DeepSeek Harness Plugin Hub

Publish and manage complete Harness Profiles. Discover Plugins for your next setup.

Explore

PluginsPresetsDocsNews

Community

Publish a pluginContactReport an issue

Resources

Plugin Hub on GitHubDeepSeek HarnessSystem statusPrivacy notice
© 2026 DeepSeek Harness Plugin HubPowered byPaxTech

Independent and unofficial. Not affiliated with, authorized by, or endorsed by DeepSeek.

DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in
← Plugins
V

voicetranser

Voicetranser

Fully local push-to-talk voice input for macOS: hold a global hotkey, speak, release — transcription is pasted at your cursor. Local-first STT (Qwen3-ASR MLX / SenseVoice / mlx-whisper), zero external APIs. This package ships the agent skill that installs, configures and troubleshoots the tool.

The plugin will be installed here. Keep web if you are unsure.

npx -y @deepseek-ai/dsh plugin --profile web add github:Lumos-789/VoiceTranser#933bce3ebc911777b5751d369247d67f17abf5e5
READMECompatibilityVersions

Compatibility and provenance

Voicetranser is published as voicetranser and currently resolves to version 1.0.2. The Hub verifies its manifest and preserves the exact installation source for reproducible installs.

DSH compatibility
*
Runtime surfaces
any
Release source
github
Registry updated
11/4/2026

Versions

1.0.2stable
11/4/2026
1.0.0stable
11/1/2026

Related plugins

Loading related plugins…

Latest
1.0.2
DSH
*
HMR
Process restart
Tree shaking
Safe tree shaking not declared
Unpacked size
Unavailable
Files
Unavailable
Surface
any
License
MIT
Source
github
GitHub
★ 0
Weekly downloads
0
Last push
11/4/2026
View source ↗
README badge

Click the badge to copy Markdown for your README.

Do you maintain this Plugin?Claim benefit · Priority security scan

Verify the GitHub repository declared in package.json to manage this listing. After you claim it, Hub will prioritize a security scan of the current version and publish the result when it passes.

Claim this Plugin →
Report an issue

Related plugins

More verified plugins in vision-media.

Experimental Voice Input Bundle@deepseek-ai/dsh-experimental-voice-input-bundleExperimental voice input with local SenseVoice; downloads its runtime on first useModlens@liustack/modlensPlug-in vision for text-only LLMs, powered by the free Antigravity CLIImage Gendsh-image-genBring ChatGPT-like image generation to DeepSeek Harness — Gemini, OpenAI, Seedream, DashScope, local ComfyUI & more.Ab Ocrdsh-ab-ocr--- description: "The out-of-tree ocr tool: recognizes a scanned PDF or image page by page, merges the pages in order only after the last one, and saves one Markdown document with the heading levels the model decided." kind: "package-reference" ---

README

VoiceTranser

语音输入 → 转写 → 自动粘贴

按住全局热键说话,松开后自动完成语音转写并粘贴到当前应用。专为 AI 编程助手(Claude Code、Cursor 等)设计,完全本地运行,零外部 API 依赖。

✨ 特性

  • 🎙️ 全局热键录音 — 通过外部快捷键工具(Karabiner-Elements/Raycast/Hammerspoon)触发 HTTP 端点,按住说话、松开出稿
  • 🧠 本地 STT,三引擎 — 默认 Qwen3-ASR 0.6B 4bit(MLX/Metal GPU 推理,RTF 0.012-0.021,中文近完美自带标点、中英夹杂强);SenseVoice Small int8(CPU fallback,RTF 0.03);mlx-whisper large-v3(英文/小语种 fallback)。均离线推理,隐私安全
  • 📋 自动粘贴 — 转写完自动粘贴到当前光标位置
  • 🔧 误识纠正 — corrections.json 整词词表,发现新误识加一行重启即生效
  • 🔔 系统通知 — 每个阶段 macOS 通知反馈,不盯终端也知道进度
  • 🛡️ 自愈守护 — launchd KeepAlive + CoreAudio 死锁看门狗 + 8 项自检脚本
  • 🍎 macOS 原生 — 菜单点击粘贴 + 系统通知,深度系统集成

架构

External Hotkey → HTTP /start|/stop → Recorder (sounddevice 16k mono)
  → Transcriber (Qwen3-ASR MLX 默认 / SenseVoice / mlx-whisper)
  → Corrector (corrections.json 整词纠正)
  → Output (clipboard + paste)

快速开始

前置要求

  • macOS Apple Silicon(MLX 引擎需要;Intel 机型走 SenseVoice CPU 引擎)
  • Python 3.11+
  • uv 包管理器

