winmsg-tts

Windows本地TTS朗读技能。通过WM_COPYDATA消息把AI回复实时发送到迷你窗口朗读，支持中英文标点分割、队列顺序播放、语速音量滑块调节，零token消耗，完全本地运行。

3,891 stars

byopenclaw

View on GitHub Installation ↓

Best use case

winmsg-tts is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Teams using winmsg-tts should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

You only need a quick one-off answer and do not need a reusable workflow.
You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/tts-winmsg-free/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/512548510/tts-winmsg-free/SKILL.md"

Manual Installation

Download SKILL.md from GitHub
Place it in .claude/skills/tts-winmsg-free/SKILL.md inside your project
Restart your AI agent — it will auto-discover the skill

How winmsg-tts Compares

Feature / Agent	winmsg-tts	Standard Approach
Platform Support	Not specified	Limited / Varies
Context Awareness	High	Baseline
Installation Complexity	Unknown	N/A

Frequently Asked Questions

What does this skill do?

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

AI Agents for Marketing

Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.

Best AI Agents for Marketing

A curated list of the best AI agents and skills for marketing teams focused on SEO, content systems, outreach, and campaign execution.

AI Agent for YouTube Script Writing

Find AI agent skills for YouTube script writing, video research, content outlining, and repeatable channel production workflows.

SKILL.md Source

# winmsg-tts

Windows 本地 TTS 朗读技能。通过 WM_COPYDATA 消息把 AI 回复实时发送到迷你窗口朗读，支持中英文标点分割、队列顺序播放、语速音量滑块调节，零 token 消耗，完全本地运行。

## 核心规则（重要！）

### 开启朗读模式
- 用户说"开启朗读模式"时 → 自动启动 TTS 迷你窗口
- 启动后第一条消息要说点自然的、有上下文的话，不要说通用测试句
- 把 HWND 和启动成功状态告诉用户

### 朗读中（每次回复必须执行！）
**TTS 模式下，AI 的每一条用户可见回复，都必须同步调用 sendmsg_hwnd.py 发送到小窗口朗读。不得遗漏。不得只发文字不转发音频。**

流程：
1. 收到用户消息
2. 生成回复文字
3. 调用 sendmsg_hwnd.py：`python sendmsg_hwnd.py <回复内容>`
4. 把同一回复文字也发给用户（webchat）

### 关闭朗读模式
- 用户说"关闭朗读模式"时 → 发送精确退出命令：`python sendmsg_hwnd.py --quit`
- 只关闭自己的 TTS 窗口，不会影响其他进程
- 关闭后告知用户

### 规则要点
- 只把用户看得见的回复发给 TTS 窗口，不要发内部推理
- 开启时说自然的话，不要每次都说"这是一条测试消息"
- 滑块调节实时生效，无需重启

## 技术特性

- **自动分句**：按中英文标点（`。` `；` `：` `！` `？` `……` `.` `,` `;` `:` `!` `?`）分割句子，保留标点到句尾
- **队列播放**：多句按顺序排队播放，不重叠，不打断
- **label 同步**：窗口文字随播放进度同步更新，每播一句更新一句
- **无弹窗**：使用 CREATE_NO_WINDOW (0x08000000) + Base64 编码，彻底解决 PowerShell 窗口问题
- **配置持久化**：语速/音量保存到配置文件，断电重启后恢复上次设置
- **精确关闭**：通过 `__QUIT__` 命令关闭自己的窗口，不杀其他进程

## 文件说明

- `scripts/wmserver_20260327.py` — TTS 接收端，320×90像素迷你窗口，无边框右下角永远置顶
- `scripts/sendmsg_hwnd.py` — 发送端，通过 WM_COPYDATA 发送字符串；支持 `--quit` 精确关闭
- `config/tts_speed.txt` — 语速配置（-10 到 +10）
- `config/volume.txt` — 音量配置（0-100）
- `config/wmserver_hwnd.txt` — 当前窗口 HWND（运行时生成）

## 使用方法

1. 安装依赖：`pip install pywin32`
2. 启动 TTS：`python scripts/wmserver_20260327.py`
3. 发送信息：`python scripts/sendmsg_hwnd.py <消息内容>`
4. 关闭 TTS：`python scripts/sendmsg_hwnd.py --quit`

## 技术原理

- WM_COPYDATA = 0x004A + COPYDATASTRUCT 结构，跨进程传字符串
- PowerShell `System.Speech.Synthesis.SpeechSynthesizer` TTS 引擎
- Base64 编码命令避免中文和长度限制
- 消息队列顺序播放，不重叠
- tkinter 做 UI，overrideredirect(True) 无边框窗口
- CREATE_NO_WINDOW 禁止 PowerShell 弹窗
- `__QUIT__` 命令通过窗口类名精确关闭窗口，不影响其他进程
- 配置持久化到文本文件，断电重启后恢复上次设置

## UI 布局（320×90）

```
[白色文字显示区域（当前播放的句子）]
[慢]━━━●━━━━━━━━[快]   ← 语速滑块
[小]━━━●━━━━━━━━[大]   ← 音量滑块
```

- 背景：深灰色 #2d2d2d
- 文字：白色 #FFFFFF，微软雅黑 10pt 粗体
- 滑块轨道：灰色 #555555
- 滑块把手：白色 oval

## 系统要求

- Windows 系统
- Python 3.8+
- pywin32

Related Skills

---

3891

from openclaw/skills

name: article-factory-wechat

Content & Documentation

humanizer

3891

from openclaw/skills

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.

Content & Documentation

find-skills

3891

from openclaw/skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

General Utilities

tavily-search

3891

from openclaw/skills

Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.

Data & Research

baidu-search

3891

from openclaw/skills

Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.

Data & Research

agent-autonomy-kit

3891

from openclaw/skills

Stop waiting for prompts. Keep working.

Workflow & Productivity

Meeting Prep

3891

from openclaw/skills

Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.

Workflow & Productivity

self-improvement

3891

from openclaw/skills

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

Agent Intelligence & Learning

botlearn-healthcheck

3891

from openclaw/skills

botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.

DevOps & Infrastructure