49 ms time to first audio on Speko's board (read October 22, 2026); not measured by Coval, so no speed tier.
Benchmark summary: No speed tier: Coval, the source of the tiers, does not measure this model.
Nari Qwen3-TTS is an open-weights text-to-speech (TTS) API from Alibaba (Qwen), served by Nari Labs, measured by one independent benchmark, Speko.
Speed tier
Not measured by Coval
No speed tier: Coval, the source of the tiers, does not measure this model.
Data read October 22, 2026. No combined score: methodology
Gradium TTS vs Nari Qwen3-TTS Fastest TTS APIs, by speed tierSpeko's board plots it at 49 ms time to first audio from US East; its model page reports a 75 ms sweep.
Speko rates its naturalness at 1,510 Elo from blind A/B votes on phone-agent lines (22nd highest of the 43 models Speko rates).
Speko's pronunciation test on numbers, dates and currency scores it 0.32 on a 0-to-1 scale (14th 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.
Speko lists about $5. List prices, as each source prints them.
The benchmarks measure this model through Nari Labs' API, so the latency above is Nari Labs'. The creator, Alibaba (Qwen), is inferred from the model name.
Alibaba Qwen-Audio-3.0-TTS-Plus is a proprietary text-to-speech (TTS) API from Alibaba (Qwen), measured by one independent benchmark, Artificial Analysis.
Alibaba Qwen-Audio-3.1-TTS-Plus is a proprietary text-to-speech (TTS) API from Alibaba (Qwen), measured by one independent benchmark, Artificial Analysis.
Alibaba Qwen3 TTS is a proprietary text-to-speech (TTS) API from Alibaba (Qwen), measured by one independent benchmark, Artificial Analysis.