安装

git clone https://github.com/Lumos-789/VoiceTranser.git
cd VoiceTranser
uv sync   # PyPI 慢时: UV_DEFAULT_INDEX=https://pypi.tuna.tsinghua.edu.cn/simple uv sync
uv run python download_model.py   # 下 SenseVoice fallback 模型(228MB, hf-mirror 源)

Qwen3-ASR 主力模型(~500MB)首次运行自动从 hf-mirror 拉取,无需手动下载。

使用

# 守护模式(HTTP 服务器,默认引擎 qwen3-mlx)
uv run python -m voicetranser

# 临时切换引擎
STT_ENGINE=sensevoice uv run python -m voicetranser   # CPU fallback
STT_ENGINE=mlx-whisper uv run python -m voicetranser  # 英文/小语种

# 处理音频文件(不粘贴,对比引擎用)
uv run python -m voicetranser --file recording.wav --no-paste

# 8 项链路自检(音频检查有界,不会卡在系统授权框)
.venv/bin/python tests/diagnose.py
# 麦克风不能碰 / 不想弹权限框时跳过音频检查
.venv/bin/python tests/diagnose.py --skip-audio

诊断按实际运行的实例解析端口:--port > SERVER_PORT 环境变量 > 已安装 launchd plist 的 SERVER_PORT > 项目 .env > 默认端口(config.DEFAULT_SERVER_PORT,9877);plist 与默认不一致时会打印 WARNING。麦克风不能碰时用 --skip-audio。

全局热键(推荐 Karabiner-Elements)

Karabiner complex_modifications 配置:right_option 按下 → curl localhost:9877/start,松开 → curl localhost:9877/stop。按住说话、松开自动转写粘贴。也可用 Raycast/Hammerspoon 触发 /toggle。

常驻后台(launchd)

uv run python install_launchd.py
curl -s localhost:9877/status

安装脚本会按当前 checkout 的绝对路径生成 ~/Library/LaunchAgents/com.voicetranser-sense.plist,再加载并启动服务;开机自启 + 崩溃自愈,服务启动时后台预热模型。需要换端口或引擎时用 --port / --engine,只生成不加载用 --no-load。

macOS 辅助功能权限

首次使用需要授予终端辅助功能权限:系统设置 → 隐私与安全性 → 辅助功能 → 勾选你的终端应用(自动粘贴所必需)。

测试与自检

.venv/bin/python -m unittest discover -s tests -v   # 单元测试
.venv/bin/python tests/diagnose.py --fix            # 8 项体检 + 自动重启修复

故障排查

先跑 tests/diagnose.py,它会把上面这些一次性查完,别凭现象猜。

  • 转写成功但不自动粘贴 → 辅助功能权限没授。launchd 启动的实例要单独授一次(列表里会出现 python 条目)。
  • curl 连接被拒 → 服务没起来。tail -f ~/Library/Logs/VoiceTranser-sense.log;常见是端口被占(改 SERVER_PORT)或模型没下(跑 download_model.py)。
  • 录到空白 → 麦克风权限没授。
  • launchd 反复崩 → 99% 是 plist 里路径写错。重跑 install_launchd.py 让它按当前 checkout 重新生成。
  • 音频报错 -9986 / PortAudio 异常 → 休眠后音频子系统损坏或蓝牙耳机切换。看门狗会在 5s 超时后自杀重启,多数无感自愈;连续失败时 launchctl kickstart -k gui/$(id -u)/com.voicetranser-sense。

HTTP 端点

守护模式启动后监听 http://127.0.0.1:9877(默认;SERVER_PORT 可覆盖):

端点说明
GET /toggle切换录音(idle → recording → processing)
GET /start开始录音
GET /stop停止录音并处理
GET /status当前状态

性能实测(2026-11,Apple Silicon,16.5s 中文)

引擎转写耗时RTF标点
Qwen3-ASR 0.6B 4bit MLX(默认)0.25s0.015自带,规范
SenseVoice Small int8 CPU0.53s0.033自带
mlx-whisper large-v3~1.1s~0.07长句易丢

技术栈

组件技术
STT 主力mlx-audio + Qwen3-ASR 0.6B 4bit(MLX/Metal)
STT fallbacksherpa-onnx + SenseVoice / mlx-whisper
音频录制sounddevice
包管理uv

作为 DSH 插件使用

本仓同时是 DSH 插件(dsh.bundle 已声明):安装后 agent 获得 voicetranser 技能,可代你完成安装、launchd 配置、Karabiner 热键配置与排障。

卸载

launchctl bootout gui/$(id -u)/com.voicetranser-sense
rm ~/Library/LaunchAgents/com.voicetranser-sense.plist
rm -rf ~/VoiceTranser                      # 项目目录
rm ~/Library/Logs/VoiceTranser-sense.log

再到系统设置里移除辅助功能 / 麦克风权限中的相关条目。

License

MIT