Welcome to the tts project! This application allows you to easily convert text into speech. Follow the steps below to download and run the software.
To get started, you need to visit the Releases page and download the latest version of the application. Click the link below:
Once you're on the Releases page, look for the latest version. You will find various files available. Choose the one that fits your system and click to download.
The tts project supports different deployment options:
- Use the
gemini-ttsbranch for Gemini TTS deployment. - You need to provide your own Gemini API key. Instructions for setting it up can be found below.
- Use the
openai-ttsbranch for OpenAI TTS deployment. - Similar to Gemini, you will need an OpenAI API key. Follow the setup instructions provided.
- Use the
ms-ttsbranch for deploying Microsoft Azure TTS. - You must add an environment variable,
API_KEY. This key controls access for users. After setting up your API key, you will also need to set it in the front-end page to access the service.
- Go to Workers & Pages.
- Click on Your Worker.
- Go to Settings.
- Navigate to Variables and Secrets.
- Click on Add.
- Type:
Secret - Name:
API_KEY - Value:
YOUR_API_KEY
For both gemini-tts and openai-tts, you will need to set your API keys in the front-end interface.
- In the front-end, locate the settings option.
- Enter your
gemini api-keyas prompted.
- Navigate to the API settings in the front-end.
- Input your
openai api-keywhere indicated.
For more insights on setting up your TTS service, you may find the following links useful:
- Building Your Own TTS Service - A Comprehensive Guide
- Gemini TTS Client is Open Source!
- New Version of OpenAI TTS Source Code Available
If you have questions or need assistance, refer to the documentation, or visit the community forums. Enjoy using tts!