Qwen3-TTS Demo

Qwen3-TTS Demo

Turns typed text into speech with the Qwen3-TTS models on a Gradio page, in the browser or on your own computer. For anyone who wants to hear the model's voices or see how the demo is wired.

Made by Qwen on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face.

About

What it is: Qwen3-TTS Demo is a Gradio page from the Qwen team for trying their text-to-speech models. It names three 1.7B checkpoints called Base, CustomVoice and VoiceDesign. You can use it in the browser with nothing to install.

Who it suits: It suits people who want to hear what a modern open speech model sounds like, and developers who want to see how a demo around one is built.

Industry | Who uses it | How they use it | Example
Software | Developers | Read the demo code before adding speech to an app | Look through app.py and the qwen_tts folder
Media | Content creators | Try spoken versions of a short script | Type a few lines and play the audio that comes back
Research | Speech researchers | Compare the three named checkpoints in one place | Run the same text through each model the Space names
Education | Teachers and students | Hear written material read aloud | Paste a short passage and listen to it

Skip it if you need a finished product with its own app or support, since this is a demo page.

Where to use it:

• A web browser, on the Space's page at Hugging Face
• Your own Windows, macOS or Linux computer with Python

Use case | Who | What they get back
Hear text read aloud | Creators | Generated speech for the text you give it
Try the named models | Researchers | A way to listen to Base, CustomVoice and VoiceDesign
Study the demo | Developers | A small Gradio app you can read and change

How to set it up: The online page needs nothing. A local copy needs Python and the packages listed in requirements.txt.

• Python and pip
• The packages listed in requirements.txt
• Windows, macOS or Linux

1. Install the Hugging Face hub library.
2. Download the Space's files into a folder named Qwen3-TTS.
3. Move into that folder.
4. Install Gradio 5.33.0, then the packages from requirements.txt.
5. Start app.py.

pip install -U huggingface_hub
hf download Qwen/Qwen3-TTS --repo-type space --local-dir Qwen3-TTS
cd Qwen3-TTS
pip install gradio==5.33.0
pip install -r requirements.txt
python app.py

How to use it: Open the Space's page and use the form it shows. For a local copy, run the last command above and open the address it prints in your browser.

python app.py

Example: You open the page, give it a short piece of text and ask for speech. The page runs a model and returns audio you can play back in the browser.

For newcomers and experts: Open the online page and give it one short sentence. Play the audio that comes back before you try anything longer.

The app is built with Gradio 5.33.0, and its main file is app.py. The Hugging Face copy runs on ZeroGPU hardware, which hands out a GPU per request. The repository holds app.py, a qwen_tts folder and requirements.txt. The record gives no README, so it does not describe the page's settings or what separates the three checkpoints.

Open the page
Give it the text to speak
A Qwen3-TTS model runs
Play the audio

Good to know:

• Hardware: The Hugging Face copy runs on ZeroGPU hardware.
• Gaps: The source has no README, so voice options and limits are not described here.
• License: apache-2.
• Cost to run: none named.
• Data it reaches: The text you give it. A local copy also downloads the packages in requirements.txt.

On Hugging Face, 13 November 2026

• Likes: 2,410
• Built with: gradio
• License: apache-2.0

Links

• Space: https://huggingface.co/spaces/Qwen/Qwen3-TTS
• Files: https://huggingface.co/spaces/Qwen/Qwen3-TTS/tree/main

Try it

Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself.