{"skill":{"slug":"voice-reply-mode","displayName":"Voice Reply Mode","summary":"Enables agents to reply in the same modality as received: voice messages get voice replies, text messages get text replies, using Edge TTS and config snippets.","tags":{"latest":"1.0.0"},"stats":{"comments":0,"downloads":343,"installsAllTime":2,"installsCurrent":2,"stars":0,"versions":1},"createdAt":1773239578221,"updatedAt":1777525862962},"latestVersion":{"version":"1.0.0","createdAt":1773239578221,"changelog":"Voice Reply Mode（语音对语音 / 文本对文本）\n\n让 agent 实现：语音进 → 语音出，文字进 → 文字出。\n包含工作区行为规则（SOUL/IDENTITY/TOOLS 片段）、Edge TTS 辅助脚本、以及 messages.tts 网关配置示例。\n适用于 Telegram / 飞书语音消息场景，按文档复制配置即可启用同模态回复。\n\n使用步骤\n\n1. 阅读 references/workspace-snippets.md 与 references/gateway-config.md\n2. 将片段写入目标 agent 的 SOUL.md / IDENTITY.md / TOOLS.md\n3. 如需自动语音回复，设置网关：messages.tts.auto = inbound\n4. 用 一条文字 + 一条语音 验证效果\n\n───\n\nVoice Reply Mode (Same‑Modality Reply)\n\nEnables voice‑in → voice‑out, text‑in → text‑out behavior for agents.\nIncludes workspace behavior snippets (SOUL/IDENTITY/TOOLS), an Edge TTS helper script, and gateway config examples for messages.tts.\nDesigned for Telegram/Feishu voice‑note workflows—copy the snippets and it just works.\n\nQuick Steps\n\n1. Read references/workspace-snippets.md and references/gateway-config.md\n2. Copy snippets into the target agent’s SOUL.md / IDENTITY.md / TOOLS.md\n3. For auto voice replies, set messages.tts.auto = inbound\n4. Validate with one text + one voice message","license":"MIT-0"},"metadata":null,"owner":{"handle":"nasplycc","userId":"s17awvdy31r2yyyb547xqanc4183kzk1","displayName":"nasplycc","image":"https://avatars.githubusercontent.com/u/257000910?v=4"},"moderation":null}