synapsr/vexa-dashboard repository overview

⁠Vexa Dashboard

100% open source web interface for Vexa⁠ - the self-hosted meeting transcription API.

🔒 Own your data. Self-host everything. No cloud dependencies.

⁠🚀 Deploy in Seconds

docker run -p 3000:3000 \
  -e VEXA_API_URL=http://your-vexa-instance:18056 \
  -e VEXA_ADMIN_API_KEY=your_admin_api_key \
  synapsr/vexa-dashboard

That's it! Open http://localhost:3000⁠ and start transcribing meetings.

⁠✨ Features

• 🎯 Join Meetings - Send transcription bots to Google Meet and Microsoft Teams
• 📝 View Transcripts - Browse and search through meeting transcriptions
• ⚡ Real-time - Watch live transcriptions via WebSocket
• 🤖 AI Assistant - Chat with your transcripts (OpenAI, Anthropic, Groq, Ollama)
• 📤 Export - Download in TXT, JSON, SRT, or VTT formats
• 👥 User Management - Admin dashboard for users and API tokens
• 🌙 Dark Mode - System-aware theme switching
• 📱 Responsive - Works on all devices

⁠Screenshots

Coming soon

⁠🐳 Docker Deployment

⁠Quick Start (Recommended)

Pull and run the pre-built image:

docker run -p 3000:3000 \
  -e VEXA_API_URL=http://your-vexa-instance:18056 \
  -e VEXA_ADMIN_API_KEY=your_admin_api_key \
  synapsr/vexa-dashboard

⁠With AI Assistant

Add AI-powered transcript analysis:

docker run -p 3000:3000 \
  -e VEXA_API_URL=http://your-vexa-instance:18056 \
  -e VEXA_ADMIN_API_KEY=your_admin_api_key \
  -e AI_MODEL=openai/gpt-4o \
  -e AI_API_KEY=sk-your-openai-key \
  synapsr/vexa-dashboard

⁠With Email Authentication

Enable Magic Link login with SMTP:

docker run -p 3000:3000 \
  -e VEXA_API_URL=http://your-vexa-instance:18056 \
  -e VEXA_ADMIN_API_KEY=your_admin_api_key \
  -e SMTP_HOST=smtp.resend.com \
  -e SMTP_PORT=587 \
  -e SMTP_USER=resend \
  -e SMTP_PASS=your_smtp_key \
  -e [email protected] \
  synapsr/vexa-dashboard

⁠Docker Compose

services:
  vexa-dashboard:
    image: synapsr/vexa-dashboard
    ports:
      - "3000:3000"
    environment:
      - VEXA_API_URL=http://vexa-api:18056
      - VEXA_ADMIN_API_KEY=${VEXA_ADMIN_API_KEY}
    restart: unless-stopped

⁠🛠️ Configuration

⁠Required Variables

⁠Optional Variables

⁠AI Providers

# OpenAI
AI_MODEL=openai/gpt-4o

# Anthropic Claude
AI_MODEL=anthropic/claude-sonnet-4-20250514

# Groq (fast & free)
AI_MODEL=groq/llama-3.3-70b-versatile

# Local Ollama
AI_MODEL=ollama/llama3.2
AI_BASE_URL=http://localhost:11434/v1

⁠🔐 Authentication Modes

⁠Direct Login (Default)

Without SMTP configured, users authenticate with just their email (no verification). Great for development and trusted environments.

⁠Magic Link (with SMTP)

With SMTP configured, users receive a secure sign-in link via email. Recommended for production.

⁠💻 Local Development

# Clone
git clone https://github.com/Vexa-ai/vexa-dashboard.git
cd vexa-dashboard

# Install
npm install

# Configure
cp .env.example .env.local
# Edit .env.local with your values

# Run
npm run dev

⁠🏗️ Build from Source

# Build image
docker build -t vexa-dashboard .

# Run
docker run -p 3000:3000 \
  -e VEXA_API_URL=http://your-vexa-instance:18056 \
  -e VEXA_ADMIN_API_KEY=your_admin_api_key \
  vexa-dashboard

⁠Tech Stack

• Framework: Next.js 16 (App Router)
• UI: shadcn/ui + Tailwind CSS
• State: Zustand
• Language: TypeScript
• AI: Vercel AI SDK

⁠Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

⁠License

Apache License 2.0 - see LICENSE⁠ for details.

⁠Related Projects

• Vexa⁠ - Self-hosted meeting transcription API