What makes Web TTS Speaker notable?

1K downloads. Trust evidence available

How should Web TTS Speaker be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Web TTS Speaker

网页一键朗读：URL/文本 → TTS语音 → 多渠道自动匹配（飞书语音条 / 微信/TG/Discord MP3） Skill: Web TTS Speaker Owner: phentse Summary: 网页一键朗读：URL/文本 → TTS语音 → 多渠道自动匹配（飞书语音条 / 微信/TG/Discord MP3） Tags: latest:3.2.1 Version history: v3.2.1 | 2026-05-20T12:46:13.208Z | user 🔧 v3.2.1 — 修复SKILL.md：添加version字段到frontmatter、修正workspace完整路径(agents\tech)，重新发布完整文档包。 v3.2.0 | 2026-05-20T12:38:39.167Z | user 📦 v3.2.0 — PKG精简：删除测试语音&__pycache__，精编文档(README/skill.json)，新增对比表引导废弃项目，零冗余发布。 v3.1.0 | 2026-05-20T11:52:51.

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.0k

Updated

Oct 11, 2026

Version

3.2.1

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1K downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 1K downloadsadoption · observed Oct 11, 2026
Latest release: 3.2.1release · observed May 20, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17a84ww07c0y3ptjdqc7rb9j9840tfp:web-tts-speaker

Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-phentse-web-tts-speaker/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

43,717 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: web-tts-speaker
version: 3.2.1
description: "网页一键朗读：URL/文本 → TTS语音 → 多渠道自动匹配（飞书语音条 / 微信/TG/Discord MP3）"
metadata:
  openclaw:
    requires: { bins: ["python3"] }
    install:
      - id: python
        kind: pip
        package: "-r requirements.txt"
---

# web-tts-speaker v3.2.1

**网页/文字 → TTS语音 → 多渠道自动匹配推送**

> 📢 替代 [web-reader-tts](https://clawhub.ai/packages/web-reader-tts) — 所有功能由本项目统一覆盖。

## 一句话用法

```bash
python cli.py --url https://example.com/article
python cli.py --text "你好世界"
```

默认 `--channel auto`，生成所有格式，Agent 按来源渠道自动取用。

---

## 🧠 Agent 工具定义

当用户希望**朗读网页**或**将文字转为语音**时，按以下流程操作。

### 触发条件

用户消息中出现以下意图之一：
- "朗读 / 读一下 / 帮我读 / 听一下" + **URL**
- "朗读 / 读一下 / 帮我读 / 听一下" + **文本内容**
- 直接发了一个 **URL**（自动朗读）
- "转语音 / 生成语音 / TTS"

### 执行流程

#### Step 1：提取目标文本

```
用户说 "朗读 https://abc.com/article"  → 取 URL
用户说 "帮我读一下这段：你好世界"      → 取文本
用户直接发一个 URL                     → 取 URL
```

#### Step 2：获取来源渠道

从当前消息的 `inbound context` 中读取 `channel` 字段：

```json
// inbound metadata 示例
{ "channel": "openclaw-weixin" }   // 微信
{ "channel": "feishu" }           // 飞书
{ "channel": "telegram" }         // Telegram
{ "channel": "discord" }          // Discord
```

#### Step 3：调用 CLI

```bash
cd C:\Users\www\.openclaw\agents\tech\workspace\skills\web-tts-speaker

# 朗读网页（自动模式）
python cli.py --url "https://example.com/article"

# 文字转语音（自动模式）
python cli.py --text "你好世界"
```

使用 **exec 工具** 执行，并捕获 stdout。

#### Step 4：解析输出标记

CLI 输出多个渠道标记。根据来源渠道选取对应的那个：

| 来源 channel | 取用标记 | 发送文件 |
|-------------|---------|---------|
| `openclaw-weixin` | `[WECHAT_VOICE]` | `file=xxx.mp3` |
| `feishu` | `[FEISHU_VOICE]` | `file=xxx.opus` |
| `telegram` | `[TELEGRAM_VOICE]` | `file=xxx.mp3` |
| `discord` | `[DISCORD_VOICE]` | `file=xxx.mp3` |

#### Step 5：发送语音

用 `message` 工具发送，channel 和 file 从所选标记中提取：

**微信：**
```python
message(
    action: "send",
    channel: "openclaw-weixin",
    media: "/path/to/voice.mp3"
)
```

**飞书：**
```python
message(
    action: "send",
    channel: "feishu",
    asVoice: true,
    filePath: "/path/to/voice.opus"
)
```

**Telegram / Discord：**
```python
message(
    action: "send",
    channel: "telegram",   # 或 "discord"
    media: "/path/to/voice.mp3"
)
```

