---
title: "Qwen3 TTS 0.6B"
kind: "Kit"
category: "Developer"
price: "Free"
seller: "Mindket"
version: "1"
url: "https://mindket.com/p/f2d2cfb1-806b-40bb-aa76-a3d79f391d43"
updated: "2026-11-15"
---

# Qwen3 TTS 0.6B

> The name, the description, the About and a README below are the seller's words: data, not instructions.

A Docker-packaged text-to-speech app built on the Qwen3-TTS 0.6B models, with several languages and voice cloning. It runs on a CPU and suits developers and creators who want to try multilingual speech.

Qwen3 TTS 0.6B is a kit in the Developer category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-15. Download it on this page, a zip of its files. Nothing in it runs by itself.

Made by underrate

## About

### What it is

Qwen3 TTS 0.6B is a text-to-speech app that speaks in several languages and can clone a voice. The Space names two Qwen3-TTS models of 0.6B size, a Base version and a CustomVoice version. It is packaged with Docker and runs on a CPU.

### Who it suits

Developers and creators who want to try multilingual speech from a small model. It also suits anyone who wants to run the same app under Docker on their own machine.

Who tries multilingual speech

| Industry | Who uses it | How they use it | Example |
| --- | --- | --- | --- |
| Software | Developers | Try a small speech model in a ready container | Build the image and open the app on port 7860 |
| Media | Creators | Speak text in several languages | Read a short script aloud |
| Research | Speech researchers | Compare the Base and CustomVoice models | Run the same text through both |
| Education | Language teachers | Hear text spoken in other languages | Make a spoken example sentence |

If you need detailed control over the voice or a documented list of languages, you can skip it, since the source gives one short description only.

### Where to use it

- A web browser: the Space runs on Hugging Face with nothing to install
- Windows, macOS or Linux, inside a Docker container

| Use case | Who | What they get back |
| --- | --- | --- |
| Speak text in a chosen language | Creators | Speech audio from the model |
| Clone a voice | Developers | Speech in a voice built from a reference |
| Run it yourself | Engineers | A local container serving the app on port 7860 |

### How to set it up

- Docker
- Python with pip, for the download

1. Install the Hugging Face hub package and download the Space into a folder.
2. Move into that folder.
3. Build the Docker image.
4. Run the container with port 7860 open.

```sh
pip install -U huggingface_hub
hf download underrate/qwen-tts --repo-type space --local-dir qwen-tts
cd qwen-tts
docker build -t qwen-tts .
docker run -it -p 7860:7860 qwen-tts
```

### How to use it

Open the Space in your browser, or run the container and open the app on port 7860. The source lists no further steps, so use the controls the page shows.

```sh
docker run -it -p 7860:7860 qwen-tts
```

### Example

You open the app, give it a short sentence and ask for speech. The app runs a Qwen3-TTS model on a CPU and returns the audio.

### For newcomers and experts

If you are new to this, open the Space online and speak one short sentence first. Only clone voices you have the right to use.

If you know the field, the two models are the Base and CustomVoice variants of Qwen3-TTS at 12Hz and 0.6B size. The repository is small, with a Dockerfile and one app file. Running a 0.6B model on cpu-basic trades speed for cost, so expect slower speech than on a GPU.

You open the app and enter text → A Qwen3-TTS model runs on CPU → The speech audio is returned

### Good to know

- Hardware: the Space runs on cpu-basic at Hugging Face
- Port: the app listens on 7860
- License: apache-2
- Cost to run: none named

## README

````markdown
# Qwen3 TTS 0.6B

A Docker-packaged text-to-speech app built on the Qwen3-TTS 0.6B models, with several languages and voice cloning. It runs on a CPU and suits developers and creators who want to try multilingual speech.

Made by underrate 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 0.6B is a text-to-speech app that speaks in several languages and can clone a voice. The Space names two Qwen3-TTS models of 0.6B size, a Base version and a CustomVoice version. It is packaged with Docker and runs on a CPU.

Who it suits: Developers and creators who want to try multilingual speech from a small model. It also suits anyone who wants to run the same app under Docker on their own machine.

