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

talk-pi

v1.0.16

Published

Pi extension for local tools voice capture, Whisper transcription, and Piper TTS playback

Downloads

2,377

Vulnerabilities

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

Links

Git

Maintainers

castelloescastelloes

Keywords

pi-packagepitalk-pivoicetoolspush-to-talkspeech-to-texttext-to-speechwhisperpiperextension

Readme

talk-pi

Talk-Pi is Pi extension for local voice capture, Whisper transcription, and Piper TTS playback.

What it does

  • /talk-pi opens unified voice menu
  • push-to-talk records audio and sends it to Whisper
  • replies are spoken with Piper
  • voice model and output language can be selected between English and Portuguese
  • Voice Language and mute state are saved and restored on the next open
  • downloads show Talk-pi: Downloading 📥

Install

pi install npm:talk-pi

pi install brings Talk-Pi package plus bundled tools. At runtime, Talk-Pi prefers ~/.pi/agent/extensions/talk-pi when ~/.pi exists, otherwise it creates/uses local ./tools, so no PATH setup is needed.

Requirements

  • Node.js 24+
  • ~/.pi/agent/extensions/talk-pi when a user-scoped .pi folder exists, otherwise local ./tools
  • ./tools/piper/piper or ./tools/piper/piper.exe
  • voice capture uses bundled microphone support
  • Piper voice model under ./tools/piper/models/
  • Whisper model under ./tools/whisper/models/

Talk-Pi prefers ~/.pi/agent/extensions/talk-pi when available and falls back to local ./tools for fresh installs.

Setup & Configuration

  1. Copy .env.example to .env.
  2. Run pi install npm:talk-pi to bring bundled tools automatically.
  3. If ~/.pi exists, keep user-scoped tools under ~/.pi/agent/extensions/talk-pi.
  4. If ~/.pi does not exist, Talk-Pi creates and uses local ./tools in the install folder.
  5. Adjust TALK_PI_TOOLS_DIR only if the local tools/ folder lives somewhere else.

| Variable | Default / Note | | --- | --- | | TALK_PI_SEND_TRANSCRIPT_KEY | F9 | | TALK_PI_INSERT_TRANSCRIPT_KEY | F10 | | TALK_PI_TOOLS_DIR | ./tools (override) | | TALK_PI_PIPER_BIN | ./tools/piper/piper | | TALK_PI_PIPER_MODEL_PATH | ./tools/piper/models/pt_BR-faber-medium.onnx | | TALK_PI_TTS_OUTPUT_DIR | ~/.pi/agent/extensions/talk-pi/tts | | TALK_PI_WHISPER_MODEL_PATH | ./tools/whisper/models/ggml-base.bin | | TALK_PI_WHISPER_MODEL_URL | https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-base.bin | | TALK_PI_TRANSCRIBE_TIMEOUT_MS | 60000 | | TALK_PI_TRANSCRIBE_FIRST_TIMEOUT_MS | 600000 |

Usage

  1. Open /talk-pi.
  2. Choose push-to-talk.
  3. Record speech.
  4. Wait for Whisper transcription.
  5. Listen to Piper reply, or send/insert transcript as needed.

Platform notes

  • Windows, Linux, and macOS use same setup.
  • Unzip Piper into ~/.pi/agent/extensions/talk-pi/piper when using a user-scoped .pi folder, or ./tools/piper for a local install.
  • No separate recorder install needed.
  • Put voice and Whisper models under ~/.pi/agent/extensions/talk-pi/piper/models or ./tools/piper/models, and the Whisper model under the matching whisper/models folder.
  • TALK_PI_TOOLS_DIR is only needed if the tools folder lives elsewhere.

Publish

npm publish --access public