← 返回 Skills 市场
mrliugangqiang

Edge Tts Global

作者 刘岗强 · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
85
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install edge-tts-global
功能描述
Use the globally installed edge-tts command to generate Chinese or multilingual text-to-speech audio on this machine. Use when the user wants text converted...
使用说明 (SKILL.md)

Edge TTS Global

Use this skill when the user wants fast text-to-speech with the globally installed edge-tts command.

What is available

Global commands:

  • edge-tts
  • edge-playback

Bundled helper script:

  • scripts/tts_edge.py

Preferred Chinese test voice:

  • zh-CN-XiaoxiaoNeural

Fast workflow

  1. Put output files in the current caller workspace temp/ directory.
  2. Prefer the bundled Python script scripts/tts_edge.py for standard generation.
  3. If needed, call edge-tts directly.
  4. If sending back to Telegram and the user wants a voice bubble, send the audio with message and set asVoice=true.
  5. If the user wants a normal file/audio attachment, send it normally.
  6. After successful sending, immediately delete the generated temporary file.

Preferred script usage

Generate audio to the current caller workspace temp/ directory automatically:

python3 /data/claw/shared/skills/edge-tts-global/scripts/tts_edge.py -t "老板，你好，我是你的小助理。"

Generate audio with explicit relative path under the current caller workspace:

python3 /data/claw/shared/skills/edge-tts-global/scripts/tts_edge.py -t "老板，你好，我是你的小助理。" -o ./temp/out.mp3

Delete temporary file after successful sending:

python3 /data/claw/shared/skills/edge-tts-global/scripts/tts_edge.py cleanup ./temp/out.mp3

Delete both audio and subtitles:

python3 /data/claw/shared/skills/edge-tts-global/scripts/tts_edge.py cleanup ./temp/out.mp3 ./temp/out.vtt

Change voice explicitly:

python3 /data/claw/shared/skills/edge-tts-global/scripts/tts_edge.py -t "你好" -v zh-CN-XiaoxiaoNeural -o ./temp/out.mp3

Generate subtitles too:

python3 /data/claw/shared/skills/edge-tts-global/scripts/tts_edge.py -t "你好" -o ./temp/out.mp3 --subs ./temp/out.vtt

Direct command patterns

Generate MP3

mkdir -p ./temp
edge-tts --voice zh-CN-XiaoxiaoNeural --text "老板，你好，我是你的小助理。" --write-media ./temp/out.mp3

List voices

edge-tts --list-voices

Telegram sending rule

If the user asks for “气泡语音”, “语音条”, or a voice-message style result:

  • generate the file first
  • send with message
  • set asVoice=true
  • after successful sending, delete the temporary file immediately

If the user asks for a normal audio file:

  • send as a regular attachment
  • do not set asVoice=true
  • after successful sending, delete the temporary file immediately

Cleanup guidance

  • Temporary outputs belong in the current caller workspace temp/ directory
  • Sending succeeds → delete the generated temporary files immediately
  • Prefer python3 scripts/tts_edge.py cleanup \x3Cfile> [subtitle] for deterministic cleanup
  • Do not remove the global edge-tts install unless the user explicitly asks
安全使用建议
This skill is coherent and appears safe in purpose: it simply runs the local edge-tts binary via a small Python wrapper and manages temporary files in the caller workspace. Before installing, confirm that you trust the system-level edge-tts binary that will be invoked (the skill executes it as a subprocess), ensure the agent's workspace temp/ directory is appropriate for generated audio, and be aware the helper script will read an undocumented EDGE_TTS_VOICE env var if present. If you plan to run in a different environment, note the SKILL.md examples use an absolute path (/data/claw/shared/...), which may need adjusting.
功能分析
Type: OpenClaw Skill Name: edge-tts-global Version: 1.0.0 The skill bundle is a legitimate wrapper for the 'edge-tts' utility, providing a Python script (scripts/tts_edge.py) and instructions (SKILL.md) for generating and cleaning up audio files. The code uses safe subprocess execution and standard file handling without any signs of data exfiltration, obfuscation, or malicious intent.
能力评估
✓ Purpose & Capability
Name/description match the included files and instructions: the script and SKILL.md invoke the global edge-tts binary to produce TTS output. The only minor mismatch is that the script honors an environment variable EDGE_TTS_VOICE (for a default voice) that is not documented in SKILL.md or listed in requires.env.
✓ Instruction Scope
SKILL.md limits actions to generating audio in the current caller workspace temp/ directory, optionally listing voices, and deleting temporary files after sending. The included script only runs the edge-tts subprocess, creates/removes files under the workspace, and does not read other system files or send data externally.
✓ Install Mechanism
There is no install spec and no remote downloads; the skill is instruction-only plus a small helper script. It requires a preinstalled edge-tts binary (as stated) — this is proportional and low-risk for an instruction-only skill.
ℹ Credentials
No credentials or sensitive env vars are requested. The script does read EDGE_TTS_VOICE for a default voice (non-sensitive) but that env var is undocumented in the SKILL.md; otherwise environment access is minimal and proportionate.
✓ Persistence & Privilege
The skill is not always-enabled, does not request persistent elevated privileges, and does not modify other skills or global agent configuration.
如何使用
  1. 确保已安装 OpenClaw（本地或 Docker 部署）
  2. 在对话框中输入安装命令：/install edge-tts-global
  3. 安装完成后，直接呼叫该 Skill 的名称或使用 /edge-tts-global 触发
  4. 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
v1.0.0
Initial release of edge-tts-global - Enables text-to-speech audio generation using the globally installed edge-tts command. - Supports fast, multilingual TTS output (with a focus on Chinese), including Telegram voice-bubble style audio. - Provides bundled helper script (scripts/tts_edge.py) for audio generation, voice selection, and cleanup. - Outputs are stored in the current caller workspace temp/ directory and cleaned up after sending. - Allows selection of voices, MP3 generation, and subtitle creation.
元数据
Slug edge-tts-global
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Edge Tts Global 是什么？

Use the globally installed edge-tts command to generate Chinese or multilingual text-to-speech audio on this machine. Use when the user wants text converted... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 85 次。

如何安装 Edge Tts Global？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install edge-tts-global」即可一键安装，无需额外配置。

Edge Tts Global 是免费的吗？

是的，Edge Tts Global 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。

Edge Tts Global 支持哪些平台？

Edge Tts Global 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 Edge Tts Global？

由 刘岗强（@mrliugangqiang）开发并维护，当前版本 v1.0.0。

推荐 Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463283 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259410 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200423 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191115 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190156 · by oswalpalash

💬 留言讨论