Back to directory

dsh-dania-voice

Curated pickMaintenance: Active

xcw520/dsh-dania-voice

Local GPT-SoVITS TTS for DeepSeek Harness: reads assistant replies aloud with a draggable mascot and one-click installer.

View on GitHub
$ dsh plugin --profile web add dsh-dania-voice

16

stars

1

forks

JavaScript

Language

MIT

License

2026-10-18

Created

2026-10-24

Last push

Local TTS for DSH replies with browser playback and mascot controls.

DSH integration

Native runtime

Author-claimed

Safety audit

Unaudited

Last verified

2026-10-24

License

MIT

01What can it help you accomplish?

  • Listen to DSH assistant replies

    Locally synthesized speech played in the browser, with a draggable mascot for control

    DeepSeek Harness users who want spoken replies

02How to install into DeepSeek Harness

Prerequisites

  • DSH >=0.1.7-rc.1; Python 3.10–3.12; about 5 GB disk space

Installation steps

  1. 01

    Run `dsh plugin --profile web add dsh-dania-voice`.

    $ dsh plugin --profile web add dsh-dania-voice

  2. 02

    Open the mascot panel and click One-click setup.

Verify the integration

Not specified by the author

03DSH integration and capability boundaries

DSH integrationNative runtime

Local GPT-SoVITS speech for DSH assistant replies

  • Reply-to-speech pipeline

    Clean reply text, split it into at most 90-character segments and synthesize locally.

    Audio is cached by text and parameters.
  • Mascot playback controls

    Click to toggle reading; right-click or Shift-click to open settings.

04Who is it for? When not to use it?

Good for

  • DeepSeek Harness users who want spoken replies

Not for

  • The installer does not install Python. NVIDIA GPU with 8 GB+ VRAM is recommended; CPU works several times slower.
  • Short English identifiers may sound unclear; URLs and tables are omitted from speech.

05Compatibility, maintenance and safety notes

  • The installer does not install Python. NVIDIA GPU with 8 GB+ VRAM is recommended; CPU works several times slower.
  • Short English identifiers may sound unclear; URLs and tables are omitted from speech.
  • The panel writes configuration to $DSH_HOME/dania-voice/config.json; setup downloads the engine and models.
2026-10-182026-10-24Not specified by the author

README author claims

06Frequently asked questions

Does DSH speech use cloud TTS?

The README says text and audio stay on your machine; GPT-SoVITS runs locally. Setup still downloads source and models.

How do I configure voice playback in DSH?

Right-click or Shift-click the mascot to open its settings panel.

Why is DSH ready but silent?

The browser may block autoplay. The README says to click the mascot once.

08Data and sources

  • Author-claimedgithub.com27b29c16ad09…

    Local **GPT-SoVITS** text-to-speech for DeepSeek Harness.

  • Author-claimedgithub.com27b29c16ad09…

    It reads assistant replies aloud in a fine-tuned voice, controlled by a small draggable mascot hanging at the top of the…

This page is generated from the project’s public documentation, repository metadata and a structured parse of DSH Plugins; last verified on 2026-10-24. Found an error? Submit a correction.

🏆

Best DeepSeek Harness Plugins

Twelve plugins worth installing first — picked from the whole catalog, across every category.

AD

DSH Plugins is an independent community directory of DeepSeek Harness plugins. Not affiliated with or endorsed by DeepSeek. Third-party plugins are not security-audited — review the source before installing.

New DeepSeek Harness plugins, weekly. No spam.