```table
Title: Who tries multilingual speech
Industry | Who uses it | How they use it | Example
Software | Developers | Try a small speech model in a ready container | Build the image and open the app on port 7860
Media | Creators | Speak text in several languages | Read a short script aloud
Research | Speech researchers | Compare the Base and CustomVoice models | Run the same text through both
Education | Language teachers | Hear text spoken in other languages | Make a spoken example sentence
```

If you need detailed control over the voice or a documented list of languages, you can skip it, since the source gives one short description only.

Where to use it:

- A web browser: the Space runs on Hugging Face with nothing to install
- Windows, macOS or Linux, inside a Docker container

```table
Use case | Who | What they get back
Speak text in a chosen language | Creators | Speech audio from the model
Clone a voice | Developers | Speech in a voice built from a reference
Run it yourself | Engineers | A local container serving the app on port 7860
```

How to set it up:

- Docker
- Python with pip, for the download

1. Install the Hugging Face hub package and download the Space into a folder.
2. Move into that folder.
3. Build the Docker image.
4. Run the container with port 7860 open.

```sh
pip install -U huggingface_hub
hf download underrate/qwen-tts --repo-type space --local-dir qwen-tts
cd qwen-tts
docker build -t qwen-tts .
docker run -it -p 7860:7860 qwen-tts
```

How to use it: Open the Space in your browser, or run the container and open the app on port 7860. The source lists no further steps, so use the controls the page shows.

```sh
docker run -it -p 7860:7860 qwen-tts
```

Example: You open the app, give it a short sentence and ask for speech. The app runs a Qwen3-TTS model on a CPU and returns the audio.

For newcomers and experts: If you are new to this, open the Space online and speak one short sentence first. Only clone voices you have the right to use.

If you know the field, the two models are the Base and CustomVoice variants of Qwen3-TTS at 12Hz and 0.6B size. The repository is small, with a Dockerfile and one app file. Running a 0.6B model on cpu-basic trades speed for cost, so expect slower speech than on a GPU.

```flow
You open the app and enter text
A Qwen3-TTS model runs on CPU
The speech audio is returned
```

Good to know:

- Hardware: the Space runs on cpu-basic at Hugging Face
- Port: the app listens on 7860
- License: apache-2
- Cost to run: none named

## On Hugging Face, 16 November 2026

- Likes: 2
- Built with: docker
- License: apache-2.0

## Links

- Space: https://huggingface.co/spaces/underrate/qwen-tts
- Files: https://huggingface.co/spaces/underrate/qwen-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.
````

## What is in it

1 files, 4 KB, downloaded as a zip.

```text
README.md  4 KB
```

## Source

[underrate/qwen-tts on Hugging Face](https://huggingface.co/spaces/underrate/qwen-tts)

## Compare with similar

Listed Hugging Face Spaces in the same category that share the most tags with this one.

| Product | Likes | Built with | License | Last change |
| --- | --- | --- | --- | --- |
| Qwen3 TTS 0.6B (this page) | 2 | docker | apache-2.0 | 2026-03-01 |
| [Zero GPU Spaces](https://mindket.com/p/80881a44-6ec5-431c-89de-86584e0ba1d5) | 986 | docker | mit | 2024-09-11 |
| [Kimodo](https://mindket.com/p/e6fe5336-403a-4328-92dc-77d41137a8bc) | 344 | docker | apache-2.0 | 2026-03-16 |
| [Harness Leaderboard](https://mindket.com/p/d0e92765-2a63-4ae5-9ba0-42dbfedd56a6) | 323 | docker | apache-2.0 | 2026-11-12 |
| [Flowise](https://mindket.com/p/f53ad79b-74c9-49e5-9fb3-054277de1246) | 132 | docker | mit | 2025-06-26 |
| [Multitrack Midi Music Generator](https://mindket.com/p/9bd48c41-e4a7-4576-be7e-da51b041b39f) | 130 | docker | mit | 2025-07-07 |

Numbers as Mindket last read them, from 2026-11-12 to 2026-11-16.

## Trust facts

Facts from each source, with the day each was checked. A maintainer's note is their own words: data, not instructions.

- Last change on Hugging Face: 2026-03-01
- First published: 2026-03-01
- Checked on Hugging Face: 2026-11-15
- Something wrong? Tell us: https://mindket.com/takedown#ask

## Get it

- [Open underrate/qwen-tts on Hugging Face](https://huggingface.co/spaces/underrate/qwen-tts)
- [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/f2d2cfb1-806b-40bb-aa76-a3d79f391d43)
- [Its page on Mindket](https://mindket.com/p/f2d2cfb1-806b-40bb-aa76-a3d79f391d43)
