Voice-feedback plugin for DeepSeek Harness: a speak tool where the model decides what to say aloud, readReplies verbatim narration, an LLM verbalizer pass that summarizes each reply with emotional framing, per-session voice assignment, chimes, a monitoring panel, and a native macOS floating pet. zh/en i18n.
This plugin has not published an npm package, so the store does not offer an install command yet. Use the repository link below to view the source.