LiveKit AgentsIntegrationConfigChecked against the official docs, Nov 8, 2026

A voice assistant you can talk to from your terminal

One Python file that listens, thinks and talks back, using LiveKit Agents and LiveKit Inference with only your LiveKit keys.

Open LiveKit Agents

Your keys

0 of 3 ready

Create each key on its own page, paste it below, then copy the finished lines into your project's .env file. What you paste stays in this tab. It is never sent to Wirestack or saved.

LiveKit project URLLIVEKIT_URLGet key
Your project's WebSocket URL. Run lk cloud auth, then lk app env -w to write it to .env.local.
LiveKit API keyLIVEKIT_API_KEYGet key
Project API key. lk cloud auth creates one for the CLI and lk app env -w writes it to .env.local.
LiveKit API secretLIVEKIT_API_SECRETGet key
Project API secret, written by lk app env -w. Keep it on the server, never in client code.

Save them once on your computer, and every project can use them:npx wirestack keys add livekit-agentsthennpx wirestack keys fill

Set up with one command

$npx wirestack add terminal-voice-assistant-livekit-agents-python@3

Revision 3, checked Nov 8, 2026. Installs exactly livekit-agents 1.8.11, livekit-plugins-ai-coustics 0.3.5, python-dotenv 1.2.4, creates the files and adds the key names to your .env. It shows everything first and asks before changing anything.

Adapt to my stackProShowing the original (Python). Pick your stack to see it rewritten.

Free accounts can open one adapted integration a month. Sign in to try it.

3 of 3 free copies left this month.Unlimited with Pro

What you get

A voice assistant you can talk to out loud from your terminal. It is one Python file built on LiveKit Agents: your speech goes to AssemblyAI for speech-to-text, Gemma 4 31B writes the reply, and Fish Audio S2.1 Pro speaks it back. All three models run through LiveKit Inference, so your LiveKit Cloud keys are the only keys you need. A turn detector decides when you have finished talking, and ai-coustics cleans background noise from your microphone.

Prerequisites

Python 3.10 to 3.14 (livekit-agents 1.8.11 declares requires_python >=3.10, <3.15).
A microphone and speakers.
A free LiveKit Cloud account and project at https://cloud.livekit.io (the Build plan needs no credit card).
Your project's keys in LIVEKIT_URL, LIVEKIT_API_KEY and LIVEKIT_API_SECRET. The LiveKit CLI writes them for you in step 4.
The LiveKit CLI (lk), version 2.18.8 or later according to the starter project README.

Steps

Install the LiveKit CLI:

Shell

# Windows
winget install LiveKit.LiveKitCLI

# macOS
brew install livekit-cli

# Linux
curl -sSL https://get.livekit.io/cli | bash

A voice assistant you can talk to from your terminal

Your keys

What you get

Prerequisites

Steps

Test it

Not confirmed