Recipes
Recipes are reference integrations between Teler and popular AI voice
providers. Each one is a runnable repo (clone, set environment variables,
docker compose up) and ships with both a Python and a Node variant
(except where noted).
Realtime model providers
Section titled “Realtime model providers”A single WebSocket handles STT, LLM, and TTS, with configurable components
Voice agent platforms
Section titled “Voice agent platforms”End-to-end agent platforms that handle conversation logic on their side. Lowest latency, fastest path to a working agent.
Common shape
Section titled “Common shape”Every WebSocket-based bridge follows the same pattern. Once you’ve run one, you’ve run them all.
git clone https://github.com/frejun-tech/teler-<provider>-bridgecd teler-<provider>-bridgecp .env.example .env# fill TELER_API_KEY, NGROK_AUTHTOKEN, and the provider's API keydocker compose up --build
# in another shellcurl -X POST http://localhost:8000/api/v1/calls/initiate-call \ -H "Content-Type: application/json" \ -d '{"from_number":"+91...","to_number":"+91..."}'Standard environment variables across all bridges:
| Variable | Required | Purpose |
|---|---|---|
TELER_API_KEY | yes | Your Teler API key from the dashboard |
NGROK_AUTHTOKEN | yes (local) | Tunnel for receiving Teler webhooks during dev |
SERVER_DOMAIN | auto | Public URL exposed to Teler, set by ngrok |
<PROVIDER>_API_KEY | yes | Provider-specific credential, see each recipe |
Build your own
Section titled “Build your own”The bridges are intentionally small. If your provider isn’t listed:
- Fork the closest recipe (Deepgram for Voice Agent pipeline, Sarvam for realtime models, ElevenLabs for agent platforms).
- Replace the provider WebSocket logic.
- Adjust the sample-rate conversion if needed.
Or build from scratch using the SDKs: the StreamConnector primitive
is exactly the abstraction the bridges use under the hood.