# Send Voice (Edge TTS) to your agent
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
## Fast path
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
## Suggested prompts
### New install

```text
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete.
```
### Upgrade existing

```text
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run.
```
## Machine-readable fields
```json
{
  "schemaVersion": "1.0",
  "item": {
    "slug": "voice-edge-tts",
    "name": "Voice (Edge TTS)",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/zhaov1976/voice-edge-tts",
    "canonicalUrl": "https://clawhub.ai/zhaov1976/voice-edge-tts",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadUrl": "/downloads/voice-edge-tts",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=voice-edge-tts",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "packageFormat": "ZIP package",
    "primaryDoc": "SKILL.md",
    "includedAssets": [
      "CHANGELOG.md",
      "example.js",
      "index.js",
      "package-lock.json",
      "package.json",
      "README.md"
    ],
    "downloadMode": "redirect",
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-30T16:55:25.780Z",
      "expiresAt": "2026-05-07T16:55:25.780Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
        "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/voice-edge-tts"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    }
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/voice-edge-tts",
    "downloadUrl": "https://openagent3.xyz/downloads/voice-edge-tts",
    "agentUrl": "https://openagent3.xyz/skills/voice-edge-tts/agent",
    "manifestUrl": "https://openagent3.xyz/skills/voice-edge-tts/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/voice-edge-tts/agent.md"
  }
}
```
## Documentation

### Voice Skill (Edge TTS)

Text-to-speech skill using Microsoft Edge TTS engine with real-time streaming playback support.

### Features 功能特点

Edge TTS Engine - High quality text-to-speech using Microsoft Edge
Streaming Playback - Real-time audio streaming (边生成边播放)
Multiple Voices - Support for Chinese, English, Japanese, Korean voices
Customizable - Adjust rate, volume, and pitch
Secure Implementation - No command injection vulnerabilities

### 1. Install Python dependencies

pip install edge-tts

### 2. Install ffmpeg (required for streaming)

Windows:
Download from: https://github.com/GyanD/codexffmpeg/releases
Extract and add bin folder to PATH

macOS:

brew install ffmpeg

Linux:

sudo apt install ffmpeg

### Streaming Playback (Recommended) 流式播放（推荐）

Real-time audio generation and playback:

// Basic usage
await skill.execute({
  action: 'stream',
  text: '你好，我是小九'
});

// With custom voice
await skill.execute({
  action: 'stream',
  text: 'Hello, how are you?',
  options: {
    voice: 'en-US-Standard-A',
    rate: '+10%',
    volume: '+0%',
    pitch: '+0Hz'
  }
});

### Text-to-Speech with File 生成语音文件

await skill.execute({
  action: 'tts',
  text: 'Hello, how are you today?',
  options: {
    voice: 'zh-CN-XiaoxiaoNeural'
  }
});
// Returns: { success: true, media: 'MEDIA: /path/to/file.mp3' }

### Direct Speak 直接播放

await skill.execute({
  action: 'speak',
  text: 'Hello!'
});

### List Available Voices 查看可用语音

await skill.execute({
  action: 'voices'
});

### Available Voices 可用语音

LanguageVoice IDChinese (Female)zh-CN-XiaoxiaoNeuralChinese (Male)zh-CN-YunxiNeuralChinese (Male)zh-CN-YunyangNeuralEnglish (US Female)en-US-Standard-AEnglish (US Male)en-US-Standard-DEnglish (UK)en-GB-Standard-AJapaneseja-JP-NanamiNeuralKoreanko-KR-SunHiNeural

### Options 参数

OptionDefaultDescriptionvoicezh-CN-XiaoxiaoNeuralVoice IDrate+0%Speech rate (-50% to +100%)volume+0%Volume adjustment (-50% to +50%)pitch+0HzPitch adjustment

### Security 安全

This skill implements enterprise-grade security best practices:

### 🛡️ Security Features

FeatureImplementationInput ValidationVoice parameter whitelist validation - only allowed voices can be usedNo Shell ExecutionUses spawn() with array arguments instead of shell command concatenationCommand Injection PreventionAll user inputs are properly validated and escapedPath SafetyFixed script path prevents path traversal

### Security Details

// ❌ UNSAFE - Don't use exec with string concatenation
exec(\`py script.py "${userText}" --voice ${userVoice}\`);

// ✅ SAFE - Use spawn with array arguments
spawn('py', [scriptPath, text, '--voice', voice], { shell: false });

### Voice Whitelist

Only these voices are allowed:

const allowedVoices = [
  'zh-CN-XiaoxiaoNeural', 'zh-CN-YunxiNeural', 'zh-CN-YunyangNeural',
  'zh-CN-YunyouNeural', 'zh-CN-XiaomoNeural',
  'en-US-Standard-C', 'en-US-Standard-D', 'en-US-Wavenet-F',
  'en-GB-Standard-A', 'en-GB-Wavenet-A',
  'ja-JP-NanamiNeural', 'ko-KR-SunHiNeural'
];

Any invalid voice parameter will be rejected and replaced with the default voice.

### v1.10 (2026-02-24)

Enterprise-grade security - Full command injection protection
Voice whitelist validation
Replaced exec with spawn for secure process execution
Input sanitization for all parameters

### v1.1.0

Add streaming playback support (边生成边播放)
Add ffmpeg dependency
Fix command injection vulnerability
Add voice whitelist validation

### v1.0.0

Initial release with basic TTS support
## Trust
- Source: tencent
- Verification: Indexed source record
- Publisher: zhaov1976
- Version: 1.10.0
## Source health
- Status: healthy
- Source download looks usable.
- Yavira can redirect you to the upstream package for this source.
- Health scope: source
- Reason: direct_download_ok
- Checked at: 2026-04-30T16:55:25.780Z
- Expires at: 2026-05-07T16:55:25.780Z
- Recommended action: Download for OpenClaw
## Links
- [Detail page](https://openagent3.xyz/skills/voice-edge-tts)
- [Send to Agent page](https://openagent3.xyz/skills/voice-edge-tts/agent)
- [JSON manifest](https://openagent3.xyz/skills/voice-edge-tts/agent.json)
- [Markdown brief](https://openagent3.xyz/skills/voice-edge-tts/agent.md)
- [Download page](https://openagent3.xyz/downloads/voice-edge-tts)