# Project export: Vocal AI
This document was generated by HackStack to give an AI agent context about a hackathon project. Sections are labeled with their provenance; content marked as truncated was cut to keep this document small.
## Project metadata
- Hackathon: UC Berkeley AI Hackathon 2025
- Tagline: Revolutionary AI vocal coach with real-time voice analysis, personalized lessons, and 24/7 conversational coaching. Professional training made accessible for singers, speakers & voice actors globally.
- Devpost: https://devpost.com/software/vocai-ai-coach
- GitHub: https://github.com/ramizik/berkley-hack
- Demo: https://prismatic-buttercream-5f0d5a.netlify.app/
- Video: https://www.youtube.com/embed/4XWiMuE9wwM?enablejsapi=1&hl=en_US&rel=0&start=&version=3&wmode=transparent
- Result: winner (Vapi: Most Ambitious Vapi Project)
- Team: 4 GitHub contributor(s) — Ramis H. (72 commits), BLTA (35 commits), Rohan Jagdish Tilwani (5 commits), Bexs (2 commits)
## Devpost submission (written by the team)
### Overview
Author: Vocal Coach AI Team Repository: Berkeley Hack 2025 Overview This project is a comprehensive AI-powered vocal coaching system built for the Berkeley Hackathon 2025. The application provides a full-stack solution for personalized vocal training, combining real-time voice analysis, intelligent coaching, and conversational AI agents to create a holistic vocal development experience. VocalAIAgent solves the problem of fragmented vocal training by combining multiple functionalities into one intuitive and multimodal assistant. This AI-powered system simplifies vocal coaching by: Understanding natural voice patterns and interpreting audio recordings to gather vocal characteristics Providing personalized recommendations based on vocal analysis and user preferences Fetching real-time data for vocal metrics, progress tracking, and performance insights Generating dynamic lesson plans tailored to the user's vocal type, skill level, and practice goals Offering intelligent coaching conversations grounded in real-time voice analysis data VocalAIAgent is not just an LLM chatbot. The agent is enhanced with numerous AI capabilities, including: Voice Understanding: Real-time pitch detection, vocal analysis with metrics like jitter, shimmer, vibrato rate Retrieval-Augmented Generation (RAG): Providing personalized coaching tips by retrieving relevant vocal techniques from a knowledge base Few-Shot Prompting: Generating dynamic lesson plans and exercises based on minimal user input Function Calling: Executing specific functions based on user commands, such as starting voice sessions, analyzing recordings, or generating progress reports Long Context Window: Managing and retaining user vocal profiles and practice history across multiple sessions Context Caching: Storing relevant vocal data temporarily to improve response speed and reduce redundant analysis AI Evaluation: Using LLM-based evaluation to assess vocal progress and provide "Vocal Scores" based on improvement and consistency Grounding: Ensuring that coaching recommendations are grounded in real-time vocal analysis data Embeddings: Utilizing embeddings for effective vocal pattern matching and personalized exercise recommendations Multimodal Integration: Understanding both voice inputs and conversational text for comprehensive coaching Problem Statement Vocal training can be an isolated and inconsistent process. Singers and speakers often struggle with: Lack of real-time feedback during practice sessions Limited access to personalized coaching based on their specific vocal characteristics Difficulty tracking progress and identifying improvement areas Fragmented resources across multiple platforms and tools Inconsistent practice routines without proper guidance VocalAIAgent addresses these challenges by providing a unified, intelligent coaching platform that combines voice analysis, personalized AI coaching, and comprehensive progress tracking in one seamless experience. 🚀 Key Features Core Vocal Analysis 🎵 Real-Time Pitch Detection: Instant feedback during practice sessions with live pitch visualization 📊 Deep Vocal Analysis: Advanced metrics including jitter, shimmer, vibrato rate, vocal range analysis 🎯 Voice Type Classification: Automatic classification of voice types (soprano, alto, tenor, bass) 📈 Progress Tracking: Comprehensive tracking of vocal improvements over time AI-Powered Coaching System 🤖 Dual-AI Architecture: Proactive Fetch.ai Agent + Reactive Letta Conversational Agent 💬 Stateful Conversations: AI coach that remembers context and discusses specific progress 📋 Personalized Lesson Plans: Dynamic lesson generation based on vocal analysis and user goals 🎓 Exercise Recommendations: Tailored vocal exercises based on analysis results Advanced Features 🗣️ VAPI Voice Integration: Real-time voice conversations with AI coach 📱 Multimodal Interface: Support for voice input, text chat, and visual feedback 🔄 Lesson Feedback Loop: Comprehensive storage and analysis of lesson completion data 📊 AI-Generated Reports: Daily summaries of performance trends and insights 🎪 Community Features: Progress sharing and vocal challenges Data & Memory Management 💾 Persistent Memory: User preferences, vocal characteristics, and practice history retention 📤 Export Capabilities: Save vocal analyses, lesson plans, and progress reports 🔐 Secure Data Storage: Supabase integration with proper authentication and RLS 📋 Session Management: Comprehensive tracking of practice sessions and improvements Why This Matters Vocal training today lacks the personalized, data-driven approach that modern AI can provide. VocalAIAgent brings together voice science, conversational AI, and personalized coaching into one intelligent system, offering a more effective, engaging, and accessible vocal training experience. By combining real-time voice analysis, stateful AI conversations, and comprehensive progress tracking, this tool showcases the potential of Generative AI in revolutionizing music education and vocal development. 