dsh-gsv
Run the following command in DeepSeek Harness:
dsh plugin install TaoruiLiu19/dsh-gsv
Paste the following prompt into your AI chat to install this plugin:
To install this plugin in DeepSeek Harness, use the command 'dsh plugin install TaoruiLiu19/dsh-gsv' with the full source address at https://github.com/TaoruiLiu19/dsh-gsv。
About this plugin
In the DeepSeek Harness ecosystem, users often need to convert text to speech, but cloud TTS services can introduce latency, privacy risks, or dependencies. The dsh-gsv plugin addresses these issues by integrating the GSV-TTS-Lite local engine, enabling fully offline and secure voice synthesis. It offers voice cloning, streaming synthesis, and auto-reading, enhancing interaction while simplifying engine management with one-click controls.
Its core capabilities include voice cloning that replicates target voices from reference audio; true streaming synthesis using SSE for low-latency, chunk-by-chunk processing; and reading features like one-click playback of assistant messages, auto-reading of replies with pause/resume options, and progress display. The voice settings panel provides visual configuration that takes effect immediately without restart.
dsh-gsv is ideal for DSH users who prioritize privacy and custom voice solutions. For example, content creators can clone specific voices for audio production; developers can build voice application prototypes with local TTS; and regular users enjoy secure, convenient reading services. Overall, it brings powerful local voice capabilities to the DSH ecosystem, advancing offline interaction scenarios.
Screenshots
Use Cases
- Real-time voice output in voice assistant development
- Content creators clone specific voices for audio production
- Auto-reading assistant replies to enhance interaction
Best For
- Developers building local voice applications
- Content creators customizing voice content
- Privacy-conscious users utilizing offline services
Related Plugins
ModLens is a vision plugin for DeepSeek Harness that gives text-only models sight by reading images pasted directly into chat, with zero-config setup and multiple vision engines.
On-demand vision for text-only DeepSeek Harness agents: built-in free keyless vision chain and 14 vision tools, routing image turns as tool calls to vision models with pixel fidelity, no Python needed, one-command install.
Give text-only models in DeepSeek Harness eyes, enabling image Q&A, long-screenshot OCR, UI restoration, and GUI visual tasks.
An armor-breaking plugin for DeepSeek: rewrites instruction priority, expands refusal-blocked phrases, persists across sessions, and shows a green active indicator.