Overview
Cartesia is a real-time voice AI platform known for fast, natural-sounding speech and configurable voice agents. The bridge connects Teler call audio to your Cartesia agent and streams the agent’s spoken response back to the caller over the same connection.
At the start of each call, the bridge requests a session URL from Cartesia for your agent. It then holds two WebSockets — one to Teler and one to Cartesia — and pumps audio between them for the duration of the call.
Key Features
- Reference implementations in Python and Node — Clone
teler-cartesia-bridge(Python) orteler-cartesia-node-bridge(Node) and get a working bridge in minutes. - One-command Docker setup — Clone the repo, fill in your environment variables, and start with a single command.
- Bi-directional, real-time streaming — Caller audio flows to Cartesia and agent responses flow back to the call live, with no batching.
How to Integrate
Prerequisites
- A Cartesia account with a voice agent created
- The
agent_idof that Cartesia agent - A Cartesia API key
- A Teler account with an active API key
- One Teler phone number on your account
- An ngrok auth token (for local development)
- Docker and Docker Compose
Step 1: Clone and configure
git clone https://github.com/frejun-tech/teler-cartesia-bridge
cd teler-cartesia-bridge
cp .env.example .env
docker compose up -d --buildStep 2: Initiate a call
curl -X POST http://your-domain.com/api/v1/calls/initiate-call \
-H "Content-Type: application/json" \
-d '{
"from_number": "+91XXXXXXXXXX",
"to_number": "+91XXXXXXXXXX"
}'Integration at a Glance
| Requirements | Cartesia account with a voice agent and its agent_id, Cartesia API key, Teler account with API key and phone number, Docker + Docker Compose, ngrok auth token (local dev) |
| Setup type | Self-hosted bridge — clone the repo, configure .env, and run via Docker Compose; not dashboard-configured |
| Support | support@frejun.com, or file an issue directly on the GitHub repo for bridge-specific bugs |