🛠 Tech Stack Frontend React: Modern component-based UI framework TypeScript: Type-safe development with enhanced IDE support Vite: Fast build tool and development server Tailwind CSS: Utility-first CSS framework for responsive design Framer Motion: Smooth animations and transitions Backend FastAPI: High-performance Python web framework with automatic API docs Python: Core backend language with extensive AI/ML libraries Uvicorn: ASGI server for production deployment AI Services Letta: Stateful conversational AI with long-term memory capabilities Fetch.ai: Autonomous agent system for proactive analysis and reporting VAPI: Voice AI platform for real-time voice conversations Database & Authentication Supabase: PostgreSQL database with built-in authentication and real-time features Row Level Security (RLS): Secure user data isolation Voice Processing Web Audio API: Real-time audio processing and pitch detection Custom Voice Analyzer: Advanced vocal metrics calculation Hosting & Deployment Netlify: Frontend hosting with automatic deployments Google Cloud Run: Scalable backend container hosting Docker: Containerized backend for consistent deployments How It Works Intent Recognition and Routing System VocalAIAgent uses a sophisticated routing system that directs user requests to appropriate handlers based on vocal coaching context: Vocal Analysis Pipeline The voice analysis system combines multiple AI techniques: Real-time Processing: Web Audio API captures and processes audio in real-time Feature Extraction: Advanced algorithms extract vocal characteristics (pitch, formants, etc.) AI Classification: Machine learning models classify voice type and detect patterns Contextual Analysis: Results are interpreted within the user's vocal development context Dual-AI Architecture Proactive Fetch.ai Agent Reactive Letta Conversational Agent Session Management and Memory VocalAIAgent maintains comprehensive session state and user memory: Current Capabilities Demonstrated ✅ Voice Analysis & Processing Real-time pitch detection with Web Audio API Advanced vocal metrics (jitter, shimmer, vibrato) Voice type classification and range analysis Session recording and playback capabilities ✅ AI-Powered Coaching Fetch.ai autonomous agents for progress analysis Letta conversational AI with stateful memory VAPI real-time voice conversations Personalized lesson and exercise generation ✅ Data Management & Persistence Comprehensive user vocal profiles Session history and progress tracking Lesson feedback storage and retrieval Secure multi-user data isolation ✅ User Experience Features Modern, responsive React interface Real-time visual feedback during voice sessions Progress dashboards and analytics Community features and challenges Current Errors and Solutions Issues Identified: URL Construction Error: Double slash in API endpoints causing malformed URLs Database Connection Issues: Lesson feedback storage failing due to Supabase credential problems Error Handling: Generic error messages making debugging difficult Solutions Implemented: Fixed URL Construction: Added trailing slash removal in frontend API calls Enhanced Error Logging: Improved backend error reporting with detailed messages Database Health Checks: Added endpoints to verify service connectivity Limitations & Future Work Current Limitations: Voice Processing Accuracy: Browser-based analysis has limitations compared to specialized hardware AI Model Training: Limited training data for vocal coaching specific AI models Scalability: Current architecture needs optimization for large-scale deployment Future Enhancements: High Priority: Enhanced Voice Processing: Integrate professional-grade voice analysis libraries Advanced AI Models: Fine-tune models specifically for vocal coaching contexts Mobile Applications: Native iOS/Android apps with enhanced voice processing Medium Priority: Social Features: Enhanced community aspects with vocal challenges and peer learning Integration Ecosystem: Connect with music learning platforms and DAWs Offline Capabilities: Voice analysis and basic coaching without internet connection Built With Core Technologies React 18 with TypeScript for modern, type-safe frontend development FastAPI for high-performance Python backend with automatic API documentation Supabase for PostgreSQL database, authentication, and real-time features Tailwind CSS for responsive, utility-first styling AI & Voice Technologies Letta for stateful conversational AI with long-term memory Fetch.ai for autonomous agent systems and proactive analysis VAPI for real-time voice AI conversations Web Audio API for browser-based voice processing DevOps & Deployment Docker for containerized backend deployment Google Cloud Run for scalable, serverless backend hosting Netlify for frontend hosting with automatic deployments VocalAIAgent demonstrates the transformative potential of AI in music education, combining cutting-edge voice processing, conversational AI, and personalized coaching to create a comprehensive vocal training platform.
