Custom TTS using Gemini 2.5 Flash for high-quality, persona-driven voice output.

This skill appears to be a simple Gemini TTS client, but there are a few red flags to address before installing: (1) The script and SKILL.md require GEMINI_API_KEY but the registry metadata does not declare it — assume you must supply a sensitive API key. Only provide a key with minimal permissions and rotate it after testing. (2) The script sends the API key in the URL query string, which can expose it in logs; prefer using an Authorization header (Bearer token). (3) The --voice argument is ignored and the code hard-codes a specific prebuilt voice — verify the voice selection works as you expect or update the code. (4) The script writes audio files to the current directory; run it in a sandboxed workspace to avoid accidental overwrites. (5) Confirm the endpoint (generativelanguage.googleapis.com) is the intended Google API for your account and that billing/quotas are acceptable. If you want to proceed, ask the publisher to update the registry metadata to declare GEMINI_API_KEY and to fix the hard-coded voice and API key handling so the skill’s declared requirements match its behavior.

Type: OpenClaw Skill Name: gemini-tts Version: 1.0.0 The skill is a legitimate implementation of a Text-to-Speech (TTS) generator using the Google Gemini API. The script `generate_voice.py` correctly handles environment variables for authentication, makes standard API calls to the official Google endpoint, and processes the resulting audio data without any signs of malicious intent, data exfiltration, or obfuscation.