DSH Realtime Voice Plugin
DeepSeek Harness (DSH) Realtime Voice is an official plugin that provides full-duplex voice interaction and interruption capabilities for the DSH system. Users can conduct voice conversations through the WebUI dial button or a standalone floating window, with support for real-time transcription, acoustic interruption, and model switching (Qwen Audio Realtime). The plugin adopts a "dual-plane" architecture that combines low-latency voice processing with the execution capabilities of the DSH Agent, using event subscription to implement a closed loop for task approval and progress tracking. It supports secure API key configuration without modifying source code or adding background processes. Developers can quickly install and use it via the CLI.
Read Moredsh-qwen-voice: Real-time voice control for DeepSeek Harness Web
# Introduction When developing with DSH Web, creating sessions, switching sessions, and dispatching tasks require step-by-step manual interaction on the page. To manage several sessions simultaneously, you have to switch back and forth in the sidebar. dsh-qwen-voice integrates real-time voice into the Harness page: you can create, continue, and schedule multiple named DSH sessions simply by speaking, and the voice connection remains uninterrupted when switching sessions. Below is an introduction to its features, installation steps, and usage considerations. # What is it dsh-qwen-voice (`leaveimagination/dsh-qwen-voice`) is an experimental voice control plugin for DeepSeek Harness Web, built upon Qwen Audio Agent. It uses...
Read More