Voice Reply

What to consider before installing: - The package is missing the runtime wrapper/driver that SKILL.md claims ({baseDir}/bin/voice-reply). Ask the author or check for the missing executable; otherwise the install will provide sherpa and models but not the skill entrypoint. - The installer requires sudo and writes to /opt; be prepared for system-wide changes and apt installs (ffmpeg). Consider running in a disposable VM or container if you want to limit impact. - Downloads come from GitHub releases (expected) but the script does not verify checksums. If you care about supply-chain integrity, verify release checksums from the upstream project before running the installer. - Confirm license/usage terms of the voice models you download and that disk/RAM requirements (mentioned in README) are acceptable. - If you need the promised [[audio_as_voice]] output semantics, verify or obtain the missing wrapper script that produces the MEDIA:/tmp/... and tag lines. - If you are unsure about running arbitrary install scripts as root, request a fuller source (the missing runtime script) or run the installer in an isolated environment and inspect files under /opt after install. Given the missing runtime component and the need for root installs without checksum verification, treat this package with caution until the runtime wrapper is provided or you verify the installer outputs and downloaded artifacts.