Multi-role TTS Skill
v1.0.1Multi-role audio generator skill v1.0.1 全家桶版 - Universal professional tool for creating dialogue audio with multiple character voices.
⭐ 0· 82·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
medium confidencePurpose & Capability
Name/description (multi-role TTS) match the declared and used dependencies (edge-tts and ffmpeg). The Python script and shell tooling call edge-tts and ffmpeg as expected for TTS generation and audio processing.
Instruction Scope
SKILL.md and the included scripts instruct parsing a user-supplied dialogue script, calling edge-tts, applying ffmpeg filters, and composing outputs. They do not attempt to read unrelated system files or request secrets. Some legacy role-name prefixes remain in code for backward compatibility, but that's a functionality note, not scope creep.
Install Mechanism
Install uses standard package methods: pip install edge-tts and brew/apt/ yum for ffmpeg. The install script may install Homebrew via a curl | bash from the official Homebrew raw URL (common but worth noting). The script copies the repo into a system OpenClaw skills directory (uses sudo) and creates a /usr/local/bin symlink — expected for system-wide installs but requires privilege.
Credentials
The skill declares no required environment variables or secrets. Runtime tools (edge-tts) will perform network calls to the TTS provider as part of normal operation, but the skill itself does not request unrelated API keys or credentials.
Persistence & Privilege
The install script runs operations that require elevated privileges (sudo mkdir/cp/chmod, creating symlink in /usr/local/bin and writing into OpenClaw skills directories). This is proportionate for installing a system-wide skill, but users should be aware it writes into system locations.
Assessment
This package appears to be what it claims: a multirole TTS generator that calls edge-tts and ffmpeg. Before installing, review the repository locally and consider these points:
- The installer runs with sudo and will copy the entire repo into a system OpenClaw skills directory and create a /usr/local/bin symlink; run it only on systems where you trust the source.
- edge-tts will make network requests to Microsoft endpoints to synthesize speech; no credentials are requested by the skill, but network access is required.
- The install script bootstraps Homebrew via a standard curl | bash URL (common practice) — if you prefer, install dependencies manually (brew/apt/pip) and then run only the parts of install.sh you trust.
- package.json lists edge-tts as a dependency even though edge-tts is installed via pip (minor inconsistency) — nothing malicious but indicates the packaging is informal.
- If you need extra caution, run the install inside an isolated VM or container, or inspect/modify install.sh to avoid automatic sudo operations. If you plan to use it in production, review config/config.sh (if present) and verify any default mappings before running.Like a lobster shell, security has layers — review code before you run it.
audiovk9718f59kmmc3c0vwwt77qygj183n2bplatestvk97fbnk107dt8xvk5z4g5nzvg583mndqmultirolevk9718f59kmmc3c0vwwt77qygj183n2bpttsvk9718f59kmmc3c0vwwt77qygj183n2bpvoice-generationvk9718f59kmmc3c0vwwt77qygj183n2bp
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
Binsedge-tts, ffmpeg
Install
Install FFmpeg
Bins: ffmpeg