PROVIDER DIRECTORY
Compare voice AI providers
The companies behind benchmarked voice AI, measured independently — no blended vendor scores and no self-reported numbers.
30 providers
Top result: Whisper Large v3 — #10 of 24 on STT TTFS 180 ms
Top result: Chirp 3 HD — #24 of 30 on TTS TTFA 512 ms
Top result: Scribe v2 Realtime — #7 of 24 on STT TTFS 120 ms
Top result: S2.1 Pro — #14 of 30 on TTS TTFA 374 ms
Top result: TTS Flash 2 — #3 of 30 on TTS TTFA 128 ms
Top result: Neural — #6 of 30 on TTS TTFA 236 ms
Top result: Parakeet TDT 0.6B v3 — #2 of 24 on STT TTFS 70 ms
Top result: Universal 3.5 Pro — #8 of 24 on STT TTFS 146 ms
Top result: Speech 2.8 Turbo — #16 of 30 on TTS TTFA 411 ms
Top result: Parakeet TDT 0.6B v3 — #2 of 24 on STT TTFS 70 ms
Top result: Pulse — #13 of 24 on STT TTFS 205 ms
Top result: Default — #14 of 24 on STT TTFS 223 ms
Top result: Qwen3 TTS Flash Realtime — #28 of 30 on TTS TTFA 645 ms
Top result: Default — #15 of 30 on TTS TTFA 384 ms
Top result: Voxtral Mini Transcribe Realtime 2602 — #18 of 24 on STT TTFS 356 ms
Top result: Velma 2 STT Streaming — #11 of 24 on STT TTFS 191 ms
Top result: Palabra TTS v1 — #1 of 30 on TTS TTFA 116 ms
Top result: resonant-1 — #16 of 24 on STT TTFS 288 ms
No ranked results in the last 30 days
About this directory
“Top result” is the strongest placement any of a provider’s models holds on its category’s headline metric — TTFS, TTFA or V2V — over the last 30 days. Created models count across every host serving them; hosted models count only on that provider’s own endpoint — results are never combined into a company-level score. Individual models are compared in the model directory.
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.