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

hermes-live

v0.1.0

Published

Real-time voice chat with any OpenAI-compatible endpoint — local VAD + whisper ASR + free edge-tts, one command to run. 和任意 OpenAI 兼容端点实时语音对话:本地 VAD + whisper 识别 + 免费 edge-tts,一行命令跑起来。

Readme

hermes-live

一行命令,和你的 LLM 实时语音对话。 浏览器开麦即聊:本地 silero VAD 断句、whisper 本地识别、 免费 edge-tts 合成,接任意 OpenAI 兼容端点(本地 gateway、ollama/vllm 前的兼容层、云端 API 均可)。 支持随时开口打断(barge-in:断开 SSE,上游立即停止生成不空烧 token)。

npx hermes-live --api-url http://127.0.0.1:8647 --api-key sk-xxx --model k3

首次运行自动完成:建 Python venv → 装依赖 → 下 whisper 权重(574MB)→ 起服务 → 打开浏览器。 之后每次秒起。数据都在 ~/.hermes-live/(含 config.yaml,改配置编辑它)。

浏览器开麦 ──ws──> 本地服务 ──SSE──> 你的 OpenAI 兼容端点
 AudioWorklet 16k    silero VAD 分段
 24k 播放(打断过滤)  whisper.cpp 识别(Metal/CPU)
                     edge-tts 流式合成(免费)

常用选项

| 选项 | 说明 | |---|---| | --api-url / --api-key / --model | 你的 OpenAI 兼容端点三件套 | | --mirror | 中国大陆网络:pip 走阿里云镜像、权重走 hf-mirror | | --skip-model | 跳过 whisper.cpp 权重(改用 faster-whisper 自动下载) | | --host 0.0.0.0 --token <随机串> | 手机/局域网接入(带鉴权门,回环免 token) | | --port / --no-browser | 端口 / 不自动开浏览器 |

要求

  • Python ≥ 3.10(系统里有即可,其余全自动)
  • Node ≥ 16、curl
  • macOS(Apple Silicon 走 Metal 加速,实测停口→出声 ~4s);Linux/Windows 理论可用(CPU 识别,未充分测试)

说明

  • 语音全链路本地/免费:无 OpenAI Realtime 之类的按分钟计费,唯一的 LLM 消耗是你自己的端点。
  • 打字也行:页面有文本框与附件拖拽(文件落盘、路径回填,端点侧用工具自取)。
  • edge-tts 使用微软在线免费接口,音色可在页面切换(晓晓/云希等)。

MIT © bb4407777