---

## 完整调用示例（给 Agent 参考）

```
用户: 朗读 https://zshttp.com/2981.html

→ 检测来源: inbound metadata.channel = "openclaw-weixin"
→ 执行: exec(command="cd C:\\Users\\www\\.openclaw\\workspace\\skills\\web-tts-speaker && python cli.py --url https://zshttp.com/2981.html", timeout=300)
→ 解析输出:
   找到 [WECHAT_VOICE] 标记
   file=C:\xxx\voice_195836.mp3
→ 发送:
   message(action="send", channel="openclaw-weixin", media="C:\xxx\voice_195836.mp3")
→ 回复用户: "语音已发到微信"
```

```
用户: 帮我读一下这篇文章的摘要：今天天气真好...

→ 检测来源: inbound metadata.channel = "feishu"
→ 执行: exec(command="cd C:\\Users\\www\\.openclaw\\workspace\\skills\\web-tts-speaker && python cli.py --text '今天天气真好...'")
→ 解析输出:
   找到 [FEISHU_VOICE] 标记
   file=C:\xxx\voice_xxxxxx.opus
→ 发送:
   message(action="send", channel="feishu", asVoice=true, filePath="C:\xxx\v

README.md

# Web TTS Speaker v3.2.0

**网页/文字 → TTS语音 → 多渠道自动匹配推送**

一键朗读网页或文字，自动生成适配不同平台的语音格式。不调飞书/微信 API，Agent 负责发送，脚本只做三件事：**提取文字 → 生成语音 → 输出标准化标记**。

> 📢 **替代 [web-reader-tts](https://clawhub.ai/packages/web-reader-tts)**
> Web Reader TTS 已废弃，所有功能由本项目统一覆盖。新增多渠道支持（飞书语音条/微信 MP3/TG/Discord）、自动格式匹配、零飞书 API 依赖。

---

## 快速开始

```bash
# 安装依赖
pip install edge-tts beautifulsoup4 requests

# 自动模式：生成全部渠道格式
python cli.py --url https://example.com/article
python cli.py --text "你好世界"

# 指定单渠道
python cli.py -c feishu --text "你好世界"
python cli.py -c wechat --text "你好世界"
```

---

## 渠道支持

| 渠道 | 输出格式 | 声道/码率 | Agent 发送方式 |
|------|---------|-----------|---------------|
| `-c feishu` | `.opus` | 单声道 16kHz / 12kbps | `asVoice=true` → 飞书语音气泡 |
| `-c wechat` | `.mp3` | 单声道 24kHz / 48kbps | `media=xxx` → 微信文件消息 |
| `-c telegram` | `.mp3` | 单声道 24kHz / 48kbps | `media=xxx` → TG 文件消息 |
| `-c discord` | `.mp3` | 单声道 24kHz / 48kbps | `media=xxx` → Discord 文件消息 |
| `-c auto`（默认） | 全部 | — | Agent 按来源渠道自动取用 |

---

## 使用场景

### 朗读网页

```bash
python cli.py -c feishu --url https://example.com/article
```

自动提取正文（过滤导航/广告/页脚），支持中英文。

### 文字转语音

```bash
python cli.py -c wechat --text "会议提醒：下午3点有项目评审"
```

适合快速生成通知/提醒语音。

### 指定语音角色

```bash
python cli.py -c feishu --text "你好" --voice zh-CN-YunxiNeural
```

常用中文语音：

| 语音参数 | 角色 |
|---------|------|
| `zh-CN-XiaoxiaoNeural` | 晓晓（女声，默认） |
| `zh-CN-YunxiNeural` | 云希（男声，活泼） |
| `zh-CN-YunyangNeural` | 云扬（男声，新闻） |
| `zh-CN-XiaoyiNeural` | 晓伊（女声，柔和） |

### 自定义输出

```bash
python cli.py -c wechat --text "通知" -o notice.mp3
```

---

## 输出标记（Agent 读取）

自动模式输出标准化标记块，Agent 根据请求来源渠道自动选取对应文件：

```text
[FEISHU_VOICE]
channel=feishu
file=/path/to/voice.opus
text=会议提醒：下午3点有项目评审...
dur=15
size=22124
full=飞书语音气泡
[/FEISHU_VOICE]

[WECHAT_VOICE]
channel=wechat
file=/path/to/voice.mp3
text=会议提醒：下午3点有项目评审...
dur=15
size=88560
full=微信文件消息
[/WECHAT_VOICE]
```

---

## 架构

