Oct 7, 2025
Building voice AI agents is tricky. There’s lots to remember: even when developing locally with a tool like Layercode, you need to remember to run a tunnel and add the correct URL to your dashboard so Layercode can send webhooks.
This was annoying us, so we built Layercode CLI — a command-line interface designed to help you get started in minutes.
What you get with Layercode CLI:
Zero to production in minutes: Initialize a voice AI agent with one command, and get real-time speech-to-text (STT), text-to-speech (TTS), turn-taking, and low-latency audio delivery to our global edge network. No infrastructure setup required.
Built-in tunnelling: Test locally using our integrated tunnel — no need for copy-pasting your webhook urls into our dashboard.
Sample agent backend: Backend logic receives conversation transcripts and responds based on your prompt and the tool calls you define. Deployable anywhere.
Complete backend control: Use any LLM, and keep your existing agent logic and tools — Layercode handles all of the voice infrastructure.
Edge-native voice AI deployment: Layercode is deployed to 330+ locations that process audio within ~50ms of users, anywhere in the world.
See it in action:
How to get started:
First, run with:
Then, authenticate with your Layercode account.
Choose a template, and our CLI sets up your tunnel and webhook URLs for local development.
We also have a tunnel command that works for existing agents:
So, no need to run ngrok and copy-paste the URL to your dashboard just to test locally.
And there is an AGENTS.md and CLAUDE.md file in the repo with all the Layercode documentation so you can get up to speed faster with Cursor, Claude Code or your AI tools of choice.
If you haven’t already, sign up for a free Developer account and start building with $100 credits (enough for ~1,000 minutes of agent conversation).
