Fireside DAM - Satoshi Nakamoto AI

A character-switching conversational AI agent for fireside chat conference presentations using OpenAI's Realtime API with WebRTC. Features multiple Satoshi Nakamoto personas with automatic rotation, sound effects, and special privacy detection.

🎭 Features

Character Switching System

• 6 Unique Personas: Hal Finney, Nick Szabo, Dorian Nakamoto, Craig Wright, Jack Dorsey, and AI Satoshi
• Automatic Rotation: Characters switch every 2-4 messages or based on conversation cues
• Manual Control: Dedicated button for instant character switching
• Theatrical Effects: Visual transitions with animations and sound effects

Enhanced Audio Experience

• Real-time Voice Chat: Direct WebRTC connection to OpenAI's Realtime API
• Sound Effects: Character switch sounds, privacy alerts, and system notifications
• Voice Variety: Each persona has a unique voice (echo, ash, verse, shimmer, etc.)
• Audio Controls: Toggle sound effects on/off

Special Effects

• Privacy Detection: Visual and audio alerts when privacy topics are mentioned
• AI Satoshi Glitch: Special glitch effects for the AI Satoshi persona when privacy is discussed
• Visual Overlays: Dramatic transition effects during character switches

🚀 Quick Start

Prerequisites

• Node.js 18+
• OpenAI API key with Realtime API access

Installation

1. Clone the repository

   git clone https://github.com/stoicma/ai-satoshi.git
   cd fireside-dam

2. Install dependencies

   npm install

3. Set up environment variables

   cp .env.example .env.local

   Add your OpenAI API key to .env.local:

   OPENAI_API_KEY=your_openai_api_key_here
   

4. Start the development server

   npm run dev

5. Open your browser Navigate to http://localhost:3000

🎮 Usage

Basic Operation

1. Start Recording: Click the microphone button to begin voice chat
2. Speak Naturally: The AI will respond in character as the current persona
3. Character Switching:
   • Automatic: Characters rotate every 2-4 messages
   • Manual: Click the 👥 button to switch immediately
   • Conversation Cues: AI detects handoff phrases like "what do you think?"

Controls

• 🎤 Microphone: Start/stop voice recording
• 👥 Character Switch: Manually trigger character change
• 🔄 Auto-Rotate: Toggle automatic character switching
• 🔊 Sound Effects: Enable/disable audio effects

Personas

Hal Finney

• Voice: Echo
• Style: Technical, optimistic, clear explanations
• Background: Early Bitcoin developer, received first Bitcoin transaction

Nick Szabo

• Voice: Echo
• Style: Academic, complex terminology, historical references
• Background: Smart contracts creator, Bit Gold inventor

Dorian Nakamoto

• Voice: Ash
• Style: Confused about crypto, broken English, denies being Satoshi
• Background: Engineer mistakenly identified as Satoshi by Newsweek

Craig Wright

• Voice: Verse
• Style: Authoritative, combative, claims to be Satoshi
• Background: Australian computer scientist, Bitcoin SV advocate

Jack Dorsey

• Voice: Ash
• Style: Calm, minimalist, Bitcoin maximalist
• Background: Twitter founder, Square/Block CEO

AI Satoshi

• Voice: Shimmer
• Style: Futuristic AI claiming to be real Satoshi, glitches on privacy topics
• Background: AI from the future with regrets about Bitcoin's limitations

🛠 Technical Details

Architecture

• Frontend: Next.js 14 with React 18
• Styling: Tailwind CSS
• Audio: Web Audio API with custom sound effects
• Real-time: WebRTC connection to OpenAI Realtime API
• Voice Processing: OpenAI's gpt-4o-realtime-preview model

Key Components

• TrueRealtimeVoiceUI.tsx: Main voice interface with character switching
• PersonaSelector.tsx: Character selection component
• soundEffects.ts: Audio effects system
• personas/index.ts: Character definitions and configurations

API Routes

• /api/realtime-chat: Creates OpenAI Realtime API sessions with persona context

🔧 Configuration

Environment Variables

OPENAI_API_KEY=your_openai_api_key_here

Persona Customization

Edit src/personas/index.ts to modify:

• Character personalities and speaking styles
• Voice assignments
• Rotation durations
• System prompts

Sound Effects

Modify src/utils/soundEffects.ts to customize:

• Character switch sounds
• Privacy alert tones
• Transition effects

🎯 Use Cases

• Conference Presentations: Engaging fireside chats with dynamic character switching
• Educational Demos: Teaching about Bitcoin history through different perspectives
• Entertainment: Interactive conversations with Bitcoin personalities
• Research: Exploring different viewpoints on cryptocurrency topics

🔒 Security

• ✅ API keys stored server-side only
• ✅ No client-side secret exposure
• ✅ Environment variables properly configured
• ✅ WebRTC secure connections

📝 License

MIT License - see LICENSE file for details

🤝 Contributing

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Test thoroughly
5. Submit a pull request

🐛 Troubleshooting

Common Issues

"Module not found" errors: Ensure all dependencies are installed with npm install

API connection failures: Verify your OpenAI API key has Realtime API access

Audio not working: Check browser permissions for microphone access

Character switching not working: Ensure WebRTC connection is established (check browser console)

Debug Mode

Enable debug logging by checking the browser console for [DEBUG] messages.