Add read-aloud, auto-read, voice selection, and streamed long-response playback to DSH Web.
DSH integration
Native runtime
Author-claimed
Safety audit
Unaudited
Last verified
2026-09-25
License
MIT
01What can it help you accomplish?
Read assistant replies aloud in DSH
Read-aloud controls, auto-read, voice settings, and streamed long-reply playback
DSH Web users who want spoken assistant responses
02How to install into DeepSeek Harness
Prerequisites
- DeepSeek Harness `web` profile (`dsh web`)
- Node.js >= 22
Installation steps
- 01
Run `dsh plugin --profile web add "github:1624318455/dsh-plugin-tts#main"`.
$ dsh plugin --profile web add "github:1624318455/dsh-plugin-tts#main"
- 02
Restart `dsh web`.
$ dsh web
Verify the integration
- After restart, the plugin loads automatically as a profile bundle.
03DSH integration and capability boundaries
Host and Web UI text-to-speech plugin for DSH
Voice provider selection
Assistant text and a selected provider→Speech through Edge TTS, custom RVC, local Index-TTS2, local CosyVoice, or Google Cloud TTS
04Who is it for? When not to use it?
Good for
- DSH Web users who want spoken assistant responses
Not for
- RVC conversion is local, but Edge TTS sends the text to be read to Microsoft's endpoint for online synthesis.
05Compatibility, maintenance and safety notes
- RVC conversion is local, but Edge TTS sends the text to be read to Microsoft's endpoint for online synthesis.
README-backed author documentation
06Frequently asked questions
Does Edge TTS keep the text local?
No. The README says Edge TTS sends the text to Microsoft's endpoint for online synthesis, while RVC conversion is local.
Does the plugin require a separate model download?
The README says the default Edge TTS experience is small and does not require a service or model download; custom RVC voices have separate documented runtime requirements.
How does installation take effect?
Run the documented `dsh plugin --profile web add` command, then restart `dsh web`; the README says the plugin loads as a profile bundle.
07Related DSH workflows
vox-director
by alisa0808
Turn one topic into a finished Vox-style paper-collage explainer/ad video — automated end to end on Atlas Cloud + ffmpeg. An agent skill.
dsh-voice-ai-girlfriend
by beiyege-01
Voice AI girlfriend for DeepSeek Harness — Whisper voice input, voice cloning, streaming TTS and a digital-human avatar with interrupt mode.
dsh-voice-scribe
by pensivefei
DSH voice input plugin: tap Alt to talk, get text in composer. Web Speech default (zero config), optional OpenAI-compatible ASR, polish via DSH LLM.
dsh-voice
by goodandready
Voice input for DeepSeek Harness: dictation and voice messages with multi-provider STT fallback chains
08Data and sources
# dsh-plugin-tts — Edge TTS + RVC / Index-TTS2 / CosyVoice / Cloud voices for DeepSeek Harness
This page is generated from the project’s public documentation, repository metadata and a structured parse of DSH Plugins; last verified on 2026-09-25. Found an error? Submit a correction.
Best DeepSeek Harness Plugins
Twelve plugins worth installing first — picked from the whole catalog, across every category.