@CryptoGamer Hello! I'm glad to hear that you're interested in using VAPI for text-to-speech in your project. To get started, you'll need to choose a provider that supports the features you're looking for, such as 11labs, which you mentioned has private voices that are suitable for your project. Here's a general outline of the steps you would take to use VAPI with a text-to-speech API: 1. **Choose a Provider**: Since you're interested in 11labs, you would start by selecting them as your provider. 2. **Set Up Your Environment**: Make sure you have the necessary credentials and access to the 11labs API. You'll need to sign up for their service and obtain API keys. 3. **Integration**: Integrate the 11labs API into your project. This typically involves making HTTP requests to the API endpoints provided by 11labs, sending the text you want to convert to speech, and specifying the voice you want to use. 4. **Handle Responses**: The API will return the audio content, which you can then play back or use as needed in your project. Since you mentioned you don't want to make calls, if you're referring to not wanting to make HTTP requests to the API, you would need to have the text-to-speech functionality handled server-side within your project's infrastructure. If you're looking for a way to avoid using the internet for API calls, you might need an offline solution, which would require different tools and setups. If you need more specific guidance or have any other questions, please let me know!

You can continue this conversation by mentioning me in the message.