## README (from the GitHub repository)
# VocalAIAgent - AI-Powered Vocal Coaching System 🎤
**Winner of "Most Ambitious Vapi Project" at UC Berkeley Hackathon 2025**
VocalAIAgent is a comprehensive AI-powered vocal coaching system that combines real-time voice analysis, intelligent coaching, and conversational AI agents to create a holistic vocal development experience. Built during the world's biggest AI in-person hackathon where over 1,200 developers competed.
YouTube Demo:
[](https://youtu.be/4XWiMuE9wwM)
## 🎯 Problem Statement
Vocal training can be an isolated and inconsistent process. Singers and speakers often struggle with:
- Lack of real-time feedback during practice sessions
- Limited access to personalized coaching based on their specific vocal characteristics
- Difficulty tracking progress and identifying improvement areas
- Fragmented resources across multiple platforms and tools
- Inconsistent practice routines without proper guidance
## Solution
VocalAIAgent addresses these challenges by providing a unified, intelligent coaching platform that combines voice analysis, personalized AI coaching, and comprehensive progress tracking in one seamless experience.
## 🚀 Key Features
### Core Vocal Analysis
- **🎵 Real-Time Pitch Detection**: Instant feedback during practice sessions with live pitch visualization
- **📊 Deep Vocal Analysis**: Advanced metrics including jitter, shimmer, vibrato rate, vocal range analysis
- **🎯 Voice Type Classification**: Automatic classification of voice types (soprano, alto, tenor, bass)
- **📈 Progress Tracking**: Comprehensive tracking of vocal improvements over time
### AI-Powered Coaching System
- **🤖 Dual-AI Architecture**: Proactive Fetch.ai Agent + Reactive Letta Conversational Agent
- **💬 Stateful Conversations**: AI coach that remembers context and discusses specific progress
- **📋 Personalized Lesson Plans**: Dynamic lesson generation based on vocal analysis and user goals
- **🎓 Exercise Recommendations**: Tailored vocal exercises based on analysis results
### Advanced Features
- **🗣️ VAPI Voice Integration**: Real-time voice conversations with AI coach
- **📱 Multimodal Interface**: Support for voice input, text chat, and visual feedback
- **🔄 Lesson Feedback Loop**: Comprehensive storage and analysis of lesson completion data
- **📊 AI-Generated Reports**: Daily summaries of performance trends and insights
- **�� Community Features**: Progress sharing and vocal challenges
### Data & Memory Management
- **💾 Persistent Memory**: User preferences, vocal characteristics, and practice history retention
- **📤 Export Capabilities**: Save vocal analyses, lesson plans, and progress reports
- **🔐 Secure Data Storage**: Supabase integration with proper authentication and RLS
- **�� Session Management**: Comprehensive tracking of practice sessions and improvements
## 🛠 Tech Stack
### Frontend
- **React**: Modern component-based UI framework
- **TypeScript**: Type-safe development with enhanced IDE support
- **Vite**: Fast build tool and development server
- **Tailwind CSS**: Utility-first CSS framework for responsive design
- **Framer Motion**: Smooth animations and transitions
### Backend
- **FastAPI**: High-performance Python web framework with automatic API docs
- **Python**: Core backend language with extensive AI/ML libraries
- **Uvicorn**: ASGI server for production deployment
### AI Services
- **Letta**: Stateful conversational AI with long-term memory capabilities
- **Fetch.ai**: Autonomous agent system for proactive analysis and reporting
- **VAPI**: Voice AI platform for real-time voice conversations
