A Node.js server that accepts text prompts, generates conversational responses via the OpenAI API (GPT‑4 or GPT‑3.5‑turbo), and converts those responses to natural-sounding speech using the Eleven Labs API. Designed for local deployment, it provides an HTTP endpoint that returns audio files for further playback or download.
Key Features
Generates chat-style text using GPT‑4 or GPT‑3.5‑turbo
Converts generated text to speech using Eleven Labs voices
Exposes a POST /chat endpoint for prompt-to-audio functionality
Supports adjustable parameters such as temperature and voice selection
Easy-to-use setup with Node.js and Express framework
Outputs audio files (e.g., MP3) directly via API responses