Default — 246 ms, 10.1%resonant-1 — 264 ms, 3.4%Whisper Large v3 via Together AI — 291 ms, 8.5%Gemini 3.5 Transcribe Live — 302 ms, 3.9%Voxtral Mini Transcribe Realtime 2602 — 404 ms, 6.2%GPT Realtime Whisper — 553 ms, 5.1%GPT-4o mini Transcribe — 694 ms, 5.0%GPT-4o Transcribe — 760 ms, 4.6%Chirp 3 — 777 ms, 4.1%Solaria 1 — 874 ms, 7.1%Chirp 2 — 880 ms, 5.0%Qwen3 ASR Fast — 46 ms, 3.2%
Benchmarked models with their Time to Final Segment over the last 30 days.
ModelHostTTFSRank
Qwen3 ASR FastNari46 ms2nd of 27

Text-to-Speech

Full TTS dashboard

Ranked on Time to First Audio against 28 measured models.

Time to First Audioms · lower is better · Nari models markedEvery measured TTS model on Time to First Audio, with Nari's models highlighted.
  1. #1vui64 ms
  2. #2Qwen3 TTS Fast70 ms
  3. #3TTS Flash 291 ms
  4. #4Qwen3 TTS 1.7b105 ms
  5. #5Palabra TTS v1115 ms
  6. #6TTS 2181 ms
  7. #7Flash v2.5193 ms
leaders plus Nari models · 21 other models in the full table
Word Error Rate% · lower is better · Nari models markedEvery measured TTS model on Word Error Rate, with Nari's models highlighted.
  1. #1TTS RT v13.9%
  2. #2TTS Rt v24.2%
  3. #3Qwen3 TTS Fast4.2%
  4. #4Simba 3.24.4%
  5. #5Eleven v3 Conversational4.4%
  6. #6Lightning v3.1 Pro4.4%
  7. #7TTS 24.7%
leaders plus Nari models · 21 other models in the full table
TTFA vs WER — Nari vs every measured modelEach point is one measured TTS model · Nari models highlighted · 30-day averagesTime to First Audio against Word Error Rate for every measured TTS model, with Nari's models highlighted.
vui — 64 ms, 5.4%TTS Flash 2 — 91 ms, 5.4%Qwen3 TTS 1.7b — 105 ms, 5.5%Palabra TTS v1 — 115 ms, 5.8%TTS 2 — 181 ms, 4.7%Flash v2.5 — 193 ms, 6.7%Default — 236 ms, 5.3%TTS Rt v2 — 245 ms, 4.2%TTS RT v1 — 245 ms, 3.9%Mist v3 — 258 ms, 5.5%Sonic 3.5 — 278 ms, 5.9%Phantom Z 3.4 conversational — 284 ms, 6.0%Aura 2 — 307 ms, 5.3%Coda — 311 ms, 5.0%S2.1 Pro — 336 ms, 4.8%Eleven v3 Conversational — 346 ms, 4.4%Lightning v3.1 Pro — 363 ms, 4.4%S1 — 380 ms, 4.9%Grok TTS — 399 ms, 4.9%Sonic 3.6 — 412 ms, 5.3%Simba 3.2 — 423 ms, 4.4%Simba 3.0 — 447 ms, 5.3%Chirp 3 HD — 536 ms, 5.2%Falcon 2 — 544 ms, 5.2%Qwen3 TTS Flash Realtime — 740 ms, 8.9%GPT-4o mini TTS — 1013 ms, 4.8%S2.1 Pro Free — 1100 ms, 4.7%Qwen3 TTS Fast — 70 ms, 4.2%
Benchmarked models with their Time to First Audio over the last 30 days.
ModelHostTTFARank
Qwen3 TTS FastNari70 ms2nd of 28

How fast are Nari's STT and TTS models?

Qwen3 ASR Fast measures mean 46 ms time to final segment (2nd of 27) among STT systems. Last measured 2026-09-18. Qwen3 TTS Fast measures mean 70 ms time to first audio (2nd of 28) among TTS systems. Last measured 2026-09-18.

How accurate are Nari's STT and TTS models?

Qwen3 ASR Fast measures 3.2% word error rate (2nd of 29) among STT systems. Last measured 2026-09-18. Qwen3 TTS Fast measures 4.2% word error rate (3rd of 28) among TTS systems. Last measured 2026-09-18.

Which Nari model is fastest?

Its fastest dated STT result is Qwen3 ASR Fast at mean 46 ms time to final segment (2nd of 27) among STT systems, with 3.2% WER. Last measured 2026-09-18. Its fastest dated TTS result is Qwen3 TTS Fast at mean 70 ms time to first audio (2nd of 28) among TTS systems, with 4.2% WER. Last measured 2026-09-18.

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