Voice AI BenchmarksBy

MODEL DIRECTORY

Compare voice AI models

Independent benchmarks for 57 speech-to-text, text-to-speech and speech-to-speech models, re-measured every day.

Fastest final transcript (TTFS)#1 / 28
39ms
Qwen3 ASR 1.7bvia Baseten
Fastest first audio (TTFA)#1 / 28
66ms
vuivia Fluxions

57 models

Speech-to-Text: latency vs quality

Speed against accuracy for every measured STT model — the best sit toward the bottom left.

TTFS vs WEREach point is one measured STT model · 30-day averagesTime to Final Segment against Word Error Rate for every measured STT model.
Qwen3 ASR 1.7b — 39 ms, 4.1%Qwen3 ASR Fast — 46 ms, 3.2%STT RT v5 — 57 ms, 5.7%STT 1 — 65 ms, 4.4%Parakeet TDT 0.6B v3 — 81 ms, 11.2%Nova 3 — 89 ms, 6.2%Nova 2 — 92 ms, 7.9%Flux Multilingual — 98 ms, 8.8%Flux — 99 ms, 6.7%Ink 2 — 122 ms, 4.8%Whisper Large v3 via Baseten — 125 ms, 5.6%Scribe v2 Realtime — 133 ms, 5.5%Universal 3.5 Pro — 173 ms, 3.2%Grok STT — 207 ms, 4.6%Default via Speechmatics — 209 ms, 5.4%Pulse — 212 ms, 5.4%Default via Gradium — 246 ms, 10.0%resonant-1 — 264 ms, 3.4%Whisper Large v3 via Together AI — 295 ms, 8.5%Enhanced — 299 ms, 4.3%Gemini 3.5 Transcribe Live — 305 ms, 3.9%Voxtral Mini Transcribe Realtime 2602 — 401 ms, 6.2%GPT Realtime Whisper — 551 ms, 5.1%GPT-4o mini Transcribe — 690 ms, 4.9%GPT-4o Transcribe — 754 ms, 4.6%Chirp 3 — 776 ms, 4.1%Solaria 1 — 806 ms, 7.1%Chirp 2 — 873 ms, 4.9%

Text-to-Speech: latency vs quality

Speed against intelligibility for every measured TTS model — the best sit toward the bottom left.

TTFA vs WEREach point is one measured TTS model · 30-day averagesTime to First Audio against Word Error Rate for every measured TTS model.
vui — 66 ms, 5.5%Qwen3 TTS Fast — 71 ms, 4.2%TTS Flash 2 — 91 ms, 5.4%Qwen3 TTS 1.7b — 106 ms, 5.5%Palabra TTS v1 — 115 ms, 5.8%TTS 2 — 181 ms, 4.6%Flash v2.5 — 194 ms, 6.7%Default — 235 ms, 5.3%TTS Rt v2 — 245 ms, 4.2%TTS RT v1 — 245 ms, 3.9%Mist v3 — 258 ms, 5.6%Sonic 3.5 — 276 ms, 5.9%Phantom Z 3.4 conversational — 286 ms, 6.0%Aura 2 — 308 ms, 5.2%Coda — 312 ms, 5.0%S2.1 Pro — 335 ms, 4.8%Eleven v3 Conversational — 348 ms, 4.4%Lightning v3.1 Pro — 362 ms, 4.4%S1 — 379 ms, 4.9%Grok TTS — 397 ms, 4.9%Sonic 3.6 — 423 ms, 5.3%Simba 3.2 — 451 ms, 4.4%Simba 3.0 — 473 ms, 5.2%Chirp 3 HD — 535 ms, 5.2%Falcon 2 — 545 ms, 5.2%Qwen3 TTS Flash Realtime — 753 ms, 8.9%S2.1 Pro Free — 963 ms, 4.7%GPT-4o mini TTS — 1014 ms, 4.8%

About this directory

A placement always names its metric — #2 on TTFS is a different claim than #2 on WER — and is judged across every host serving the model. Models without enough qualifying samples in the last 30 days show no number at all.

Open-weight models can post different latency on different hosts because serving infrastructure and configuration differ, so each hosted endpoint is measured separately. The provider directory covers which organizations create models, host them, or do both.

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