PiyotaHu/muxiva-dsh-voice

由Muxiva编排的DeepSeek Harness本地优先全双工语音功能

Project Overview项目介绍

Muxiva Voice is a local-first, full-duplex voice plugin for DeepSeek Harness. It runs microphone capture, VAD, ASR, sentence scheduling, TTS, playback, and barge-in on the Mac, while DSH keeps the agent, sessions, tools, and Web UI. Use it to add low-latency voice conversation on Apple Silicon. It is alpha software, limited to macOS arm64, specific DSH releases, and local model setup.

Muxiva Voice 是 DSH 的本地全双工语音插件:麦克风、VAD、ASR、TTS、播放与打断均在 Mac 本地运行,DSH 继续负责会话、工具与 Web 界面。适合在 Apple Silicon 上为 DSH 添加低延迟语音对话。目前为 alpha,仅支持 macOS arm64、指定 DSH 版本及本地模型环境。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 1 warning1 项注意
  • Only 2 stars - very few users, little community feedback星标只有 2,几乎没人在用,遇到问题缺少社区反馈
DSH walks through these 9 checksDSH 会逐条核对这 9 项

Compatibility兼容性

  • DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
  • External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时(Electron / Python / Docker 等)是否齐备
  • Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突:命令名、skill / tool 重名、端口占用、重复 MCP 注册

Security安全性

  • Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致,是否归档或长期停更
  • Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
  • curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
  • Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
  • Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需(filesystem / network / shell / clipboard)
  • Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限,以及卸载与回滚方式

Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照,不能替代安全审计。

Or use CLI install (for developers)或使用命令行安装(适合开发者)

CLI Install命令行安装

dsh plugin --profile web add @muxiva/dsh-voice@alpha

把 PiyotaHu/muxiva-dsh-voice 加入你的 DSH 配置(web profile)即可启用。

READMEREADME

Muxiva Voice for DeepSeek Harness

Local-first, full-duplex voice for the official DeepSeek Harness, orchestrated by Muxiva.

Your microphone, VAD, ASR, sentence scheduling, TTS, playback and interruption path stay on the Mac. DSH remains the stateful Agent harness and keeps its tools, sessions and Web transcript.

Alpha: public npm installation, the integration contract and unattended M1 Pro certification are complete. Muxiva 0.1.1 wheels are published for CPython 3.8–3.14, including macOS universal2. DSH rc.5 and rc.6 are supported; alpha.2 is certified against rc.6.

What runs where

DSH Web microphone ──PCM16──▶ Muxiva Graph
                              ├─ Silero VAD ──barge-in──┐
                              ├─ Zipformer ──preview─────┤
                              └─ SenseVoice zh/en final─┼─▶ DSH Session / Agent / Tools
DSH assistant deltas ─────────▶ sentence buffer ─▶ speech formatter ─▶ speech normalizer ─▶ Qwen3-TTS / MLX ─▶ browser speaker
  • Muxiva owns the real-time pipeline: typed Frames, bounded queues, backpressure, Signals, cancellation and observability.
  • DSH owns the Agent: session history, model selection, tools, permissions and Web UI.
  • The plugin owns only the bridge: additive DSH UI, a versioned loopback protocol and project Node Packs. Neither upstream repository is patched.

Install the alpha (Apple Silicon)

Prerequisites: macOS arm64, Node.js 22.19+, Python 3.11–3.13, the Muxiva 0.1.1 CLI, and the official DSH CLI.

dsh plugin --profile web add @muxiva/dsh-voice@alpha
npx @muxiva/dsh-voice@alpha setup
npx @muxiva/dsh-voice@alpha start

Run dsh --profile web in a second terminal. Models, the isolated Python environment and logs are stored outside the npx cache in the stable OS user-data directory. Print it with npx @muxiva/dsh-voice@alpha home, or override it with MUXIVA_DSH_VOICE_HOME.

Develop from source

Prerequisites: macOS arm64, Node.js 22.19+, Python 3.11–3.13, Rust, Muxiva source at ../muxiva, the muxiva CLI, and an installed official DSH CLI.

git clone https://github.com/PiyotaHu/muxiva-dsh-voice.git
cd muxiva-dsh-voice

# Build the project Python environment and fetch revision- and SHA-256-pinned models.
npm run doctor -- --fix
npm run models

# Install this checkout as a DSH Bundle. No prepare script is executed.
dsh plugin --profile web add .

Showing the opening section of the README — the full document lives in the repository以上为 README 开头摘要,完整文档在仓库内 · View the full README on GitHub →在 GitHub 查看完整 README →

← 上一个 Prev dsh-plogin-plugin-recommender 下一个 Next solidworks-wlj-dsh →