### Database & Authentication
- **Supabase**: PostgreSQL database with built-in authentication and real-time features
- **Row Level Security (RLS)**: Secure user data isolation
### Voice Processing
- **Web Audio API**: Real-time audio processing and pitch detection
- **Custom Voice Analyzer**: Advanced vocal metrics calculation
### Hosting & Deployment
- **Netlify**: Frontend hosting with automatic deployments
- **Google Cloud Run**: Scalable backend container hosting
- **Docker**: Containerized backend for consistent deployments
## 🚀 Getting Started
### Prerequisites
- Node.js (v18 or higher)
- Python (v3.8 or higher)
- Docker (for backend deployment)
### Frontend Setup
```bash
cd src
npm install
npm run dev
```
### Backend Setup
```bash
cd backend
pip install -r requirements.txt
uvicorn main:app --reload
```
### Environment Variables
Create `.env` files in both frontend and backend directories with the necessary API keys and configuration.
## Why This Matters
Vocal training today lacks the personalized, data-driven approach that modern AI can provide. VocalAIAgent brings together voice science, conversational AI, and personalized coaching into one intelligent system, offering a more effective, engaging, and accessible vocal training experience.
By combining real-time voice analysis, stateful AI conversations, and comprehensive progress tracking, this tool showcases the potential of Generative AI in revolutionizing music education and vocal development.
## Live Demo
https://prismatic-buttercream-5f0d5a.netlify.app/
---
**Built with ❤️ at UC Berkeley Hackathon 2025**
## Detected evidence (automated analysis)
Indexed codebase: 65 recognized source files, 613 KB.
- CSS (language) — detected in the code
- FastAPI (technology) — detected in the code
- HTML (language) — detected in the code
- JavaScript (language) — detected in the code
- Python (language) — detected in the code
- React (technology) — detected in the code
- Supabase (technology) — detected in the code
- Tailwind CSS (technology) — detected in the code
- TypeScript (language) — detected in the code
- Docker (technology) — claimed on Devpost, not found in the code
## Codebase structure (from repository index)
### Files (79 of 79)
```
.bolt/prompt
.gitignore
backend/.dockerignore
backend/cloudbuild.yaml
backend/DEPLOYMENT.md
backend/Dockerfile
backend/enhanced_api_endpoints.py
backend/enhanced_letta_service.py
backend/fetch_ai_agent.py
backend/fetch_ai_service.py
backend/lesson_feedback_service.py
backend/letta_service.py
backend/main.py
backend/pyproject.toml
backend/README.md
backend/requirements-build.txt
backend/requirements.txt
backend/start.bat
backend/start.sh
backend/test_api.py
backend/test_build.py
backend/test_fetch_ai.py
backend/test_groq_fix.py
backend/test_letta_integration.py
backend/test_letta_progress.py
backend/test_requirements.py
backend/voice_analyzer.py
eslint.config.js
index.html
netlify.toml
package.json
postcss.config.js
README.md
src/App.tsx
src/components/animations/ParticleBackground.tsx
src/components/auth/AuthPage.tsx
src/components/auth/LoginForm.tsx
src/components/auth/ProtectedRoute.tsx
src/components/auth/SignupForm.tsx
src/components/dashboard/AchievementCard.tsx
src/components/dashboard/PracticeReminder.tsx
src/components/dashboard/RecommendedLessons.tsx
src/components/dashboard/UpcomingChallenges.tsx
src/components/dashboard/VocalStats.tsx
src/components/layout/Header.tsx
src/components/layout/Sidebar.tsx
src/components/layout/TopNav.tsx
src/components/letta/EnhancedLettaWidget.tsx
src/components/letta/LettaChat.tsx
src/components/practice/FeedbackModal.tsx
src/components/practice/LyricsRequest.tsx
src/components/shared/Card.tsx
