Qwen3 TTS

Qwen3 TTS TTS

Alibaba's 1.7B multilingual model offering both 9 preset voices and voice design from a plain-text description.

Qwen3-TTS is a 1.7-billion-parameter model from Alibaba's Qwen team, built on the Qwen3 backbone with a multi-codebook decoder. What sets it apart is its dual operating mode: you can pick from 9 preset speakers with emotion control, or switch to a voice-design mode where you describe the voice you want in natural language and the model synthesizes a matching one. It spans 10 languages — English, Chinese, Japanese, Korean, German, French, Russian, Portuguese, Spanish, and Italian — with high expressiveness and natural prosody. It handles up to 2,000 characters per request, making it a flexible choice for multilingual content that needs either consistent preset voices or bespoke custom ones.

At a glance

Developer
Alibaba (Qwen)
License
Apache 2.0
Tier
standard
Speed
medium
Voice cloning
No
Languages
English, Chinese, Japanese, Korean, German, French, Russian, Portuguese, Spanish, Italian
Max characters
2000

Qwen3 TTS AI Voices

Aiden

English
Defaŭlta Male
Uzu

Aiden (Italian)

Italian
Defaŭlta Male
Uzu

Dylan

English
Defaŭlta Male
Uzu

Dylan (Russian)

Russian
Defaŭlta Male
Uzu

Dylan (Spanish)

Spanish
Defaŭlta Male
Uzu

Eric

English
Defaŭlta Male
Uzu

Eric (French)

French
Defaŭlta Male
Uzu

Ono Anna

Japanese
Defaŭlta Female
Uzu

Ryan

English
Defaŭlta Male
Uzu

Ryan (German)

German
Defaŭlta Male
Uzu

Ryan (Portuguese)

Portuguese
Defaŭlta Male
Uzu

Serena

English
Defaŭlta Female
Uzu

Serena (Italian)

Italian
Defaŭlta Female
Uzu

Serena (Portuguese)

Portuguese
Defaŭlta Female
Uzu

Serena (Spanish)

Spanish
Defaŭlta Female
Uzu

Sohee

Korean
Defaŭlta Female
Uzu

Uncle Fu

Chinese
Defaŭlta Male
Uzu

Vivian

English
Defaŭlta Female
Uzu

Vivian (French)

French
Defaŭlta Female
Uzu

Vivian (German)

German
Defaŭlta Female
Uzu

Vivian (Russian)

Russian
Defaŭlta Female
Uzu

Best for

Multilingual content with preset voices or custom voice design

Qwen3 TTS TTS — FAQ

Qwen3 TTS covers 10 languages: English, Chinese, Japanese, Korean, German, French, Russian, Portuguese, Spanish, and Italian.

Yes. Alongside its 9 preset voices with emotion control, Qwen3 TTS has a voice-design mode where you describe the voice in natural language and it generates one to match. It does not do reference-audio voice cloning, however.

Yes. Qwen3 TTS is licensed under Apache 2.0, allowing commercial use.
← All voices