520 ms median and 1,027 ms P95 time to first audio on Coval (30 days to October 22, 2026): Visible delay speed tier.
Benchmark summary: Visible delay speed tier on Coval's P95 (the voice becomes a visible part of the delay).
Deepgram Aura 2 En is a proprietary text-to-speech (TTS) API from Deepgram, served by Cloudflare, measured by one independent benchmark, Coval.
Speed tier
Visible delayP95 of 320 ms or more. The voice becomes a visible part of the delay.
Data read October 22, 2026. No combined score: methodology
Gradium TTS vs Deepgram Aura 2 En Fastest TTS APIs, by speed tierOn Coval's 30-day window ending October 22, 2026 (3,144 runs from US East), Deepgram Aura 2 En starts speaking after 519.8 ms on a typical turn (median) and 1,027.1 ms on a slow turn (P95, the slowest one in twenty). That P95 is 30th lowest of the 32 models Coval measures, which puts it in the Visible delay tier: the voice becomes a visible part of the delay.
Neither Speko nor Artificial Analysis rates its voice quality.
Speko has not scored its pronunciation of numbers and dates.
No list price is published by Coval, Speko or Artificial Analysis for this model.
The benchmarks measure this model through Cloudflare's API, so the latency above is Cloudflare's. Coval's model registry names Deepgram as the creator and Cloudflare as the host.
Google Chirp 3: HD is a proprietary text-to-speech (TTS) API from Google, measured by two independent benchmarks: Artificial Analysis and Coval.
Fish Audio S2.1 Pro Free is a proprietary text-to-speech (TTS) API from Fish Audio, measured by one independent benchmark, Coval.
Alibaba Qwen3 TTS Flash Realtime is a proprietary text-to-speech (TTS) API from Alibaba (Qwen), measured by one independent benchmark, Coval.