Smart Speak Multilingual TTS

Multilingual Text-to-Speech (TTS) with intelligent Pinyin-to-Hanzi conversion. Use when the user asks to generate audio for text that contains a mix of Vietn...

This skill is suspicious because its documentation promises automatic Pinyin→Hanzi conversion and segmentation, but the included script only synthesizes audio for segments you must supply. Before installing or running: (1) ask the author to clarify where Pinyin detection/conversion is implemented or provide the code; (2) do not run the script as-is if it references another user's home (/home/jackie_chen_phong) — update paths to your workspace; (3) ensure edge-tts and ffmpeg are installed from trustworthy sources and update the script to point to their correct locations; (4) when invoking the script, avoid interpolating raw JSON into a shell command (prefer passing arguments safely) to prevent injection; and (5) inspect and test the script in an isolated environment first. If the author cannot justify the hardcoded paths or provide the missing conversion logic, treat the package as untrusted.

Type: OpenClaw Skill Name: smart-speak-vutran Version: 1.0.0 The skill bundle provides a legitimate multilingual text-to-speech (TTS) utility that handles Vietnamese, Chinese (Pinyin), and English. The core logic in `scripts/smart_speak.py` uses `edge-tts` and `ffmpeg` to generate and merge audio segments via safe `subprocess.run` calls, avoiding shell injection. While the code and `SKILL.md` contain hardcoded absolute paths specific to a particular user environment (`/home/jackie_chen_phong/`), which limits portability, there is no evidence of malicious intent, data exfiltration, or unauthorized access.