dsh-sound-lab
DSH 声音工坊插件,支持自定义对话事件音效、AI 角色语音生成及音效库上传管理,提供可视化点选界面、悬浮球和配置双持久化。
AI 分析
核心用途是提供一站式的声音自定义与角色语音生成。适合需要深度定制 AI 语音、管理音效库并进行可视化操作的用户。
安裝
$
npx -p @deepseek-ai/dsh dsh plugin --profile web add github:miiaowuwu/dsh-sound-lab說明文件
閱讀完整 README ↗Usage
- Add sounds: during development, put audio files in the repo
sounds/folder (see the directory tree above) — they are reconciled into the library automatically on startup. When installed, there is no need to hunt for the folder — open the settings dialog → Sound library → Upload, then pick a local file or drag & drop to import (it is copied into thesounds/folder of the install location automatically). You can also delete sounds from the list (bundled sounds are hidden, restorable anytime) or rename them via ✎. - Open the settings dialog: click the 🔊 floating ball
- Refresh the sound list: click "Refresh"; the plugin enumerates all audio files under
sounds/ - Configure triggers: for the four events (session end / options popup / permission request / stop), set 【enable + sound】independently — each dropdown offers "built-in chime / no sound / a specific sound" ("built-in chime" is a Web Audio arpeggio — no audio file required)
- Test sound: pick one in the "Test sound" dropdown (which includes a "built-in chime" option) and click ▶ to preview; selecting "built-in chime" or nothing previews the Web Audio arpeggio. Adjust volume with the slider (0–100%)
- In effect: the chosen sound plays automatically on matching events; a built-in beep plays as a fallback when nothing is selected or loading fails
Tip: drag the floating ball anywhere; it collapses into a half-ball at screen edges; switch between Whale Girl / Pure White / Pure Black under "Appearance"; position and config are saved automatically and survive restarts.