OpenClaw

edge-tts-english

Generate high-quality English (and multilingual) audio using Microsoft Edge TTS. Use when the user asks to "speak this", "pronounce", "read aloud", "say this in English", "озвучь голосом", "прочитай по-английски", "произнеси", or wants to hear text spoken with a native accent for language learning or pronunciation practice. Supports American and British English voices (male and female). Requires edge-tts installed via pipx. Sends the resulting MP3 directly to the user.

davydenkovm0 来源安装数☆ 0 仓库 Stars

查看来源 ↗安装与使用 SKILL.md ↗

安装与使用

请根据来源仓库和你的 AI 工具说明安装此技能。先阅读技能文件和依赖要求，再添加到工作流。

SkillHub CLI

skillhub install davydenkovm/edge-tts-english

打开来源仓库，查看说明和兼容环境后，按来源提供的命令或步骤安装。

将来源链接提供给你的 Agent，让它先读取说明、核对依赖，并向你说明将执行的安装步骤。

查看来源 ↗使用指南

技能说明

Edge TTS English

Generate native-quality English audio using Microsoft Edge TTS (/root/.local/bin/edge-tts).

Workflow

Run scripts/speak.sh "<text>" [voice] [output_path]
Send the resulting MP3 to the user via message tool with media=<output_path>

bash scripts/speak.sh "Hello, world!" en-US-AriaNeural /tmp/tts_out.mp3

Voices

Voice	Style
`en-US-AriaNeural`	Female, American (default)
`en-US-JennyNeural`	Female, American, warm
`en-US-GuyNeural`	Male, American
`en-GB-SoniaNeural`	Female, British
`en-GB-RyanNeural`	Male, British

List all voices: /root/.local/bin/edge-tts --list-voices | grep en-

Notes

Scripts path: resolve relative to this skill's directory
edge-tts binary: /root/.local/bin/edge-tts
Default output: /tmp/edge_tts_output.mp3
Always send audio via message tool (media param), not as text

来源信息

Source: github
Repository: openclaw/skills
Path: skills/davydenkovm/edge-tts-english
Version: —
Commit: 582e15598ebbf39ddcfc775374b9818e097f8c58
分类来源: rules
状态: active
可见性: public

这些信息来自收录时的来源分析，可能滞后；使用前请核对最新来源文件。

来源内容

SKILL.md

# Edge TTS English

Generate native-quality English audio using Microsoft Edge TTS (`/root/.local/bin/edge-tts`).

## Workflow

1. Run `scripts/speak.sh "<text>" [voice] [output_path]`
2. Send the resulting MP3 to the user via `message` tool with `media=<output_path>`

```bash
bash scripts/speak.sh "Hello, world!" en-US-AriaNeural /tmp/tts_out.mp3
```

## Voices

| Voice | Style |
|---|---|
| `en-US-AriaNeural` | Female, American (default) |
| `en-US-JennyNeural` | Female, American, warm |
| `en-US-GuyNeural` | Male, American |
| `en-GB-SoniaNeural` | Female, British |
| `en-GB-RyanNeural` | Male, British |

List all voices: `/root/.local/bin/edge-tts --list-voices | grep en-`

## Notes

- Scripts path: resolve relative to this skill's directory
- edge-tts binary: `/root/.local/bin/edge-tts`
- Default output: `/tmp/edge_tts_output.mp3`
- Always send audio via `message` tool (`media` param), not as text

搜索