Text-to-speech conversion using `uvx edge-tts` for generating audio from text. Use when: (1) User requests audio/voice output with the "tts" trigger or keyword. (2) Content needs to be spoken rather than read (multitasking, accessibility, driving, cooking). (3) User wants a specific voice, speed, pitch, or format for TTS output.
Security Analysis
high confidenceThe skill is an instruction-only wrapper that tells the agent to call the uvx command-line tool to produce Edge (Microsoft) neural TTS audio; its declared requirements and runtime instructions are coherent and proportionate to that purpose.
Name/description and SKILL.md consistently describe using the 'uvx edge-tts' CLI to generate TTS. The only declared runtime dependency is the uvx binary, which is exactly what the instructions call for.
Instructions are limited to invoking uvx with arguments to write media and subtitles to a supplied temp path and to list voices. The SKILL.md does not instruct the agent to read unrelated files, environment variables, or system-wide config. Placeholders ({msg}, {tempdir}, {filename}) are used as expected.
There is no install spec (instruction-only), so nothing is downloaded or written by the skill itself. This minimizes installation risk, but it requires the uvx binary to already be present on the host.
No environment variables, credentials, or config paths are requested. That aligns with a CLI wrapper that simply calls an existing local binary.
always is false and the skill has no install or config-writing steps. It does not request elevated or persistent platform privileges.
Guidance
This skill is coherent but requires you to provide and trust the uvx binary. Before installing/using: (1) verify where uvx comes from and install it from the official/trusted source; (2) confirm uvx's runtime behavior — some uvx/edge-tts implementations may launch a browser or use local Edge profile tokens to obtain Microsoft auth, which could interact with your browser profile or network; (3) be aware that Edge neural TTS may send text to Microsoft services, so avoid sending sensitive text if you have privacy concerns; (4) the skill has no homepage or source link, so test in a sandbox first and inspect uvx itself rather than relying on this SKILL.md.
Latest Release
v1.0.0
Initial release of edge-tts-uvx. - Provides text-to-speech audio generation using Microsoft Edge's neural TTS via the uvx edge-tts command-line tool. - Supports multiple languages, a wide range of voices, and options for adjusting speed, pitch, and volume. - Enables generation of speech subtitles. - Includes usage instructions and a detailed list of available voices.
Popular Skills
Published by @al-one on ClawHub
