All models
flagship

Qwen3-TTS

Apache-2.0

Alibaba's flagship, 97ms latency, 10 languages

Qwen3-TTS is the text-to-speech line from Alibaba's Qwen team, known for strong multilingual coverage — including Chinese dialects like Cantonese, Wu, and Sichuanese — with expressive preset voices and fast synthesis backed by the Qwen model family.

Voices

1 voice
Neutral
Defaultdefault
—
NeutralEmotionalNumbers & Dates

The scripts

Neutral
“The quick brown fox jumps over the lazy dog near the riverbank.”
Emotional
“I can't believe you actually did it. This is incredible!”
Numbers & Dates
“On March 14th, 2025, the team raised $4.2 million at a 38% margin.”

Install

pip install qwen3-tts

Qwen3-TTS FAQ

Do I need a GPU to run Qwen3-TTS?

For practical speeds, yes — plan on roughly 8 GB of VRAM. If you'd rather not manage a GPU, hosted access to every model in this directory is coming via OpenSpeech Cloud.

Can Qwen3-TTS clone voices?

Yes — Qwen3-TTS supports voice cloning from reference audio.

What license is Qwen3-TTS released under?

Qwen3-TTS is released under the Apache-2.0 license. Always check the repository for the exact terms — some models license code and weights separately.

What languages does Qwen3-TTS support?

Qwen3-TTS supports Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish, Italian.

Is there a hosted Qwen3-TTS API?

Yes — OpenSpeech Cloud is launching hosted, pay-per-minute access to Qwen3-TTS and every other model in this directory. No CUDA, Docker, or GPU needed.