speaker-local

Text-to-speech using Kokoro local TTS. Use when the user wants to convert text to audio, read aloud, or generate speech.

This skill appears coherent and limited to running a local Kokoro TTS CLI. Before installing or running anything: (1) verify the GitHub release URLs point to the official kokoro-tts repo and check release signatures/SHA256 if available; (2) inspect the installer `uv` (what it is and where it comes from) before running `uv tool install kokoro-tts`; (3) run the tool and downloaded model files in a sandbox or VM if you are unsure; (4) confirm you have sufficient disk space and the required Python version; and (5) review the kokoro-tts project's license and privacy/security notes if you will process sensitive text. These checks will reduce risk from running downloaded binaries or large model files.

Type: OpenClaw Skill Name: sayit Version: 1.0.0 This skill is classified as benign. Its purpose is to provide local text-to-speech functionality using the `kokoro-tts` tool. The `SKILL.md` file clearly describes its function and provides standard installation instructions, including `uv tool install kokoro-tts` and `wget` commands to download model files from the official GitHub repository (github.com/nazdridoy/kokoro-tts). All actions are transparent, directly aligned with the stated purpose, and lack any indicators of malicious intent such as data exfiltration, unauthorized execution, persistence mechanisms, or prompt injection attempts against the agent. The `reference.txt` file provides only documentation.