Update README.md

README.md

@@ -10,4 +10,47 @@ pinned: false
 license: mit
 ---
 
+# AI Speech Therapist
+
+A voice-interactive AI speech therapy tool powered by LiveKit and OpenAI, designed for students with speech impediments and neurodivergent traits.
+
+## Description
+
+This Gradio application creates a low-latency voice-to-voice interaction between students and an AI speech therapist. It's specifically optimized for students with ASD and other neurodivergent conditions, featuring clear communication and a repeat function.
+
+## Features
+
+- **Voice-to-Voice Interaction**: Real-time conversations using OpenAI's speech models
+- **Low Latency**: Optimized processing for minimal delay
+- **Repeat Function**: Helps students who need information repeated
+- **Structured Therapy**: Following speech pathology best practices
+
+## Requirements
+
+- Python 3.8+
+- OpenAI API key
+- LiveKit account (room URL and token)
+
+## Setup
+
+### Environment Variables
+
+```
+OPENAI_API_KEY=your_openai_api_key
+```
+
+### Installation
+
+```bash
+pip install -r requirements.txt
+```
+
+## Usage
+
+1. Enter your LiveKit room URL and token in the provided fields
+2. Click "Start Session" to begin
+3. Speak clearly into your microphone
+4. Click "Repeat Last Response" if needed
+5. End the session when finished
+
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference