← 返回 Skills 市场
90
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install web-tts-speaker
功能描述
网页一键朗读:输入URL或文本,TTS转语音,飞书语音条推送
使用说明 (SKILL.md)
web-tts-speaker v3.0
网页/文字 → TTS语音 → 飞书语音条
一个极简的网页转语音工具,只做三件事:提取文字 → 生成语音 → 输出标记
使用方式
# 朗读网页
python cli.py --url https://example.com/article
# 直接文字转语音
python cli.py --text "你好世界"
输出格式
脚本输出 [FEISHU_VOICE] 标记供 Cron/Agent 读取:
[FEISHU_VOICE]
file=/path/to/voice.opus
text=标题...
[/FEISHU_VOICE]
Agent 读取后用 message 工具发送飞书语音条:
message(
action: "send",
channel: "feishu",
asVoice: true,
filePath: "/path/to/voice.opus"
)
依赖
pip install edge-tts beautifulsoup4 requests
也依赖系统安装的 FFmpeg(用于转码为标准 opus 格式)。
架构原则
- 🎯 只做一件事:网页→语音,不搞复杂架构
- 🚫 不调飞书API:不依赖 app_id/app_secret
- 🔧 不转码:交给 FFmpeg 处理
- 📦 极简依赖:只需 3 个 Python 包
安全使用建议
Install only if you are comfortable sending the chosen text or webpage content to Edge TTS and Feishu. Confirm the Feishu destination, ensure FFmpeg is installed in a trusted location, and prefer pinned dependencies if you need reproducible or stricter security behavior.
功能分析
Type: OpenClaw Skill
Name: web-tts-speaker
Version: 3.0.0
The skill is a legitimate utility designed to extract text from URLs and convert it to audio files using Edge TTS and FFmpeg. The code in `cli.py` uses standard libraries and follows its stated purpose without any signs of data exfiltration, unauthorized network calls, or malicious execution. While it contains a hardcoded Windows-specific path for the FFmpeg executable, this is a functional limitation rather than a security risk.
能力评估
Purpose & Capability
The code is coherent with the stated webpage/text-to-TTS purpose, including URL fetching, Edge TTS generation, Opus output, and a Feishu voice-message handoff.
Instruction Scope
It outputs a machine-readable marker for Cron/Agent use and includes a raw snippet of fetched/user text, so downstream parsers should treat that field as untrusted data.
Install Mechanism
The skill uses third-party Python packages with version ranges and references a pip install in SKILL.md, while the registry says there is no install spec; FFmpeg is also required but not declared as a required binary.
Credentials
Fetching a user-supplied URL, writing an output audio file, and running FFmpeg are expected for this skill, but the FFmpeg path is hard-coded to a Windows location.
Persistence & Privilege
No persistence or credential storage is shown, but the intended workflow uses the agent's Feishu message capability to send the generated voice file.
如何使用
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install web-tts-speaker - 安装完成后,直接呼叫该 Skill 的名称或使用
/web-tts-speaker触发 - 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v3.0.0
v3.0 简化重构
元数据
常见问题
Web TTS Speaker 是什么?
网页一键朗读:输入URL或文本,TTS转语音,飞书语音条推送. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 90 次。
如何安装 Web TTS Speaker?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install web-tts-speaker」即可一键安装,无需额外配置。
Web TTS Speaker 是免费的吗?
是的,Web TTS Speaker 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
Web TTS Speaker 支持哪些平台?
Web TTS Speaker 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。
谁开发了 Web TTS Speaker?
由 Zach(@phentse)开发并维护,当前版本 v3.0.0。
推荐 Skills