> ## Documentation Index
> Fetch the complete documentation index at: https://docs.komaa.com/llms.txt
> Use this file to discover all available pages before exploring further.
# Installation
> Run cartesia-msteams-bridge and put a Cartesia Line voice agent (your agent code on Cartesia's platform) on Microsoft Teams calls through StandIn.
[`@komaa/cartesia-msteams-bridge`](https://www.npmjs.com/package/@komaa/cartesia-msteams-bridge)
brings a **Cartesia Line agent** onto a Microsoft Teams call. It is the Cartesia analogue of the
[ElevenLabs](/elevenlabs/installation), [LiveKit](/livekit/installation),
[OpenAI](/openai/installation) and [Deepgram](/deepgram/installation) bridges: it hosts the HMAC
WebSocket that StandIn connects to, then relays audio to and from a Line agent stream (Cartesia's
[WebSocket API](https://docs.cartesia.ai/line/integrations/websocket-api), the integration they
provide for bringing your own telephony).
**Where the brain lives.** A Line agent is **your code deployed on Cartesia's platform** - LLM,
tools, conversation logic, hangup. This bridge is deliberately a hardened transport: unlike the
other bridges there is no in-process tool registry or vision hook, because the Line wire has no
client-side tool channel. Your agent still receives the full Teams context (caller identity,
participants, active speaker, DTMF, recording state) as metadata and custom events - the
[contract is documented](https://komaa-com.github.io/cartesia-msteams-bridge/your-line-agent/).
**Prefer Python?** The same bridge exists as a Python package:
[`cartesia-msteams-bridge` on PyPI](https://pypi.org/project/cartesia-msteams-bridge/)
(`pip install cartesia-msteams-bridge`), with its own
[docs site](https://komaa-com.github.io/cartesia-msteams-bridge-py/) and
[repo](https://github.com/komaa-com/cartesia-msteams-bridge-py). Same wire protocol, same
environment variables, same hardening - pick the runtime that fits your stack. This page follows
the Node package.
## How it works
The bridge mints a **short-lived, agent-scoped access token per call** (the API key never rides an
agent socket), opens `wss://api.cartesia.ai/agents/stream/{agentId}`, sends the `start` event, and
relays once the server acks. Audio is **verbatim**: the StandIn wire is base64 PCM 16 kHz and the
Line stream is pinned to `pcm_16000` with base64 payloads both ways, so the hot path relays the
payload string untouched - no decode, no re-encode, no transcoding. Line's `clear` (barge-in) maps
to a Teams-side playback flush, and keypad digits ride the wire as native `dtmf` events.
## Requirements
* **Node.js `>= 20`**.
* A **Cartesia API key** and a **deployed Line agent** (its agent id) -
[docs.cartesia.ai/line](https://docs.cartesia.ai/line).
* A **StandIn** subscription ([standin.komaa.com](https://standin.komaa.com), free package works) -
the hosted media bridge that joins the Teams call and connects to this service. See
[Architecture](/concepts/architecture).
* Your own **Microsoft Teams bot** connected to StandIn - the [Teams setup](/teams/overview) walks
through the Azure bot, the app package, and the upload. To try it without one, use the
[sandbox](/community).
## Run
Env-configured, no install step needed:
```bash theme={null}
CARTESIA_API_KEY=sk_car_... \
CARTESIA_AGENT_ID=agent_... \
WORKER_SHARED_SECRET=... \
npx @komaa/cartesia-msteams-bridge
```
Optionally shape the call (your Line agent's own config is the default):
```bash theme={null}
CARTESIA_INTRODUCTION="Hello! You've reached Komaa. Quick note: I'm an AI assistant."
CARTESIA_VOICE_ID=a0e99841-438c-4a64-b679-ae501e7d6091 # voice override
```
Or add it to a project (`npm i @komaa/cartesia-msteams-bridge`) and embed it - see the
[library API](https://komaa-com.github.io/cartesia-msteams-bridge/library-api/) for the programmatic
surface, including the graceful `drain()` for embedders.
The bridge binds its media WebSocket (default `ws://:8080/voice/msteams/stream`; StandIn
appends `/{callId}` per call).
## Expose the WebSocket (Agent voice URL)
StandIn connects to the bridge **from the internet**, so the port must be reachable - a public host
or a tunnel. With Tailscale Funnel:
```bash theme={null}
tailscale funnel --bg --https=8080 8080
```
Your **Agent voice URL** is then:
```
wss://..ts.net:8080/voice/msteams/stream
```
## Connect it to StandIn
Register that URL (with a **matching shared secret**) on your identity in the
[dashboard](https://standin.komaa.com/dashboard), or use the
[sandbox](https://standin.komaa.com/sandbox) to try it without your own Teams bot:
1. Set the identity's **Agent voice URL** to where the bridge listens.
2. Set `WORKER_SHARED_SECRET` to the **shared secret from pairing** - both sides must match exactly,
or the WebSocket handshake is rejected with `401`.
3. Place a Teams call (or join the sandbox meeting). StandIn joins, connects to the bridge, and your
Line agent answers.
## Try the runnable example
The fastest way to understand the bridge is to run its example project - a minimal, working
embedding you can copy straight into your own repo.
Clone `examples/basic-bridge`, fill in three environment variables, expose the port, connect it to
StandIn, and place a call - about 20 lines of code, because the agent's brain lives in your Line
deployment.
Next: the full [configuration reference](/cartesia/configuration) - every environment variable,
the call governor, and the Sonic TTS goodbye. Deep protocol and library docs live on the
[project site](https://komaa-com.github.io/cartesia-msteams-bridge/), including
[what your Line agent receives](https://komaa-com.github.io/cartesia-msteams-bridge/your-line-agent/).
## Links