A reference integration between Teler and openai in Node, based on Media Streaming Bridge 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

1. Clone and configure:

   git clone https://github.com/frejun-tech/teler-openai-node-bridge.git
   cd teler-openai-node-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 /media-stream - Audio streaming
• POST /api/v1/webhooks/receiver - Teler webhook receiver

curl -X POST "https://your_ngrok_domain/api/v1/calls/initiate-call" \
  -H "Content-Type: application/json" \
  -d '{
    "from_number": "+918064xxx",
    "to_number": "+919967xxx"
  }'

• Bi-directional media streaming - Bridges audio between Teler and openai (Voice API) over WebSockets.
• Real-time audio handling - Receives live audio chunks from Teler, processes them, and forwards to openai; streams responses back to Teler.
• Dockerized setup - Comes with Dockerfile and docker-compose.yaml for easy local development and deployment.
• Dynamic ngrok URL detection - Automatically detects current ngrok domain