SAM TTS

Generate retro robotic speech audio using SAM (Software Automatic Mouth), the classic C64 text-to-speech synthesizer. Use for /sam command to generate voice messages. Supports /sam on/off toggle mode where all responses are spoken in SAM voice. Supports pitch, speed, mouth, and throat parameters for voice customization.

This skill appears to do exactly what it claims: local SAM TTS via a Node.js wrapper calling the sam-js npm package. Before installing: (1) review the sam-js package on npm/GitHub to ensure you trust that dependency (supply-chain risk exists for any npm package); (2) run npm install in a sandbox or CI with npm audit if possible; (3) be aware that enabling “SAM mode” causes the agent to call the Node script for every response (performance and file I/O implications) and that the skill will create/update memory/sam-mode.json and write WAV files to the provided output paths; (4) the skill warns to ask before installing ffmpeg — require explicit user approval if conversion tools are needed. No credentials or network endpoints are requested by the skill itself.

Type: OpenClaw Skill Name: sam-tts Version: 1.0.0 The skill provides text-to-speech functionality using the `sam-js` Node.js library. While the `SKILL.md` instructs the agent to pass user-provided text to a Node.js script (`scripts/sam-tts-wrapper.js`), the script itself processes this input as data via a JavaScript function call (`sam.buf8()`), not as a shell command. This design prevents shell injection vulnerabilities. The skill's file system access is limited to temporary WAV files in `/tmp` and its own state file (`memory/sam-mode.json`). The `SKILL.md` also explicitly instructs the agent to seek user consent before installing optional dependencies like `ffmpeg`, demonstrating good security practice. No evidence of data exfiltration, persistence, or other malicious intent was found.