Free, unlimited text-to-speech using Microsoft Edge neural voices via Python edge-tts. Use when generating long-form audio, podcasts, voice notes, spoken bri...
Security Analysis
medium confidenceThe skill does what it claims (wraps the Python edge-tts package via a small shell script) and does not request unrelated credentials or perform obvious exfiltration, but it auto-installs Python packages globally and makes platform-specific path assumptions that you should review before use.
Name/description (unlimited Edge TTS via edge-tts) match the included script and instructions. The script invokes edge-tts with expected options (voice, rate, file/text, list voices). No unrelated services, credentials, or binaries are required.
SKILL.md simply instructs running scripts/speak.sh with text or file. The script only reads an optional input file you provide, writes output to a specified path (default /tmp), lists voices, and invokes edge-tts. It does not attempt to read unrelated system files or environment variables.
There is no formal install spec, but the script will auto-install the PyPI package edge-tts by running 'pip3 install -q edge-tts' when edge-tts is not available. This is a dynamic, on-demand install from PyPI (not a vetted release host) and does not create or use a virtual environment; it may install packages into the global environment. The script also prefers a 'uv' runner if present, checking hard-coded paths (/data/clawd/.local/bin/uv, /home/node/.local/bin/uv, ~/.local/bin/uv).
The skill declares no required env vars or credentials and the script does not read credentials. It only references optional input files you pass and writes outputs to an output path. The lack of credential requests is proportionate to the TTS purpose.
always is false and the skill does not request persistent agent-level privileges. It does not modify other skills or global agent configuration. The main privilege is that it can install a Python package on first run (see install_mechanism note).
Guidance
This skill is internally consistent for its stated TTS purpose, but review these points before installing or running it in a shared environment: - It may run 'pip3 install -q edge-tts' automatically and without a virtual environment, which can modify the host Python environment. Prefer running it inside a container, dedicated VM, or create a Python virtualenv before running. - The script suppresses installer output and errors (redirects to /dev/null), which can hide installation problems—inspect logs or run manually the first time to confirm behavior. - The script checks specific local paths (/data/clawd/.local/bin/uv, /home/node/.local/bin/uv); if those are present on your system they will be used. Ensure those binaries are trustworthy. - If you need stricter isolation, install edge-tts yourself from a trusted environment, pin package versions, or run the script inside an ephemeral container. If you want a safer review, provide the environment where you plan to run this (local machine, shared server, Fly.io, etc.) and whether you prefer a version-pinned Python install or a containerized deployment.
Latest Release
v1.0.1
Fixed skill metadata and republished a clean release. Removed unsupported frontmatter fields, tightened the skill description, and re-verified the bundled speak.sh long-form Edge TTS workflow.
More by @dannyshmueli
Published by @dannyshmueli on ClawHub
