ClawHub

Feishu Edge Tts Cn

v1.0.5

Edge-TTS 在线语音合成 skill。基于微软 Edge TTS 引擎，生成速度快（1-2秒），支持多种音色和输出格式，默认输出 OGG/Opus。默认音色 xiaoxiao_lively。需联网。

⭐ 0· 51·0 current·0 all-time
byitian@itian932
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Pending
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name/description match the actual implementation. The code invokes the edge-tts library and ffmpeg to generate and transcode audio; both are appropriate and expected for an online Edge-TTS skill.
ℹ
Instruction Scope
Runtime instructions and entrypoint (scripts/engine.py) stay within TTS functionality. The skill performs network calls via edge-tts to Microsoft's online TTS service (SKILL.md states '需联网'); this is expected but has privacy implications because the input text is sent to an external service.
✓
Install Mechanism
There is no platform install spec; an included install.sh installs edge-tts via pip and checks for ffmpeg. Using pip from PyPI is normal here (moderate trust surface); the installer does not download arbitrary archives from unknown hosts.
✓
Credentials
The skill declares no required environment variables or credentials. It reads its bundled config/voices.json and writes outputs to local tmp/workspace directories as documented — these are proportional to the stated task.
✓
Persistence & Privilege
Flags show no forced always-on behavior and the skill does not modify other skills or global agent config. It only writes temporary media files to user/workspace paths as documented.
Assessment
This skill appears to be what it claims: an Edge (Microsoft) online TTS wrapper that uses the edge-tts Python library and ffmpeg. Before installing, consider: 1) Privacy: your input text will be sent to Microsoft's TTS endpoints (the SKILL.md explicitly says it needs network). Don't send sensitive secrets or personal data through it if that is a concern. 2) Package trust: the installer uses pip to install edge-tts from PyPI — review the edge-tts project (and its transitive dependencies) if you need to satisfy corporate supply-chain policies. 3) Runtime permissions: it will write files under /tmp and your home workspace (the install/test writes to ~/.openclaw/workspace/tmp and default outputs to /tmp/openclaw) — run installation in a sandbox if you want to limit filesystem exposure. 4) ffmpeg is required and invoked via subprocess; ensure your ffmpeg binary is from a trusted source. If you need higher assurance, review the edge-tts library source and/or run the skill in an isolated environment.

Like a lobster shell, security has layers — review code before you run it.

latestvk979zqm29k3697ttwzqcptw9zx846z3q

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments