Skip to content

Alibaba · Speech

Qwen3 TTS

Alibaba 🇨🇳SpeechQwen familyOne of its sources says the weights aren't publicly available.
From Modelrunner AI's listing:
Turn text into speech with nine preset voices in 10 languages, including Beijing and Sichuan dialect Mandarin, and steer the pace with a plain-language instruction.
Market median price
$20.00 /1M chars
Listings
5
Providers
5

Evidence and sources

International storefront (alibabacloud.com) is Singapore-incorporated; mainland operating entity 杭州阿里云智能科技有限公司 (Hangzhou).

Maker HQ: CN (source)
Sources: DeepInfra data, ModelRunner.ai dataPrimary data from DeepInfra from ModelRunner.ai: weights availability, primary mode, description

Advantages and trade-offs

Compared with 10 representative speech models

Advantages

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 04:34 UTC.

Input & output

as stated by the model's providers
Text
Audio

Listings

 Replicateqwen/qwen3-ttsSources: LiteLLM data, Replicate data docsNot published by the provider—$20.00—
 Modelrunner AIRegions: globalqwen/qwen3-tts/text-to-speech · text-to-speechSource: ModelRunner.ai dataNot published by the provider$0.042——
 Tinfoilqwen3-ttsSource: Tinfoil dataNot published by the provider——$0.01

2 listings without a price are hidden.

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Speech

Also known as: modelrunner-ai/qwen-qwen3-tts-text-to-speech, qwen/qwen3-tts, replicate/qwen/qwen3-tts

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works