npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@settinghead/pi-voxlert

v0.2.0

Published

SHODAN, the StarCraft Adjutant, and GLaDOS narrate your pi coding sessions. LLM-generated voice notifications spoken by game characters — know which agent needs you, by ear.

Vulnerabilities

Powered byPowered by Snyk
  • 0High
  • 0Medium
  • 0Low

Links

Git

Maintainers

settingheadsettinghead

Keywords

pi-packagevoxlertvoice-notificationsttscoding-agentnotificationsaudio

Readme

pi-voxlert

SHODAN, the StarCraft Adjutant, and GLaDOS narrate your pi coding sessions.

Voice notifications for pi powered by Voxlert. When your agent finishes a task or hits an error, you hear a contextual phrase in a game character's voice — instead of silence or a generic chime.

"Awaiting further orders, Commander. Build process complete."

Install

pi install npm:@settinghead/pi-voxlert

That's it. On first session, the extension detects that the Voxlert CLI is missing and offers to install + configure it automatically:

  • Installs @settinghead/voxlert globally
  • Downloads default voice packs (SHODAN, Adjutant, Kerrigan, etc.)
  • Auto-detects your TTS backend (Qwen3-TTS on Apple Silicon, Chatterbox on CUDA)

You can also trigger setup manually anytime with /voxlert setup, or run voxlert setup in a terminal for full interactive configuration.

What it does

| pi event | Voxlert action | |----------|---------------| | Agent finishes (agent_end) | Speaks a contextual in-character phrase | | Tool error (tool_result with error) | Announces the error in character |

Phrases are generated per-event by an LLM, so you hear things like "Pathetic authentication corrected" (SHODAN) or "Warning, Commander. Test suite failure detected" (Adjutant) — not canned sounds.

Commands

| Command | Description | |---------|-------------| | /voxlert setup | Install CLI + configure with defaults | | /voxlert test | Fire a test voice notification | | /voxlert status | Check if Voxlert CLI is available | | /voxlert | Show help |

The LLM can also call the voxlert_speak tool to say something aloud on demand.

Configuration

All voice pack, TTS backend, and LLM settings are managed through the Voxlert CLI:

voxlert config           # interactive configuration
voxlert packs            # list available voice packs
voxlert test "Hello"     # test your setup

Supports local TTS (Qwen3-TTS on Apple Silicon, Chatterbox on CUDA) and multiple LLM backends (OpenRouter, OpenAI, Anthropic, Gemini).

Requirements

  • pi coding agent
  • Voxlert CLI installed and configured (npm install -g @settinghead/voxlert && voxlert setup)
  • A TTS backend running (or Voxlert falls back to text notifications)

Links