src/components/shared/LettaIntegration.tsx
src/components/shared/UniversalLettaChat.tsx
src/components/vapi/VapiIntegration.tsx
src/context/AuthContext.tsx
src/context/VocalProfileContext.tsx
src/index.css
src/lib/supabase.ts
src/lib/useVoiceAnalysis.ts
src/lib/vapiClient.ts
src/main.tsx
src/pages/Dashboard.tsx
src/pages/Introduction.tsx
src/pages/Lessons.tsx
src/pages/LiveCoach.tsx
src/pages/Onboarding.tsx
src/pages/Practice.tsx
src/pages/Progress.tsx
src/pages/VoiceAssistant.tsx
src/services/LettaService.ts
src/types/auth.ts
src/vite-env.d.ts
tailwind.config.js
tsconfig.app.json
tsconfig.json
tsconfig.node.json
vite.config.ts
vite.config.ts.timestamp-1750614102589-a57076fb2b213.mjs
```
### Dependencies
- backend/requirements.txt: fastapi@>=0.100.0, groq@>=0.25.0,<0.29.0, gunicorn@==21.2.0, httpx@>=0.24.0,<1.0.0, letta-client@>=0.1.167, librosa@==0.10.1, matplotlib@==3.7.2, numpy@==1.24.3, pandas@==2.0.3, pydantic@>=2.0.0,<3.0.0, pydub@==0.25.1, python-dateutil@>=2.8.0, python-dotenv@==1.0.0, python-json-logger@==2.0.7, python-multipart@==0.0.6, pytz, requests@==2.31.0, scikit-learn@>=1.3.0, scipy@==1.11.4, soundfile@==0.12.1, supabase@>=2.3.0, uvicorn[standard]@>=0.23.0
- package.json: @supabase/supabase-js@^2.39.0, @types/react@^18.3.23, @types/react-dom@^18.3.7, @vapi-ai/web@^1.4.0, @vitejs/plugin-react@^4.0.3, autoprefixer@^10.4.17, framer-motion@^11.0.5, lucide-react@^0.344.0, pitchy@^4.1.0, postcss@^8.4.35, react@^18.3.1, react-dom@^18.3.1, react-particles@^2.12.2, react-router-dom@^6.22.3, tailwindcss@^3.4.1, tsparticles@^2.12.0, tsparticles-engine@^2.12.0, tsparticles-slim@^2.12.0, typescript@^5.0.2, vite@^4.4.5
### Recent commits (newest first)
- style: normalize trailing whitespace and line endings in backend services
- refactor: restructure application startup and initialization in main.py
- refactor: combine coaching recommendation functions into VocalCoachingAdvisor class
- refactor: extract Letta agent creation into helper method
- Update README with YouTube demo and project details
- Updated Progress.tsx
- Updated LiveCoach.tsx
- Updated Progress.tsx
- Remove report status indicator from Progress page
- Remove redundant Practice Session Details card
- Updated Lessons.tsx
- Updated Lessons.tsx
- Updated Lessons.tsx
- Updated Introduction.tsx
- Enhance Practice Session Details card
- Updated LiveCoach.tsx
- Updated LiveCoach.tsx
- Updated LiveCoach.tsx
- Updated LiveCoach.tsx
- Updated LiveCoach.tsx
## Key source files (fetched from GitHub, selected and truncated for size)
### backend/DEPLOYMENT.md
```markdown
# 🚀 Deployment Guide - Vocal Coach AI Backend
This guide will help you deploy your FastAPI backend to Google Cloud Run and connect it to your React frontend.
## 📋 Prerequisites
1. **Google Cloud Account**: Set up a Google Cloud Platform account
2. **Google Cloud SDK**: Install the [Google Cloud SDK](https://cloud.google.com/sdk/docs/install)
3. **Docker**: Install [Docker](https://docs.docker.com/get-docker/) for local testing
4. **GitHub Repository**: Your code should be in a GitHub repository
## 🛠️ Local Development Setup
### 1. Test Backend Locally
```bash
# Navigate to backend directory
cd backend
# Create virtual environment
python -m venv venv
# Activate virtual environment
# Windows:
venv\Scripts\activate
# macOS/Linux:
source venv/bin/activate
# Install dependencies
pip install -r requirements.txt
# Run the server
python main.py
```
### 2. Test API Endpoints
```bash
# Test health endpoint
curl http://localhost:8080/health
# Run the test script
python test_api.py
```
### 3. Test with Docker
```bash
# Build Docker image
docker build -t vocal-coach-ai-api .
