##** Introduce**
Hey everyone, I'm back with another update on my personal voice AI assistant project.
Currently, I’m done with the implementation of the call Gemini API with streaming responses and also implementing logic to convert text streaming to sentence streaming. Ok, now I’m seeking and testing with the TTS (text to speak) API and finally finding out the OpenAI TTS API.
*Why OpenAI TTS*
Incredibly natural-sounding.
Various voice options.
*OpenAI TTS in the Terminal*
First, you'll need to get your OpenAI API key.
Next, set the API key to the terminal environment variable.
Ready to go with a terminal HTTP request.
Repo: github.com/Nhinlee/ai_partner