dsh-dania-voice
达妮娅（鸣潮）语音朗读 — 使用本地 GPT-SoVITS 朗读 DSH 的助手回复，并提供一个可拖动的吉祥物开关。
插件会安装到这里；不确定时保持 web。
npx -y @deepseek-ai/dsh plugin --profile web add dsh-dania-voice@1.0.0Dania Voice 以 dsh-dania-voice 发布，当前版本为 1.0.0。Plugin Hub 会校验它的 manifest，并保存精确安装来源，便于复现安装结果。
English | 简体中文
Local GPT-SoVITS text-to-speech for DeepSeek Harness. It reads assistant replies aloud in a fine-tuned voice, controlled by a small draggable mascot hanging at the top of the interface.
Everything runs on your machine — no audio, no text leaves it.
DSH session events (assistant/message + turn/end)
│ take the final reply text, strip code blocks / tables / links
▼
Host: clean + merge into ≤120-char segments
│ POST http://127.0.0.1:9880/tts
▼
GPT-SoVITS api_v2.py (local, GPU)
│ wav → cache dir → queue
▼
Browser: poll /dania-voice/next → Web Audio playback
Playback happens in the browser on purpose: the Host process has no audio device, and the voice should come out of the machine you are actually sitting at.
| Item | Note |
|---|---|
| DSH | >= 0.1.7-rc.1 |
| Python | 3.10 – 3.12 (the installer looks for it; it does not install Python) |
| GPU | NVIDIA with 8 GB+ VRAM recommended. CPU works but is several times slower. |
| Disk | ~5 GB (PyTorch + base models + voice model) |
dsh plugin --profile web add dsh-dania-voice
Then open the mascot panel and click One-click setup. The installer runs as a separate process and reports progress into the same panel:
nvidia-smi is present)It is idempotent — if it fails halfway, click again and completed steps are skipped. That matters because step 5 is a 1.6 GB download.
The default install directory is $DSH_HOME/dania-voice. Override it with installDir if you
want it on another drive.
A mascot hangs at the top centre of the window:
Panel controls: volume, speed, temperature (lower = steadier, less breathiness), inter-sentence pause, plus repeat last reply and say a line for testing.
Changing speed/temperature applies to the next synthesis; audio is cached by text + parameters,
so repeating with the same settings is instant.
Written to $DSH_HOME/dania-voice/config.json by the panel. The config: block in your profile
patch works too and is overridden by the panel.
| Key | Default | Meaning |
|---|---|---|
enabled | true | Master switch |
volume / speed / temperature | 1 / 1 / 0.7 | Playback and sampling |
speakUser | false | Also read your own messages |
installDir | $DSH_HOME/dania-voice | Where the engine lives |
pythonPath / root / cacheDir | derived | Only needed for a hand-made install |
baseUrl | http://127.0.0.1:9880 | GPT-SoVITS endpoint |
autostart | true | Start the service when needed |
$DSH_HOME/dania-voice/install.log.This is a fan project. Wuthering Waves and its characters belong to Kuro Games.