Generate voiceover audio using local VoxCPM2 TTS model with voice cloning.
TRIGGER when the user says anything about: 配音, 配音, 语音合成, TTS, voice clone,
voiceover, 克隆声音, 音色设计, 用我的声音, 朗读文案, 生成语音, 音频克隆, 语音生成,
or asks to turn text into speech / narration / voiceover.
This skill handles the entire workflow: locating the TTS integration package,
configuring reference audio, generating voice clone or voice design audio,
and saving output files.
Use this whenever the user wants to generate spoken audio from text, even if they
don't explicitly mention "TTS" — if they want narration, voiceover, or cloned voice,
this skill applies.
2026-05-27