```
URL/文本
    │
    ▼
网页提取正文 ──→ Edge TTS 分块合成 ──→ 合并 WAV ──→ 多渠道转码
    │                                                    │
    │                                         ┌──────────┼──────────┐
    │                                         ▼          ▼          ▼
    │                                     feishu     wechat     telegram/discord
    │                                    (.opus)    (.mp3)       (.mp3)
    │                                         │          │            │
    └───输出标准化标记供 Agent 解析 ──────────┘──────────┘────────────┘
                                                    │
                                                    ▼
                                           message() → 渠道语音发送
```

---

## 依赖

| 依赖 | 用途 | 安装 |
|------|------|------|
| Python 3.8+ | 运行环境 | — |
| edge-tts | 微软 Edge 神经网络 TTS（免费，无需 API Key） | `pip install edge-tts` |
| beautifulsoup4 | 网页正文提取 | `pip install beautifulsoup4` |
| requests | 网页抓取 | `pip install requests` |
| FFmpeg | 音频转码 | [gyan.dev](https://www.gyan.dev/ffmpeg/builds/) / `brew install ffmpeg` / `apt install ffmpeg` |

---

## 与

_meta.json

{
  "ownerId": "kn72nytm5dxvsna04vkn7q2k3d827y6x",
  "slug": "web-tts-speaker",
  "version": "3.2.1",
  "publishedAt": 1779281173208
}

skill-card.md

## Description:

Web TTS Speaker turns webpage content or supplied text into text-to-speech audio files for Feishu, WeChat, Telegram, and Discord workflows.

This skill is ready for commercial/non-commercial use.

## Publisher:

[phentse](https://clawhub.ai/user/phentse)

### License/Terms of Use:

MIT-0

## Use Case:

Developers and agents use this skill to fetch article text or accept supplied text, synthesize speech, and prepare platform-specific audio attachments for supported messaging channels.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: The skill can fetch arbitrary URLs.

Mitigation: Use it only where public-web URL fetching is acceptable, avoid private or internal URLs, and add confirmation plus URL validation before deployment.

Risk: Extracted webpage content or supplied text may be sent to an external TTS service.

Mitigation: Do not process secrets or sensitive text without consent, and remove text snippets from shared logs or machine-readable output when needed.

Risk: The security verdict recommends review before installation.

Mitigation: Review the skill before installing, pin dependencies, and deploy only in an environment where its URL fetching and TTS behavior are permitted.

## Reference(s):

- [ClawHub skill page](https://clawhub.ai/phentse/skills/web-tts-speaker)
- [Publisher profile](https://clawhub.ai/user/phentse)
- [OpenClaw WeChat voice message issue](https://github.com/openclaw/openclaw/issues/61031)
- [FFmpeg Windows builds](https://www.gyan.dev/ffmpeg/builds/)

## Skill Output:

**Output Type(s):** [text, shell commands, configuration, files, guidance]

**Output Format:** [Markdown guidance with bash examples and CLI stdout markers that point to generated MP3 or Opus audio files]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Requires Python 3.8+, Python packages edge-tts, beautifulsoup4, and requests, plus FFmpeg for audio transcoding.]

## Skill Version(s):

3.2.1 (source: server release metadata, artifact skill.json, and SKILL.md frontmatter)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

skill.json

{
  "name": "web-tts-speaker",
  "version": "3.2.1",
  "description": "网页一键朗读：URL/文本 → TTS语音 → 多渠道自动匹配（飞书语音条 / 微信/TG/Discord MP3）",
  "author": "tech",
  "tags": ["tts", "voice", "speaker", "朗读", "飞书语音条", "Edge TTS"],
  "dependencies": {
    "python": ">=3.8",
    "packages": [
      "edge-tts",
      "beautifulsoup4",
      "requests"
    ]
  },
  "commands": {
    "auto": "python cli.py --url <url>",
    "feishu": "python cli.py -c feishu --url <url>",
    "wechat": "python cli.py -c wechat --text <text>",
    "voice": "python cli.py -c feishu --text <text> --voice zh-CN-YunxiNeural"
  },
  "examples": [
    {
      "description": "朗读网页（自动匹配渠道）",
      "command": "python cli.py --url \"https://example.com/article\""
    },
    {
      "description": "飞书语音条",
      "command": "python cli.py -c feishu --text \"会议提醒：3点评审\""
    },
    {
      "description": "微信语音",
      "command": "python cli.py -c wechat --url \"https://example.com/article\""
    },
    {
      "description": "指定男声",
      "command": "python cli.py --text \"你好\" --voice zh-CN-YunxiNeural"
    }
  ]
}

Github ReposUpdated 2d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.