1624318455/dsh-plugin-tts 预览 preview

1624318455/dsh-plugin-tts

Plugin插件 Native原生 ⭐ 21 MIT Vision & Media视觉与多媒体

DeepSeek Harness 的 Edge TTS 语音插件:朗读助手回复,支持自动朗读切换、语音设置面板(免费,无需 API 密钥)

Project Overview项目介绍

This repository is a native text-to-speech plugin built exclusively for DeepSeek Harness (DSH). The core function of the plugin is to read DSH assistant replies out loud for users, making it easier to consume long-form assistant output. It works out of the box with Microsoft Edge’s free online TTS service, and also supports custom voices from user-trained local RVC voice models. To install the plugin, you can add it directly via DSH’s plugin management system, and no modifications to the DSH core code are required to run it.

The plugin adds multiple interactive UI elements to the DSH interface. Every finalized assistant message gets a read-aloud button that you can click to start or stop playback. There is also a global auto-read toggle that, when enabled, will automatically read every new assistant reply after it is generated. Users can adjust TTS settings like rate, pitch, and volume in a dedicated plugin settings panel, and can even download the synthesized audio as an MP3 file directly from the message.

The plugin is released under the permissive MIT open source license. Edge TTS is free to use and does not require an API key, and RVC voice conversion runs entirely locally on your machine, so no paid subscription is needed for personal use. The plugin supports both Chinese and English interfaces, which can automatically follow your system language or be switched manually. Known limitations include that audio cache is only stored for the active session, so you will need to re-synthesize audio after a full restart of DSH.

这是一款专为 DeepSeek Harness (DSH) 开发的原生文本转语音插件,可为用户朗读 DSH 助理的回复内容。插件开箱即用支持微软 Edge 免费在线 TTS,也支持用户使用自行训练的本地 RVC 模型生成自定义音色。它针对长回复实现了无间隙自适应分块播放,支持从语音包注册表一键安装音色,自带便携 RVC 运行时无需额外安装 RVC WebUI。

插件在 DSH 界面中提供了多种交互入口,每条助理消息旁都有朗读按钮,可点击播放或停止;支持自动朗读开关,开启后新生成的助理回复会自动朗读;还提供了语音设置面板,可调整语速、音高、音量,支持试听音色、下载生成的音频文件,选中部分文本后也可触发仅朗读选中内容。

插件采用 MIT 许可证开源,Edge TTS 免费无需 API 密钥,RVC 推理完全在本地运行,个人使用免费。插件支持中英文界面,跟随系统语言自动切换,也可手动修改设置。已知限制包括设置仅存在本地缓存,音频重启后需要重新合成,英文界面可能存在文字换行溢出问题。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 1 note1 项提示
  • 21 stars - an early-stage project星标 21,属于早期项目
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 "@memef1f1y/dsh-plugin-tts"

把 1624318455/dsh-plugin-tts 加入你的 DSH 配置(web profile)即可启用。

READMEREADME

dsh-plugin-tts

dsh-plugin-tts

license Awesome node tests stars last commit

Links


dsh-plugin-tts — Edge TTS + RVC / Index-TTS2 / CosyVoice / Cloud voices for DeepSeek Harness

A dual-sided (Host + Web UI) DeepSeek Harness plugin that reads assistant replies aloud — Microsoft Edge's free online TTS out of the box, your own RVC voice models for custom voices, local Index-TTS2 reference-audio voices, local CosyVoice zero-shot prompt clones (CosyVoice-2.0-0.5B), or paid Google Cloud TTS voices (Chinese Standard/Wavenet). Long replies stream with gapless adaptive chunked playback; voices install one-click from a voice-pack registry; a portable RVC runtime means no RVC WebUI install is needed.

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-free-models-hub 下一个 Next dsh-defend →