End-to-end audio generation with ListenHub-Voice-1.0 (text / image → audio). Supports sound effects, multi-voice dialogue, reference-audio cloning, and a duration hint. Triggers on: "生成音频", "语音生成", "端到端音频", "图片转音频", "图片生成音频", "多音色对白", "参考音频克隆", "克隆音色", "音效生成", "生成音效".
安装
npx skills add marswaveai/skills --skill listenhub-voicenpx skills add marswaveai/skills --skill listenhub-voice -a claude-code -gnpx skills add marswaveai/skills --skill listenhub-voice -a codex -ggemini skills install https://github.com/marswaveai/skills.git --path listenhub-voicegh skill install marswaveai/skills listenhub-voicegit clone --depth 1 https://github.com/marswaveai/skills /tmp/marswaveai__skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/marswaveai__skills/listenhub-voice ~/.claude/skills/listenhub-voice # Claude Code
cp -R /tmp/marswaveai__skills/listenhub-voice ~/.agents/skills/listenhub-voice # Codex, Cursor, Gemini CLI, Copilot, OpenCode