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

live-translate

v0.2.0

Published

Real-time English ↔ Mandarin speech translator. Local-first, cloud-optional.

Readme

waxberry

Real-time English ↔ Mandarin speech translator. Local-first, cloud-optional. Your voice never leaves your machine.

Install

npm install -g waxberry

Quick start

waxberry doctor    # 1. check prerequisites
waxberry config    # 2. choose a provider
waxberry start     # 3. start the backend
waxberry           # 4. start translating (hold SPACE)

Provider comparison

| Provider | Quality | Speed | Cost | Privacy | Needs | |----------|---------|-------|------|---------|-------| | Opus-MT | ★★ | ★★★★★ | Free | Fully local | Nothing | | Ollama | ★★★★ | ★★★ | Free | Fully local | Ollama installed | | Claude Haiku | ★★★★ | ★★★★ | ~$0.001/use | Text via API | API key | | Claude Sonnet | ★★★★★ | ★★★ | ~$0.01/use | Text via API | API key | | GPT-4o-mini | ★★★★ | ★★★★ | ~$0.001/use | Text via API | API key | | DeepSeek | ★★★★ | ★★★ | ~$0.0005/use | Text via API | API key |

Privacy model: ASR (speech-to-text) and TTS (text-to-speech) always run locally. Only the translated text is sent to a cloud API when using a cloud provider. Your audio never leaves your machine.

Commands

waxberry doctor
  Check Node.js, Docker, Sox, microphone, speaker, and configured provider.

waxberry config
  Interactive provider setup. Saves to ~/.waxberry/config.json.

waxberry config --provider anthropic --model claude-haiku-4-5-20241022 --api-key sk-ant-...
  Non-interactive setup for scripting.

waxberry start
  Start the Docker backend. On first run, downloads ~850 MB of models.

waxberry
  Push-to-talk translation mode. Press SPACE to start/stop recording. Q to quit.

waxberry status
  Show health of all services and active provider.

waxberry stop
  Stop the Docker backend.

Privacy

Mic → ASR (local) → text → [Cloud API if configured] → text → TTS (local) → Speaker
                              ↑ only this step is cloud
  • Opus-MT and Ollama: fully local, nothing leaves your machine.
  • Anthropic, OpenAI, DeepSeek: audio stays local; only translated text is sent.

Prerequisites

  • Node.js 18+
  • Docker (with Docker Compose v2)
  • Soxbrew install sox or apt install sox

Troubleshooting

waxberry: command not found — make sure npm global bin is on your PATH: npm config get prefix/bin.

Sox not found — install with brew install sox (macOS) or apt install sox (Ubuntu).

No microphone detected — check system permissions for terminal microphone access.

Services timeout on start — first run downloads ~850 MB of models. Allow up to 10 minutes.

Ollama model not pulledwaxberry start will offer to pull it automatically, or run ollama pull qwen2.5:7b manually.

License

MIT