Welcome to CosyVoice! This application provides a simple way to transform text into speech using a user-friendly web interface. You can also make use of voice cloning and a REST API for advanced features.

Before you start, ensure your computer meets the following requirements:

• Operating System: Windows, macOS, or Linux
• RAM: At least 4 GB
• Storage: Minimum 1 GB of free space
• Docker: Ensure Docker is installed on your machine. You can download it from Docker Hub.

To get started, visit our Releases page to download the latest version. Choose the suitable package for your operating system and follow these instructions:

1. Open the Releases page.
2. Find the latest version of CosyVoice.
3. Click on the download link for your operating system.
4. Once downloaded, locate the file on your computer.

After downloading, follow these steps to set up and run the application:

1. Open a terminal or command prompt.
2. Navigate to the directory where you downloaded the file.
3. Run the following command:

   docker run -p 80:80 cosyvoice/cosyvoice
   

4. Open your web browser and go to http://localhost.

• Text-to-Speech: Convert text into realistic speech.
• Voice Cloning: Create custom voice profiles.
• Web UI: Easy access to settings and features.
• REST API: Integrate with other applications seamlessly.

Once you access the web interface via your browser, you will see options to input text and select voice preferences. The interface is designed to help you easily perform tasks without needing advanced technical knowledge.

• Select Voice: Choose from various available voices.
• Adjust Speed: Change speech speed to suit your preference.
• Build Custom Voice: Use voice cloning to create a unique voice for your projects.

If you're familiar with command-line tools, you can use the REST API to integrate CosyVoice into your applications. The API allows you to send text and receive audio in return. Refer to the documentation in the repository for detailed usage and examples.

Here's a simple example to get you started:

1. Send a POST request to http://localhost/api/synthesize.
2. Include the text you want to synthesize in the request body.

For detailed documentation, visit our GitHub Wiki where you will find:

• User guides
• API references
• Troubleshooting tips

Join our community to learn more about CosyVoice. You can ask questions and share your projects. We welcome your feedback and contributions.

If you encounter any issues while using CosyVoice, please report them on the Issues page. We will address concerns as quickly as possible.

Your data privacy is important to us. CosyVoice does not store any personal information. All processing happens locally on your machine.

We value user feedback. If you have suggestions for improvements or new features, feel free to connect with us on our GitHub discussions or via email.

• Releases Page
• Documentation
• Issues Tracker

Thank you for choosing CosyVoice. Enjoy creating with our easy-to-use text-to-speech application!