dsh-voice-input：在 DSH Web 对话里本地离线语音转文字
dsh-voice-input 是 moazzamak 维护的 DSH 社区插件，面向 web profile 的 Web GUI 对话输入框。浏览器录音后把音频交给本机 harness，用 faster-whisper（默认 CPU）或 whisper.cpp/Vulkan（可选 GPU）离线识别，文本追加到草稿且不自动发送。支持 warm 模型、静音切分下的边说边出字，以及可选的 cleanup 去口语 filler。安装需 dsh plugin --profile web add github:moazzamak/dsh-voice-input 并运行包内 python/setup.py。适合重视隐私、在本机跑 Whisper 的 DSH 用户；使用前请核对源码与 MIT 许可证。
Read MoreIntroduction to the DeepSeek Harness Voice Input Plugin
`dsh-voice-input` is a local speech-to-text plugin for DeepSeek Harness. Built on FunAudioLLM's SenseVoice model, it integrates microphone support into the Web Profile to automatically transcribe recordings. It does not upload audio to the cloud, helping protect privacy. Installation requires Python 3.10+ and Node.js >= 22.19.0. The plugin supports one-click recording, automatic model download management, and background service startup. The first use requires waiting for the model download, and the project is released under the MIT open-source license.
Read Moredsh-voice-input: System-Level Voice Input
`dsh-voice-input` is a plugin for DeepSeek Harness, designed to enable global voice transcription in non-plugin environments. It leverages a local Whisper model to transcribe speech into text in real time via hotkeys and paste it at the cursor position. Installation requires running DSH with administrator privileges. Main features include holding F2 for voice transcription, pressing F3 to record audio only, and managing the history through the system tray. The plugin supports configuring the recognition mode, language, and device, and requires downloading approximately 2.5GB of dependencies and models upon first use.
Read Moredsh-voice-input: DSH Local Voice Input Plugin
The DeepSeek Harness voice input plugin, `dsh-voice-input`, is designed to provide a local, streamlined, and precise speech-to-text experience. It integrates a local Whisper engine, enforces output in Simplified Chinese, and features hallucination prevention, privacy protection, optimization for users in China, and high performance. On first use after installation, it automatically downloads a model of approximately 500 MB. It supports click-to-record transcription via the microphone icon and also allows switching to a cloud API. It is suitable for users who find typing inconvenient or who prioritize privacy.
Read Moredsh-voice-input: Chinese-English Voice Input Plugin for DeepSeek Harness Web
DSH (DeepSeek Harness) implements web-based voice input through the `dsh-voice-input` plugin. The plugin is built on the browser-native Web Speech API, requires no server-side support or API key, and supports speech recognition for Chinese, English, and mixed-language speech. Users can click the microphone icon to the left of the web input field to start speaking, and the recognized text is automatically inserted into the input field. This plugin is suitable for quickly capturing ideas or entering conversational instructions, but recognition accuracy depends on the browser’s speech service, and it must be used in a browser that supports the Web Speech API, such as Chrome or Edge.
Read Moredsh-voice-input: Voice Dictation and Transcription Cleaning Plugin for DeepSeek Harness
# Introduction In DeepSeek Harness, the content entered into the composer is often colloquial: supplementing context, describing requirements, and stating constraints. Speaking is faster than typing, but the resulting transcription is raw—it contains filler words, repetitions, and mid-sentence corrections. Manual cleanup is required before pasting it into the input box. The approach of **dsh-voice-input** is to separate these two steps: use browser or system dictation for recording, and delegate text cleaning to the model currently selected for the current session, without the need to configure an additional API key. The following sections introduce the plugin's positioning, installation methods, and daily usage. # What is this? **dsh-voice-input** is an open-source plugin maintained by lhenlihai-hub.
Read Moredsh-voice-input: A Voice Input Plugin for DeepSeek Harness Web UI
forrestahha/dsh-voice-input is a speech-to-text plugin for the DeepSeek Harness Web UI, released under the MIT license. It adds a microphone entry in front of the composer's send button and uses the browser's Web Speech API to stream recognition results into the current draft, without automatically sending the message—users confirm and send manually. The plugin supports both the standard and WebKit-prefixed SpeechRecognition interfaces, defaults to Chinese as the fallback language, and optimizes whitespace handling for both CJK and Latin text. Installation requires no additional API keys or backend services; the plugin can be added to a Web profile via the `dsh plugin` command. It is primarily intended for use with Chromium and other browsers that support
Read More