Qwen3 TTS TTS
Alibaba's 1.7B multilingual model offering both 9 preset voices and voice design from a plain-text description.
Wrap your text in SSML tags for precise control:
<speak><prosody rate="slow">Slow speech</prosody></speak>
Tags the selected model understands — click to drop one into your text where it happens:
This model reads plain text, so inline tags are ignored. For tag-based emotion, switch to an expressive model like Orpheus or Bark.
Define custom pronunciations (word = pronunciation):
About Qwen3 TTS
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.
Best for: Multilingual content with preset voices or custom voice design
Browse all Qwen3 TTS voicesAt 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