← Back to Skills Marketplace
skglau

Edge Tts Cantonese

by Gabriel · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
107
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install edge-tts-cantonese
Description
Generate Cantonese TTS audio in OGG format using Microsoft Edge TTS for voice replies on WhatsApp and Telegram with adjustable tone styles.
README (SKILL.md)

Edge TTS Cantonese Voice Skill

Use Microsoft Edge TTS to generate natural Cantonese voice audio for WhatsApp and Telegram.

Voice Parameters

  • Voice: zh-HK-HiuMaanNeural
  • Rate: varies by tone
  • Pitch: varies by tone

Tones

Tone Rate Pitch Use Case
normal +18% +8Hz General/neutral
slow +0% +8Hz Calm/sad
fast +24% +8Hz Happy/excited
angry +36% +12Hz Impatient/angry

WhatsApp Script

# 只生成 OGG(適合 WhatsApp voice note)
/home/gabriel/.openclaw/workspace/scripts/edge-tts-voice-ogg.sh "你今日好嗎?" normal

# Slow/sad tone
/home/gabriel/.openclaw/workspace/scripts/edge-tts-voice-ogg.sh "我好傷心..." slow

# Fast/happy tone
/home/gabriel/.openclaw/workspace/scripts/edge-tts-voice-ogg.sh "好開心呀!" fast

# Angry/impatient tone
/home/gabriel/.openclaw/workspace/scripts/edge-tts-voice-ogg.sh "你到底聽唔聽我講?" angry

腳本輸出 OGG 路徑,然後可用 WhatsApp 發送命令(例如你現有腳本)傳送。

Trigger Phrases

  • "語音回應"
  • "讀俾我聽"
  • "用廣東話讀"
  • "voice reply"

Output

  • OGG/Opus format ready for WhatsApp / Telegram

Telegram Send Script

/home/gabriel/.openclaw/workspace/scripts/edge-tts-telegram.sh \x3Cchat_id> "你段文字" normal

Example:

/home/gabriel/.openclaw/workspace/scripts/edge-tts-telegram.sh 8474074290 "主人,我係小蝦。" fast
Usage Guidance
Do not run or allow this skill to invoke the hard-coded scripts referenced in SKILL.md until you verify them. Ask the author to provide the missing scripts or an install spec, or change examples to relative/templated paths. Inspect any edge-tts-*.sh scripts for network calls, credential access, or file reads/writes before execution. Confirm whether Microsoft Edge TTS requires authentication or network access and ensure any tokens would be supplied intentionally. If you cannot review the external scripts, decline or isolate the skill (run in a sandbox) — the current instructions are incomplete and could execute arbitrary local code.
Capability Assessment
Purpose & Capability
The name/description claim Microsoft Edge TTS output in OGG, which is coherent with a TTS skill. However the SKILL.md expects pre-existing, undocumented scripts at /home/gabriel/.openclaw/workspace/scripts/edge-tts-voice-ogg.sh and edge-tts-telegram.sh. The skill package provides no install, no scripts, and no explanation of required binaries or auth, so it cannot function as-is and is incoherent about its dependencies.
Instruction Scope
Instructions explicitly instruct the agent (or operator) to run absolute-path shell scripts in a specific user's home directory. That directs the agent to execute local code that is not included with the skill and could perform arbitrary actions or read arbitrary files. The SKILL.md also omits any guidance on how Edge TTS is invoked or authenticated, leaving the agent broad discretion.
Install Mechanism
There is no install spec (instruction-only), which minimizes direct install risk. However, the skill depends on external scripts that are not provided. Because no code is bundled, the static scan found nothing, but the absence means you must trust external scripts already present on the host.
Credentials
The skill requests no environment variables or credentials, which is proportionate. That said, it also provides no guidance about whether Microsoft Edge TTS requires network access or auth tokens in the deploy environment, so missing credential instructions reduce clarity (not necessarily malicious, but incomplete).
Persistence & Privilege
The skill does not request always:true and is user-invocable; it does not claim to modify system-wide agent settings. There is no indication it attempts to persist itself as a privileged skill.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install edge-tts-cantonese
  3. After installation, invoke the skill by name or use /edge-tts-cantonese
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Edge TTS Cantonese Voice Skill 1.0.0 – Initial Release - Generate natural Cantonese TTS audio using Microsoft Edge TTS. - Supports WhatsApp and Telegram voice replies via trigger phrases. - Offers multiple tones: normal, slow (sad), fast (happy), and angry, each with custom rate and pitch settings. - Outputs OGG/Opus audio suitable for messaging platforms. - Includes example scripts for generating and sending voice notes.
Metadata
Slug edge-tts-cantonese
Version 1.0.0
License MIT-0
All-time Installs 1
Active Installs 1
Total Versions 1
Frequently Asked Questions

What is Edge Tts Cantonese?

Generate Cantonese TTS audio in OGG format using Microsoft Edge TTS for voice replies on WhatsApp and Telegram with adjustable tone styles. It is an AI Agent Skill for Claude Code / OpenClaw, with 107 downloads so far.

How do I install Edge Tts Cantonese?

Run "/install edge-tts-cantonese" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Edge Tts Cantonese free?

Yes, Edge Tts Cantonese is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Edge Tts Cantonese support?

Edge Tts Cantonese is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Edge Tts Cantonese?

It is built and maintained by Gabriel (@skglau); the current version is v1.0.0.

💬 Comments