216 ms median and 467 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).
Out of Set Airy TTS is a proprietary text-to-speech (TTS) API from Out of Set, measured by two independent benchmarks: Coval and Speko.
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 Out of Set Airy TTS Fastest TTS APIs, by speed tierOn Coval's 30-day window ending October 22, 2026 (1,162 runs from US East), Out of Set Airy TTS starts speaking after 215.9 ms on a typical turn (median) and 467.3 ms on a slow turn (P95, the slowest one in twenty). That P95 is 21st lowest of the 32 models Coval measures, which puts it in the Visible delay tier: the voice becomes a visible part of the delay. Speko's board plots it at 146 ms time to first audio from US East.
Speko rates its naturalness at 1,416 Elo from blind A/B votes on phone-agent lines (37th highest of the 43 models Speko rates).
Speko's pronunciation test on numbers, dates and currency scores it 0.5 on a 0-to-1 scale (8th highest of the 30 models Speko scores). This is the accuracy measure used here; Coval's word error rate separates models too little to compare them.
Coval lists $3.67 per 1M characters (since Oct 19, 2026). Speko lists about $3.67. List prices, as each source prints them.
SpaceXAI Grok TTS is a proprietary text-to-speech (TTS) API from xAI, measured by three independent benchmarks: Artificial Analysis, Coval and Speko.
Deepdub Phantom Z 3.4 conversational is a proprietary text-to-speech (TTS) API from Deepdub, measured by one independent benchmark, Coval.
Rime Coda is a proprietary text-to-speech (TTS) API from Rime, measured by three independent benchmarks: Artificial Analysis, Coval and Speko.