64.6 ms P50 time-to-first-audio on Coval; ranked 2nd (tied) of 112 in the TTS for Voice Agents 2026 index.
Benchmark summary: 73.7/100, ranked 2nd (tied) of 112 in the TTS for Voice Agents 2026 index (Leader). Strongest criterion: real-time speed, 57.7 of 60 points.
Alibaba Qwen3 TTS Fast is an open-weights text-to-speech (TTS) API from Alibaba (Qwen), served by Nari Labs, measured by two independent benchmarks: Coval and Speko.
Overall score
73.7 /100
Data checked on September 30, 2026
Updated after each benchmark capture
Every point comes from a public benchmark: sources · methodology
Alibaba Qwen3 TTS Fast ranks 2nd of 112 in the 2026 text-to-speech (TTS) API benchmark, with a score of 73.7/100.
On Coval's 30-day window ending October 1, 2026 (7,083 runs), Alibaba Qwen3 TTS Fast has a P50 (median) time-to-first-audio (TTFA) of 64.6 ms, 3rd lowest of the 31 models Coval measures. Its P99, the slowest 1% of turns, is 125.3 ms (2nd lowest of the 31 models Coval measures). Latency consistency: a standard deviation of 14.6 ms (the lowest of the 31 models Coval measures). Mean time to first byte (TTFB) is 60.9 ms. Speko measures a P50 TTFA of 64 ms from US East (n=30), dated September 12, 2026: the lowest of the 29 models Speko measures.
Coval measures an accuracy (word error rate) of 3.7% over 7,076 samples on the same window, 2nd lowest of the 31 models Coval measures. Speko rates its pronunciation robustness on numbers, dates and currency at 0.3 on a 0-to-1 scale (14th highest of the 28 models Speko rates).
Speko rates its naturalness at 1,536 Elo from blind A/B votes (20th highest of the 41 models Speko rates).
Speko lists a cost of about $10 per 1M characters.
Coval and Speko measure this model through Nari Labs' API, so the latency above is Nari Labs'. Coval's model registry names Alibaba (Qwen) as the creator and Nari Labs as the host.
Speko changed its pronunciation robustness between the captures of September 30, 2026 and October 1, 2026 without a new measurement date (0.15, then 0.3): the score uses the average, 0.225. The value shown is the latest.
Soniox TTS Real-Time v2 is a proprietary text-to-speech (TTS) API from Soniox, measured by three independent benchmarks: Artificial Analysis, Coval and Speko.
Gradium TTS Beta is a proprietary text-to-speech (TTS) API from Gradium, measured by two independent benchmarks: Coval and Speko.
Alibaba Qwen3 TTS 1.7b is an open-weights text-to-speech (TTS) API from Alibaba (Qwen), served by Baseten, measured by one independent benchmark, Coval.