Skip to main content
@komaa/elevenlabs-msteams-bridge brings a hosted ElevenLabs agent (STT + LLM + TTS + turn-taking, all run by ElevenLabs) onto a Microsoft Teams call. It is the ElevenLabs analogue of the OpenClaw and Hermes plugins: it hosts the HMAC WebSocket that StandIn connects to, then relays audio to and from an ElevenLabs Agent conversation.
Unlike the OpenClaw and Hermes plugins, this is a standalone Node service, not a framework plugin. You do not install it into an agent runtime - you run the bridge and point StandIn at it. ElevenLabs hosts the agent itself.
Prefer Python? The same bridge exists as a Python package: elevenlabs-msteams-bridge on PyPI (pip install elevenlabs-msteams-bridge), with its own docs site and repo. Same wire protocol, same environment variables, same hardening - pick the runtime that fits your stack. This page follows the Node package.

​
How it works

Audio is relayed verbatim - both sides speak base64 PCM 16 kHz, so there is no transcoding on the call path. The bridge opens one ElevenLabs Agent WebSocket per call (wss://api.elevenlabs.io/v1/convai/conversation), mints a short-lived signed URL for private agents, maps caller barge-in to ElevenLabs interruptions, and injects caller context.
ElevenLabs agent conversations are realtime WebSocket connections (one socket per call), not webhooks. ElevenLabs post-call webhooks are a separate, optional feature for pushing a transcript or analysis to your own server after a call ends - unrelated to the live audio path, and not required by the bridge.

​
Requirements

  • Node.js >= 20.
  • An ElevenLabs agent (Agents dashboard) with its audio input and output format set to PCM 16000 Hz, plus an API key.
  • A StandIn subscription (standin.komaa.com, free package works) - the hosted media bridge that joins the Teams call and connects to this service. See Architecture.
  • Your own Microsoft Teams bot connected to StandIn - the Teams setup walks through the Azure bot, the app package, and the upload. To try it without one, use the sandbox.

​
Run

Env-configured, no install step needed: 
ELEVENLABS_API_KEY=sk_... \
ELEVENLABS_AGENT_ID=agent_... \
WORKER_SHARED_SECRET=... \
npx @komaa/elevenlabs-msteams-bridge
Or add it to a project (npm i @komaa/elevenlabs-msteams-bridge) and embed it - see the library API for the programmatic surface and a custom vision hook. The bridge binds its media WebSocket (default ws://<host>: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: 
tailscale funnel --bg --https=8080 8080
Your Agent voice URL is then: 
wss://<machine>.<tailnet>.ts.net:8080/voice/msteams/stream

​
Connect it to StandIn

Register that URL (with a matching shared secret) on your identity in the dashboard, or use the 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 ElevenLabs 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.

Run the example, step by step

Clone examples/basic-bridge, fill in three environment variables, expose the port, connect it to StandIn, and place a call - with the vision hook explained along the way.
Next: the full configuration reference - every environment variable, the call governor, and vision. Deep protocol and library docs live on the project site.

Docs site

npm

Source