dsh-voice-core

Shared voice engine for dsh companion plugins (dsh-teacher, dsh-sister): Qwen3-TTS proxy, audio-queue playback, auto-read of assistant replies, speak/cheer tools, voice-style presets, and the daily greeting scheduler. Consumers compose it via a preset row and configure the voice style (e.g. 御姐 / 派蒙).

AI Analysis

核心用途是为其他陪伴插件（如 dsh-teacher、dsh-sister）提供底层的语音合成与播放能力。适合开发或定制语音陪伴插件的开发者。需要配置对应的事件注册与 TTS 路径。

Package

dsh-voice-core

Version

0.1.0

Last updated

Aug 16, 2026

配置示例

// dsh-teacher 的 apply()
import { applyVoice } from 'dsh-voice-core'

await applyVoice(ctx, {
  presetName: 'teacher',
  ttsPath: '/dsh-teacher/tts',
  styles: { onee: { label: '🎧 清冷御姐', instruct: '清冷柔和的成年女声…' } },
  defaultStyle: 'onee',
  schedulerEnabled: false,
})

// client 侧
import { createVoiceClient } from 'dsh-voice-core'

var voiceClient = createVoiceClient({
  presetName: 'teacher',
  ttsPath: '/dsh-teacher/tts',
  styles: { onee: { label: '🎧 清冷御姐', instruct: '…' } },
  defaultStyle: 'onee',
})
// 在 apply 里：voiceClient.apply(ctx)

dsh-voice-core

AI Analysis

Install

README

配置示例