dsh-listener
安全版本地语音输入插件 for DeepSeek Harness:输入框右侧麦克风按钮,录音后经同源宿主代理转写(本地 SenseVoice-Small INT8 ONNX,音频不出网)。后端仅绑定 127.0.0.1 + 随机 token,无 CORS,模型 sha256 校验。
34 results
安全版本地语音输入插件 for DeepSeek Harness:输入框右侧麦克风按钮,录音后经同源宿主代理转写(本地 SenseVoice-Small INT8 ONNX,音频不出网)。后端仅绑定 127.0.0.1 + 随机 token,无 CORS,模型 sha256 校验。
Speech suite for DeepSeek Harness: free edge-tts page announce, speech-to-text voice input (Bailian paraformer-realtime-v2) with Alt+Q hotkey, tap/hold modes, auto-send, and stop-playback-on-record
DSH WebUI 语音输入插件(火山引擎流式 ASR / 豆包 Seed ASR):输入框麦克风按钮(Alt+V)→ 浏览器采集 16kHz PCM → 经宿主 WebSocket 中继到豆包流式识别 → 实时回填(跟随光标/Proma 式输出,失败兜底剪贴板)。协议实现源自 Proma 桌面端调研复刻。
SenseVoice 语音输入插件 for DeepSeek Harness:在对话输入框旁添加麦克风按钮,录音后调用本地 SenseVoice 服务转成文本填入输入框。首次使用自动下载模型并显示进度,后端由插件自动启动。
Voice input for DeepSeek Harness: hold Space in any editable field to speak, release to insert the transcript at the caret. Zero dependencies, browser Web Speech API. / 语音输入:在输入框长按空格键说话,松开自动上屏。零依赖,基于浏览器 Web Speech API。
Editable local and desktop dictation for DeepSeek Harness
Voice input for DeepSeek Harness: a microphone seat inside the composer plus a Web settings page, transcribing through the browser engine or any OpenAI-compatible /audio/transcriptions endpoint.
Wake-word voice input for DeepSeek Harness: an always-on, low-power keyword spotter wakes the agent, then local ASR turns what you say next into a submitted message. No API key, no cloud, no typing.
Voice control for DSH web: speech-to-text into the composer (with auto-send) and spoken playback of assistant replies via the Web Speech API
Voice input plugin (dual-face): mic button beside the composer send action, live recording bubble streaming PCM to a local Qwen3-ASR python service managed by the host, plus an ASR environment settings page (clone runtime/model repos, create venv, run server). Bilingual UI (zh/en)