Smart Telegram reply workflow for OpenClaw: if the user sends text, reply with text; if the user sends a voice note/audio, transcribe locally using the installed mlx_audio (default Qwen3-ASR on Apple Silicon), then generate a meaningful reply in the same language. Send back a Telegram voice note with a caption so the user receives ONE message containing both voice+text (the caption text must match the voice content exactly). Follow the input language (Chinese→Chinese, English→English) unless the user explicitly requests a different language.

OpenClaw 的智能 Telegram 回复流程：若用户发送文本，则回复文本；若用户发送语音或音频，则利用本地安装的 mlx_audio（Apple Silicon 默认使用 Qwen3-ASR）进行本地转录，随后以相同语言生成有意义的回复。通过 Telegram 发送包含字幕的语音消息，确保用户收到一条同时包含语音和文字的消息（字幕文本须与语音内容完全一致）。除非用户明确要求其他语言，否则始终遵循输入语言（中文→中文，英文→英文）