Skip to content

Alibaba (Qwen) · read on October 27, 2026

Alibaba Qwen3 TTS 1.7b

Alibaba Qwen3 TTS 1.7b is a TTS (text-to-speech) model from Alibaba (Qwen). Coval measures its P95 time to first audio at 136.6 ms, which puts it in the Fast enough speed tier. It ranks 5 of 86 in the full ranking.

Speed tier
Fast enough
P95 / median
136.6 ms / 103.6 ms
Listener Elo
Not rated
Price per 1M chars
Not collected

Where it ranks

Full ranking: 5 of 86. Use case ranks, by speed:

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)103.6 ms
Time to first audio, P95136.6 ms
Time to first audio, mean105.4 ms
Time to first audio, P90129.3 ms
Timed requests2,586

Benchmarked through Baseten's API: the latency shown is the host's, not the model creator's.

Details

ProviderAlibaba (Qwen)
AccessOpen weights
StreamingA benchmark measures its time to first audio
Features listed by Covalmultilingual, voice-cloning
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 1.7b.