A reference integration between Teler and OpenAI Realtime API, based on media streaming over WebSockets.

Teler is a programmable voice API by FreJun. It handles carriers, phone numbers, and real-time audio streaming so you can connect AI models directly to phone calls. → frejun.ai

This project is a reference implementation to bridge Teler and OpenAI Realtime API. It enables real-time media streaming over WebSockets, facilitating live audio interactions.

• Real-time streaming of media via WebSockets
• Bi-directional communication between Teler client and OpenAI Realtime API
• Sample structure for deployment (Docker, environment variables)
• Basic error handling and connection management
• Converts OpenAI 24kHz audio to Teler 8kHz

Ensure you have the following installed / available:

• Python 3.x
• Docker & Docker Compose
• Valid API credentials / access:
  • Teler account / API key / endpoints (frejun account)
  • OpenAI API access

1. Clone and configure:

   git clone https://github.com/frejun-tech/teler-openai-bridge.git
   cd teler-openai-bridge
   cp .env.example .env
   # Edit .env with your actual values

2. Run with Docker:

   docker compose up -d --build

• GET / - Health check with server domain
• GET /health - Service status
• GET /ngrok-status - Current ngrok status and URL
• POST /api/v1/calls/initiate-call - Start a new call with dynamic phone numbers
• POST /api/v1/calls/flow - Get call flow configuration
• WebSocket /api/v1/calls/media-stream - Audio streaming between teler and openai
• POST /api/v1/webhooks/receiver - Teler → OpenAI webhook receiver

curl -X POST "http://localhost:8000/api/v1/calls/initiate-call" \
  -H "Content-Type: application/json" \
  -d '{
    "from_number": "+1234567890",
    "to_number": "+0987654321"
  }'