CroissanTTs/dsh-voice-mini ↗★ 0

dsh-voice-mini

为 DSH 提供语音播报、朗读回复、每会话音色与提示音等语音反馈。 适合希望听语音反馈或朗读回复的用户;含 macOS 悬浮宠物。

包名
dsh-voice-mini
兼容性
待验证
Cordis 依赖范围
^4.0.1
版本
0.3.4
许可证
MIT
最近更新
2026年9月17日

安装

$npx -p @deepseek-ai/dsh dsh plugin --profile web add github:CroissanTTs/dsh-voice-mini

Configuration

Key fields (all overridable from the settings modal or POST /voice-mini/config):

FieldDefaultPurpose
presetdefaultinstant / default / quiet
backendedgeedge / kokoro / say / fake
voiceModeper-sessionper-session auto-assign or fixed
voicePalette[]custom voice pool; empty = engine default (8 zh 4F4M + 2 en)
readRepliesfalsenarrate messages verbatim
chimeEnabled / chimeSpeech / chimeStatustrue / glass / softearcon system
statusSpeechtruequiet preset: chime-only (false) vs. spoken (true)
phraseTurnEnd""custom completion phrase; {title} = workspace dir name; empty = locale default
localezhzh / en — switches UI, spoken phrases, verbalizer prompt
summarizeResult / summarizeProvider / summarizeModeltrue / "" / ""verbalizer pass (empty provider = auto-detect first adapter; empty model = stays on the template phrase until you pick one in the panel)