# Run container
docker run -p 8080:8080 vocal-coach-ai-api
# Test in another terminal
curl http://localhost:8080/health
```
## 🚀 Quick Deployment to Google Cloud Run
### Prerequisites
- Google Cloud Project with billing enabled
- Google Cloud CLI installed and configured
- Docker installed locally (for testing)
### 1. Environment Variables Setup
You need to set these environment variables in Google Cloud Run:
#### Required Variables:
```bash
# Supabase Configuration
SUPABASE_URL=your_supabase_project_url
SUPABASE_SERVICE_ROLE_KEY=your_supabase_service_role_key
# Fetch AI Configuration
ASI_1_API_KEY=your_asi_1_api_key # Get from https://asi1.ai/
# Letta Configuration
LETTA_API_KEY=your_letta_api_key # Get from https://app.letta.com/api-keys
LETTA_AGENT_ID=your_letta_agent_id # Get from https://app.letta.com
# Frontend Configuration (Set in Netlify)
VITE_FASTAPI_URL=https://your-cloud-run-service-url
```
#### How to Get API Keys:
1. **Fetch AI**: Visit [https://asi1.ai/](https://asi1.ai/), sign up, and create an API key
2. **Letta**: Visit [https://app.letta.com/api-keys](https://app.letta.com/api-keys), create an account, and generate an API key
### 2. Deploy to Google Cloud Run
#### Option A: Using Cloud Build (Recommended)
```bash
# Navigate to backend directory
cd backend
# Deploy using Cloud Build
gcloud builds submit --config cloudbuild.yaml
```
#### Option B: Manual Deployment
```bash
# Build and push Docker image
docker build -t gcr.io/YOUR_PROJECT_ID/vocal-coach-ai-api .
docker push gcr.io/YOUR_PROJECT_ID/vocal-coach-ai-api
# Deploy to Cloud Run
gcloud run deploy vocal-coach-ai-api \
--image gcr.io/YOUR_PROJECT_ID/vocal-coach-ai-api \
--platform managed \
--region us-central1 \
--allow-unauthenticated \
--memory 512Mi \
[truncated — 6428 more characters]
```
### package.json
```
{
"scripts": {
"dev": "vite",
"build": "tsc && npx vite build",
"preview": "vite preview"
},
"dependencies": {
"@supabase/supabase-js": "^2.39.0",
"@vapi-ai/web": "^1.4.0",
"@vitejs/plugin-react": "^4.0.3",
"autoprefixer": "^10.4.17",
"framer-motion": "^11.0.5",
"lucide-react": "^0.344.0",
"pitchy": "^4.1.0",
"postcss": "^8.4.35",
"react": "^18.3.1",
"react-dom": "^18.3.1",
"react-particles": "^2.12.2",
"react-router-dom": "^6.22.3",
"tailwindcss": "^3.4.1",
"tsparticles": "^2.12.0",
"tsparticles-engine": "^2.12.0",
"tsparticles-slim": "^2.12.0",
"typescript": "^5.0.2",
"vite": "^4.4.5"
},
"devDependencies": {
"@types/react": "^18.3.23",
"@types/react-dom": "^18.3.7"
},
"overrides": {
"daily-js": "^0.67.0"
},
"type": "module"
}
```
### backend/pyproject.toml
```
[build-system]
requires = ["setuptools >= 42.0.0", "wheel"]
build-backend = "setuptools.build_meta"
[project]
name = "vocal-coach-ai-backend"
version = "0.1.0"
description = "FastAPI backend for Vocal Coach AI application"
requires-python = ">=3.11"
```
### backend/requirements.txt
```
# FastAPI and ASGI server (Pydantic v2 compatible)
fastapi>=0.100.0
uvicorn[standard]>=0.23.0
# File handling and multipart support
python-multipart==0.0.6
# CORS support (FastAPI has built-in CORS, so we don't need fastapi-cors)
# fastapi-cors==0.0.6 # Removed - conflicts with FastAPI
# Logging and utilities
python-json-logger==2.0.7
# Audio processing and VibratoScope dependencies
numpy==1.24.3
scipy==1.11.4
librosa==0.10.1
matplotlib==3.7.2
pandas==2.0.3
soundfile==0.12.1
pydub==0.25.1
# Supabase client for database access (Pydantic v2 compatible)
supabase>=2.3.0
# Production deployment
gunicorn==21.2.0
