> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/QwenLM/Qwen3-TTS/llms.txt
> Use this file to discover all available pages before exploring further.

# qwen-tts-demo

> Launch a Gradio web UI demo for Qwen3-TTS models

## Overview

The `qwen-tts-demo` command launches an interactive Gradio web interface for testing and using Qwen3-TTS models. It supports all three model types: CustomVoice, VoiceDesign, and Base (voice cloning).

## Installation

The command is automatically available after installing the `qwen-tts` package:

```bash theme={null}
pip install qwen-tts
```

## Basic Usage

```bash theme={null}
qwen-tts-demo MODEL_PATH [OPTIONS]
```

### Quick Start Examples

```bash theme={null}
# CustomVoice model
qwen-tts-demo Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice --ip 0.0.0.0 --port 8000

# VoiceDesign model
qwen-tts-demo Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign --ip 0.0.0.0 --port 8000

# Base model (voice cloning)
qwen-tts-demo Qwen/Qwen3-TTS-12Hz-1.7B-Base --ip 0.0.0.0 --port 8000
```

After launching, open `http://<your-ip>:8000` in your browser, or access via port forwarding in tools like VS Code.

## Command Options

### Model Checkpoint

<ParamField path="checkpoint" type="string" required>
  Model checkpoint path or HuggingFace repo ID (positional argument)

  Can also be specified with `-c` or `--checkpoint` flag.

  **Examples:**

  * `Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice`
  * `./local/path/to/model`
</ParamField>

### Model Loading Options

<ParamField path="--device" type="string" default="cuda:0">
  Device for model inference

  **Options:** `cpu`, `cuda`, `cuda:0`, `cuda:1`, etc.
</ParamField>

<ParamField path="--dtype" type="string" default="bfloat16">
  Torch dtype for loading the model

  **Choices:** `bfloat16`, `bf16`, `float16`, `fp16`, `float32`, `fp32`
</ParamField>

<ParamField path="--flash-attn / --no-flash-attn" type="boolean" default="true">
  Enable or disable FlashAttention-2 for efficient memory usage

  FlashAttention-2 is recommended for better performance. Requires compatible hardware.
</ParamField>

### Server Configuration

<ParamField path="--ip" type="string" default="0.0.0.0">
  Server bind IP address for Gradio

  Use `0.0.0.0` to allow external connections, or `127.0.0.1` for local only.
</ParamField>

<ParamField path="--port" type="integer" default="8000">
  Server port for Gradio
</ParamField>

<ParamField path="--share / --no-share" type="boolean" default="false">
  Create a public Gradio link for sharing

  When enabled, generates a temporary public URL.
</ParamField>

<ParamField path="--concurrency" type="integer" default="16">
  Gradio queue concurrency limit
</ParamField>

### HTTPS/SSL Options

<ParamField path="--ssl-certfile" type="string">
  Path to SSL certificate file for HTTPS (optional)

  Required for secure connections and browser microphone access in Base model.
</ParamField>

<ParamField path="--ssl-keyfile" type="string">
  Path to SSL private key file for HTTPS (optional)
</ParamField>

<ParamField path="--ssl-verify / --no-ssl-verify" type="boolean" default="true">
  Whether to verify SSL certificate

  Use `--no-ssl-verify` for self-signed certificates.
</ParamField>

### Generation Parameters

<ParamField path="--max-new-tokens" type="integer">
  Maximum new tokens for generation (optional)
</ParamField>

<ParamField path="--temperature" type="float">
  Sampling temperature (optional)
</ParamField>

<ParamField path="--top-k" type="integer">
  Top-k sampling (optional)
</ParamField>

<ParamField path="--top-p" type="float">
  Top-p sampling (optional)
</ParamField>

<ParamField path="--repetition-penalty" type="float">
  Repetition penalty (optional)
</ParamField>

<ParamField path="--subtalker-top-k" type="integer">
  Subtalker top-k (optional, only for tokenizer v2)
</ParamField>

<ParamField path="--subtalker-top-p" type="float">
  Subtalker top-p (optional, only for tokenizer v2)
</ParamField>

<ParamField path="--subtalker-temperature" type="float">
  Subtalker temperature (optional, only for tokenizer v2)
</ParamField>

## HTTPS Setup for Base Model

For Base model deployments, HTTPS is recommended to avoid browser microphone permission issues:

### Generate Self-Signed Certificate

```bash theme={null}
openssl req -x509 -newkey rsa:2048 \
  -keyout key.pem -out cert.pem \
  -days 365 -nodes \
  -subj "/CN=localhost"
```

### Launch with HTTPS

```bash theme={null}
qwen-tts-demo Qwen/Qwen3-TTS-12Hz-1.7B-Base \
  --ip 0.0.0.0 --port 8000 \
  --ssl-certfile cert.pem \
  --ssl-keyfile key.pem \
  --no-ssl-verify
```

Then open `https://<your-ip>:8000` in your browser.

<Note>
  Your browser may show a security warning for self-signed certificates. This is expected. For production deployments, use a real certificate from a trusted Certificate Authority.
</Note>

## Model-Specific Features

### CustomVoice Demo

Provides interface for:

* Text input with language selection
* Speaker selection (9 premium voices)
* Optional instruction control (e.g., "Say it in a very angry tone")

### VoiceDesign Demo

Provides interface for:

* Text input with language selection
* Natural language voice design instructions
* Dynamic voice generation based on descriptions

### Base Model Demo

Provides two tabs:

1. **Clone & Generate**: Upload reference audio with transcript, then synthesize new text
2. **Save/Load Voice**: Save voice clones as reusable prompt files for consistent character voices

## Help Command

View all available options:

```bash theme={null}
qwen-tts-demo --help
```

## Related

* [Model API Reference](/api/model/overview)
* [CustomVoice Model Guide](/guides/custom-voice)
* [VoiceDesign Guide](/guides/voice-design)
* [Voice Cloning Guide](/guides/voice-cloning)