Floating TTS speaker in each conversation corner: when an AI reply finishes, edge-tts reads the summary aloud in the background with no popup windows; the toggle is remembered per conversation. Requires Windows, Python 3.9+ with the edge-tts package installed, and network access to Microsoft's Edge TTS service; summary is the default mode.
Install
# from GitHub (first run asks for allowBuilds approval — follow the hint, retry)
dsh plugin --profile web add github:1DAdidi/dsh-voice-horn
Any plugin you install runs third-party code with your own permissions — it can read your files, use your credentials, and reach the network, and tool approvals don’t sandbox it. GitHub-sourced plugins also run build scripts at install time — pnpm blocks those until you allow them, so an install can stop with ERR_PNPM_GIT_DEP_PREPARE_NOT_ALLOWED or ERR_PNPM_IGNORED_BUILDS; dsh prints the exact key to add under allowBuilds in your profile’s pnpm-workspace.yaml, and the install works on the next run. Allowing a build is a trust decision: only install sources you trust, and pin a commit (github:owner/repo#sha).
README
This plugin publishes its README in Chinese only.
DeepSeek Harness（DSH）桌面端独立 TTS 语音播报插件：AI 回复完成后，在后台静默朗读回复摘要，全程不弹黑框、不打开播放器窗口；每个对话独立记忆开关状态，新对话默认关闭。
功能
- 对话右下角悬浮喇叭按钮，一键开启/关闭播报
- 内置 14 个 edge-tts 中文音色，支持收藏置顶、语速/音调/音量独立调节
- 四种播报模式：摘要 / 全文 / 手动触发 / 关键词触发
- 自定义过滤词（静默跳过或替换），播报历史本地留存，支持重播/复制/删除
- 预留 CosyVoice 本地音色克隆扩展接口
- 配置与历史仅保存在本机
~/.dsh/voice-horn.json，不上传任何对话内容
环境要求
- Windows（本机静音播放使用 WinMM/MCI 接口）
- Python 3.9+，并安装
edge-tts：
python -m pip install edge-tts -i https://pypi.tuna.tsinghua.edu.cn/simple
安装
完整三步注册（包体 + profile dependencies + profile bundles + patch 登记）见仓库内 安装说明.md。
技术说明
- 宿主侧
index.js：负责任务队列、状态持久化、Python 进程调度、看板娘联动事件 - 前端
client.js：注入对话界面的喇叭按钮与控制面板 scripts/：edge-tts 合成脚本（单次合成、试听缓存、常驻 worker）- Python 解释器按「插件设置 →
VH_PYTHON环境变量 → 系统常见安装目录 →python/py命令」顺序自动探测
安全与隐私
- 全部运行于本机；唯一外部网络请求为调用微软 edge-tts 在线语音合成服务
- 不收集、不上传对话内容；播报历史只存本地
- 代理地址、Python 路径等均在面板内按本机需要填写，不写入代码仓库
许可
MIT
Links
More in this category
Yuuyuko-uu/dsh-tts-bridge★ 217
Reads DSH conversations aloud using the DeepSeek web page's built-in read-aloud, driven by a small browser extension.
PolinniZhong/dsh-omi-voice★ 75
In-chat read-aloud for DeepSeek Harness: tap to read, pause and resume AI replies with natural Doubao TTS voices (BYOK), reading only the final answer with code, tables and diagrams filtered; local engine, plugin keeps no API key.
1624318455/dsh-plugin-tts★ 51
Reads assistant replies aloud via free Edge TTS or your own RVC voice models: read-aloud buttons + auto-read, adaptive chunked progressive playback (gapless long reads), one-click voice-pack installs from a registry, and a portable RVC runtime.
beiyege-01/dsh-voice-ai-girlfriend-plugin★ 49
Voice AI girlfriend for the Web UI: FunASR mic input, Qwen3-TTS spoken replies, companion animation window, and two-way QQ chat (text/voice/image push) via NapCat.
ppy-web/dsh-plugin-xiaomi-mimo-tts★ 41
Provides Xiaomi MiMo, Doubao, and browser-local TTS for DSH, with automatic read-aloud, custom voices, UI sound effects, desktop pet integration, and QQBot integration.
PensiveFei/dsh-voice-scribe★ 36
Voice input for the DSH web UI: tap or hold Alt to dictate into the composer. Local SenseVoice ASR by default — offline, zero config, zero key; auto-fallback to browser Web Speech, optional OpenAI-compatible ASR chain, polish through DSH-configured models, settings UI.
Community comments
Comments are public GitHub Discussions. Loading them connects to GitHub and Giscus; a GitHub account is required to post.