Speak
PassAudited by ClawScan on May 1, 2026.
Overview
This instruction-only skill appears aligned with configuring voice output, with user-noticeable notes around saving voice preferences and optional paid TTS API keys.
This skill looks safe to install for TTS setup. Before using it, decide whether you want preferences saved over time, confirm any configuration changes, and be careful when adding paid provider API keys.
Findings (3)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Your voice-output preferences may be saved and reused in later conversations.
The skill is intended to store learned voice and style preferences for reuse, creating persistent context that should remain limited to TTS preferences.
This skill auto-evolves. Learn how the user wants to be spoken to and configure TTS accordingly.
Only store stable, non-sensitive speaking preferences, and review or clear the saved preference sections if they become inaccurate.
The agent may help change TTS settings such as provider, voice, or auto-speaking mode.
The skill documents a configuration-changing operation for TTS settings; this is purpose-aligned, but it can alter how and when audio output is generated.
Use gateway config.patch to update TTS settings without full restart.
Confirm provider, voice, and auto mode before applying TTS configuration changes, especially if using paid providers.
If you choose OpenAI or ElevenLabs TTS, you may need to provide an API key that could incur usage charges.
The reference configuration includes optional API keys for TTS providers, which is expected for those services but still involves credential handling.
openai: apiKey: "sk-..." ... elevenlabs: apiKey: "..."
Use only the provider keys you intend to use, keep them private, and monitor provider billing or usage limits.