dsh-voice-suite
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
199 results
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
多模型候选评审管线:调度智谱 GLM / Claude(CLI 无头,可走中转)/ Gemini(OpenAI 兼容口)/ Codex 四视角评审成长 artifact(教训/规则/审计板),输出严格 JSON(verdict/strengths/risks/suggestions/cannot_claim),结果只作 candidate_review_input,永不替代本地证据。适用:用户要求外部交叉评审、周期性仪式前自动评审、怀疑某条结论过度推广时。
Custom provider enhancements: User-Agent override, reasoning-level switching, and image-input declaration for DSH custom providers · 自定义供应方增强:UA 覆盖、推理等级切换、图片输入声明。
DSH web plugin: open an input dialog to create/switch to a workspace by path.
DSH input recorder & analyzer: local text capture (keyboard + UIA), daily/weekly stats, topic analysis and report export for daily reports. Privacy-first: local-only, password fields excluded, sensitive data redacted.
Local OCR for DSH: handwritten Chinese and math formulas to Markdown with LaTeX. GPU (DirectML) / CPU / NPU backends, settings-driven, one-click install.
DSH session model selector with search and reasoning-effort pane: shadows the native conversation.input.model seat (independent cordis client plugin).
DSH web plugin: desktop notification, chime, and title flash when a session stops — finished output or waiting for human input. Click a notification to jump to that session.
Voice input for DeepSeek Harness: dictation chunked by pauses and voice messages, each with its own provider fallback chain (Deepgram, Groq, HuggingFace, local whisper.cpp, plus any OpenAI-compatible API of your own).
DSH (DeepSeek Harness) web 消息增强插件:① 会话区左侧/右侧丝滑悬浮指令导航条(Codex 风格,可配置位置),刻度覆盖本地会话完整历史(含未加载部分,点击即加载更早并定位),滚动联动定位、悬停预览指令内容;② 输入框 ↑/↓ 键历史消息穿梭,像终端命令历史一样把已发送内容快速回填到输入框。
Arrow-key input history for DSH 0.1.2-alpha.1: press ↑ in an empty composer (or at the start of the draft) to recall this session's prompts, ↓ to go forward, Esc to restore what you were typing.
Git status badges for DeepSeek Harness: sidebar workspace rows (via the sidebar.workspaces.row seam) and an input-row chip showing the current conversation's workspace git state. Event-driven freshness over SSE.
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。
DeepSeek Harness plugin: LLM model selection & deployment analysis (deployability, VRAM, TTFT, latency, throughput, power for 38 models × 20 GPUs/NPUs)
DSH web plugin: plays opencode sound effects on task completion/failure/input-request with a native Settings panel (45-sound pack, per-event picker + on/off switch, preview, volume).
图片转文字输入插件:给无视觉能力的纯文本 LLM(DeepSeek 等)提供图片输入接管。输入框粘贴/拖拽图片后一键转为结构化文字描述;视觉 API 配置在设置页填写,支持任意 OpenAI 兼容视觉模型(qwen-vl / gpt-4o / glm-4v 等)。多模态模型下自动让位,不劫持原生图片通道。
Configure model input capabilities and reasoning efforts for DeepSeek Harness
在 DSH prompt 输入框按上/下方向键切换最近发送过的消息(终端式历史导航),跨会话持久化。 | Terminal-style prompt history navigation for the DSH composer: ArrowUp/ArrowDown cycles through recently sent messages, persisted across sessions.
Ring a real system sound when a DeepSeek Harness agent finishes a task OR needs your input: custom sounds, 4 intensity levels, auto escalation, and a settings card in the GUI.
Standalone pluggable March 7th (Honkai: Star Rail) skin for the dsh web GUI: theme tokens, night background, and character art flanking the input. Not part of the default web-app — add this package to a profile bundle to enable.
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。
Input assistant for DeepSeek Harness Web UI: inline AI completion (FIM ghost suggestion, Tab to accept) and Chinese-friendly typo checking with click-to-fix.
Prompt polish ✨ — a DeepSeek Harness WebUI plugin that adds a one-click button to rewrite rough input into a structured, professional prompt, written back into the input box.