🎙️ AudioPilot

AI-Powered Audio Intelligence Platform

AudioPilot transforms audio recordings into actionable insights using advanced speech transcription, audio signal analysis, and Large Language Models.

Built as a full-stack AI application with React, FastAPI, PostgreSQL, Groq LLMs, and cloud deployment infrastructure.

---

🚀 Live Demo

Frontend: https://audio-pilot-three.vercel.app/

Backend API: https://audiopilot-ckl7.onrender.com

---

✨ Features

🔐 Authentication

• JWT Authentication
• User Registration & Login
• Protected Routes
• Profile Management
• Password Updates

🎙️ Audio Processing

• Audio Upload
• Speech-to-Text Transcription
• Audio Quality Analysis
• Signal Processing with Librosa

🧠 AI Insights

• Whisper Large V3 Transcription
• Groq LLM Powered Reports
• Context-Aware Audio Understanding
• Improvement Suggestions

📊 Audio Metrics

• Clarity Score
• Energy Analysis
• Noise Detection
• Silence Percentage
• Audio Duration

📁 Analysis Management

• Analysis History
• Persistent Storage
• User-Specific Reports

---

🏗️ System Architecture

User Uploads Audio
        │
        ▼
 React Frontend
        │
        ▼
 FastAPI Backend
        │
 ┌──────┴──────┐
 ▼             ▼

Audio      Whisper
Metrics  Transcription

 ▼             ▼
 └──────┬──────┘
        ▼

   Groq LLM
 AI Insight Engine

        ▼

 PostgreSQL

        ▼

 User Dashboard

---

🛠️ Tech Stack

Frontend

• React
• Vite
• React Router
• Tailwind CSS
• Framer Motion
• Axios

Backend

• FastAPI
• SQLAlchemy
• PostgreSQL
• JWT Authentication
• Pydantic

AI & Audio

• Groq API
• Whisper Large V3
• Llama 3.1
• Librosa
• NumPy

Deployment

• Vercel
• Render
• Neon PostgreSQL

---

📂 Project Structure

AudioPilot
│
├── client
│   ├── src
│   │   ├── components
│   │   ├── context
│   │   ├── hooks
│   │   ├── pages
│   │   ├── routes
│   │   ├── services
│   │   └── utils
│   │
│   ├── App.jsx
│   └── main.jsx
│
├── server
│   ├── app
│   │   ├── core
│   │   ├── db
│   │   ├── routes
│   │   ├── schemas
│   │   └── services
│   │
│   ├── requirements.txt
│   └── runtime.txt
│
└── README.md

---

📸 Screenshots

Home Page	Analyze Audio	AI Report
Analysis History	Settings	Login

---

⚙️ Environment Variables

Backend

SECRET_KEY=

GROQ_API_KEY=

DATABASE_URL=

FRONTEND_URL=

ACCESS_TOKEN_EXPIRE_DAYS=7

Frontend

VITE_API_BASE_URL=

---

💻 Local Setup

Clone Repository

git clone https://github.com/dyson-025/AudioPilot.git

cd AudioPilot

Frontend

cd client

npm install

npm run dev

Backend

cd server

pip install -r requirements.txt

uvicorn app.main:app --reload

---

🎯 Future Improvements

• Agentic AI Audio Coach
• Speaker Identification
• Sentiment Analysis
• Audio Comparison Reports
• Real-Time Audio Analysis
• Team Collaboration

---

👨‍💻 Author

Aditya Aryan

Built with React, FastAPI, PostgreSQL, Groq, and countless debugging sessions ☕🔥