Skip to content

Alibaba (Qwen) · read on October 27, 2026

Alibaba Qwen3 TTS Flash Realtime

Alibaba Qwen3 TTS Flash Realtime is a TTS (text-to-speech) model from Alibaba (Qwen). Coval measures its P95 time to first audio at 785.8 ms, which puts it in the Visible delay speed tier. It ranks 28 of 86 in the full ranking.

Speed tier
Visible delay
P95 / median
785.8 ms / 726.8 ms
Listener Elo
Not rated
Price per 1M chars
$13

Where it ranks

Full ranking: 28 of 86. Artificial Analysis does not rate this model for a use case, and it is not among the fastest, so it appears on no use case page.

The tier and the ranks are computed by this site from the benchmarks' figures, not declared by Alibaba (Qwen).

Measurements and sources

Coval

Median time to first audio (P50)726.8 ms
Time to first audio, P95785.8 ms
Time to first audio, mean728.5 ms
Time to first audio, P90768.7 ms
Timed requests2,807

Details

ProviderAlibaba (Qwen)
AccessProprietary
StreamingA benchmark measures its time to first audio
Features listed by Covalmultilingual
Languages testedNot collected: no benchmark here lists languages for this model
Measured byCoval
Official siteqwen.ai

Not collected

Nothing below is estimated. Each line says which measure is missing and why.

Sources

Values are copied from these pages on the date shown. Vendor and model name agree in every source that lists it.

Compare it with the reference model: Gradium TTS vs Alibaba Qwen3 TTS Flash Realtime.