Getting Started
About 443 wordsAbout 1 min
Getting Started
System Requirements
- Operating System: Windows 10/11
- CPU Version: Minimum 16GB RAM, minimum requirement Intel i5-12400/AMD R5600, recommended Intel i7-13700K/AMD R7 7800X3D and higher performance CPU
- GPU Version: Minimum 16GB RAM, Nvidia graphics card device with 6GB or more VRAM (minimum requirement GTX 1070 or equivalent performance graphics card; recommended RTX 3060/4060 and higher performance graphics card)
- Storage: At least 12GB free space (single model ~4GB, environment ~6GB)
Download and Installation
Option 1: Download Executable File Directly (Recommended)
Download the Latest Version
- Download the latest version of Cyrene QwenTTS GUI from the GitHub Releases page
Download Dependencies List File
- Download the requirements.txt file
- Place it in the same directory as the executable file
Run the Application
- Double-click the executable file to launch the application
Option 2: Build from Source (Not Recommended)
Clone the Repository
- Clone the GitHub Repository
Install Dependencies
- Requirements: Python 3.10-3.12
- Run:
pip install -r requirements.txt
Run the Application
- Execute:
python package.py
- Execute:
First Launch
When you first launch Cyrene QwenTTS GUI, you will see a wizard interface. Complete the initial setup according to the wizard, including:
- Select language (English or Chinese)
- Choose to install the runtime environment based on your actual situation (GPU environment/CPU environment)
Basic Operations
Voice Generation (Using Qwen3-...-CustomVoice Model)
- Select the "Generation" tab in the main interface
- Choose the appropriate model and speaker
- Enter the text to convert to speech
- Click the "Generate" button
- Preview the generated speech and save
Voice Design (Using Qwen3-...-CustomVoice Model)
- Select the "Design" tab in the main interface
- Enter a voice description (e.g., "A young female voice, happy tone")
- Enter the text to generate
- Click the "Generate" button
- Preview the designed voice speech and save
Voice Cloning (Using Qwen3-...-Base Model)
- Select the "Clone" tab in the main interface
- Upload a reference audio file
- Enter the text for the cloned voice to speak (optional)
- Click the "Clone" button
- Preview the cloned voice speech and save
Audio Browser
- Select the "Audio Browser" tab in the main interface
- Browse all generated audio files
- Double-click files to play
- Click "Open Folder" button to view file location
Settings
In the "Settings" tab, you can:
- Change interface language
Frequently Asked Questions
If you encounter any issues, please check the FAQ page or visit the GitHub Issues page for help.
Contributors
Changelog
2/16/26, 4:37 AM
View All Changelog
66651-Add files via uploadon