# Environment variables
python-dotenv==1.0.0
# Pydantic v2 (required for letta-client)
pydantic>=2.0.0,<3.0.0
# HTTP requests for Fetch AI API
requests==2.31.0
# HTTP client for Groq SDK compatibility and VAPI proxy endpoints
httpx>=0.24.0,<1.0.0
# Letta AI integration (latest available version)
letta-client>=0.1.167
# Timezone support
pytz
# Groq SDK for lyrics generation (updated to latest stable version)
groq>=0.25.0,<0.29.0
# Enhanced Letta functionality
python-dateutil>=2.8.0
scikit-learn>=1.3.0
```
### backend/Dockerfile
```
# Use Python 3.11 slim image
FROM python:3.11-slim
# Set working directory
WORKDIR /app
# Accept build arguments
ARG GROQ_API_KEY
ARG LETTA_API_KEY
ARG SUPABASE_URL
ARG SUPABASE_SERVICE_ROLE_KEY
# Set environment variables from build args (for build-time tests)
ENV GROQ_API_KEY=${GROQ_API_KEY}
ENV LETTA_API_KEY=${LETTA_API_KEY}
ENV SUPABASE_URL=${SUPABASE_URL}
ENV SUPABASE_SERVICE_ROLE_KEY=${SUPABASE_SERVICE_ROLE_KEY}
# Set environment variables to force PEP 517 mode and avoid gRPC build issues
ENV PIP_USE_PEP517=true
ENV GRPC_PYTHON_BUILD_SYSTEM_OPENSSL=1
ENV GRPC_PYTHON_BUILD_WITH_CYTHON=1
# Install system dependencies for audio processing and Fetch AI
RUN apt-get update && apt-get install -y \
gcc \
g++ \
libsndfile1 \
libasound2-dev \
portaudio19-dev \
python3-dev \
curl \
git \
pkg-config \
libssl-dev \
build-essential \
&& rm -rf /var/lib/apt/lists/*
# Copy requirements files
COPY requirements-build.txt .
COPY requirements.txt .
# Install Python dependencies with specific versions for Fetch AI
# Install build dependencies first, then main dependencies
# Force clean install of Pydantic v2 for letta-client compatibility
RUN pip install --no-cache-dir --upgrade pip && \
pip install --no-cache-dir --use-pep517 -r requirements-build.txt && \
pip uninstall -y pydantic || true && \
pip install --no-cache-dir --use-pep517 -r requirements.txt
# Copy application code
COPY . .
# Create necessary directories for Fetch AI
RUN mkdir -p /app/.fetchai
# Test the build
RUN python test_build.py
# Test Groq SDK compatibility
RUN python test_groq_fix.py
# Expose port (Cloud Run will override this)
EXPOSE 8080
# Set environment variable for port (Cloud Run will provide PORT=8080)
ENV PORT=8080
# Health check
HEALTHCHECK --interval=30s --timeout=30s --start-period=5s --retries=3 \
CMD curl -f http://localhost:8080/ || exit 1
# Run the application
CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8080"]
```
### src/main.tsx
```typescript
import { StrictMode } from 'react';
import { createRoot } from 'react-dom/client';
import App from './App.tsx';
import './index.css';
createRoot(document.getElementById('root')!).render(
);
```
### src/App.tsx
```typescript
import React from 'react';
import { BrowserRouter as Router, Routes, Route } from 'react-router-dom';
import { AuthProvider } from './context/AuthContext';
import ProtectedRoute from './components/auth/ProtectedRoute';
import AuthPage from './components/auth/AuthPage';
import TopNav from './components/layout/TopNav';
import Dashboard from './pages/Dashboard';
import Lessons from './pages/Lessons';
import Practice from './pages/Practice';
import Progress from './pages/Progress';
import Onboarding from './pages/Onboarding';
import Introduction from './pages/Introduction';
import LiveCoach from './pages/LiveCoach';
import VoiceAssistant from './pages/VoiceAssistant';
import { VocalProfileProvider } from './context/VocalProfileContext';
function App() {
return (