dsh-voice-input

When using the DeepSeek Harness Web GUI for chatting, users often need to input text quickly, but typing can be inconvenient, especially in mobile or multitasking scenarios. Voice input offers a natural and efficient alternative. The dsh-voice-input plugin addresses this by adding a microphone button to the chat input field. With a click, users can start speaking, and the plugin uses the browser's built-in Web Speech API (supported in Chrome or Edge) to convert speech to text in real-time, automatically filling the input draft for further editing before sending. Its core capabilities include real-time speech-to-text transcription, language switching (such as Chinese, English, or auto mode), and optional auto-send functionality, all processed locally in the browser without requiring API keys or server-side changes, ensuring it is free and privacy-preserving. This plugin is ideal for all DeepSeek Harness Web GUI users, particularly those seeking efficient input or who cannot type frequently, enhancing the interaction experience on desktops and compatible browsers.