dsh-media-gen
Plan and execute Atlas Cloud image, video, audio, and 3D workflows in DeepSeek Harness.
66 results
Plan and execute Atlas Cloud image, video, audio, and 3D workflows in DeepSeek Harness.
Provider-neutral full-duplex voice Agent capability for DeepSeek Harness.
DSH 通知插件:设置页「通知」分区。任务完成 / 需要回答问题 / 权限审核 / 任务失败 四类事件的声音提醒(内置 6 种 Web Audio 合成音效 + 自定义音频)与企业微信群机器人、飞书自定义机器人(支持加签)消息推送。推送由宿主进程(Node fetch)代发,不受浏览器 CORS 限制。
Zero-config local vision and realtime audio routing for DeepSeek Harness
EVA Unit-01 desktop pet for the dsh web GUI: draggable full-body Unit-01 in the frame overlay, NERV sync-rate HUD driven by live session state, idle animations, berserk mode and synthesized SFX
DSH completion-sound bundle: a WebAudio chime plus optional long-task music (bundled "guan-yu" sample or a user-selected file/directory) and a cross-platform desktop notification when an agent turn finishes
音频比特率
DSH web plugin: speak into the composer — macOS native speech-to-text (Apple Speech framework) via a bundled Swift helper
声音提示插件:有工作需要手动选择/审查,或任务完成/失败时,播放系统提示音或自定义 wav
Media player for the dock file explorer: plays audio (MP3, WAV, OGG, FLAC, M4A, ...) and video (MP4, WebM, MOV, ...) files, with a music player for pure audio and fullscreen playback for video.
DSH 插件:在聊天记录中自动将本地音视频/图片路径渲染为可播放的预览组件。When an assistant message or tool result contains a local media path, the path is replaced inline with a playable <audio>/<video>/<img> element backed by same-origin /api/media-preview/* route.
The official Strudel REPL experience for DeepDeck with a sandboxed runtime and AI-assisted live coding
DSH plugin: speech-to-text input via microphone or file upload, transcribed through an OpenAI-compatible /v1/audio/transcriptions endpoint.
Web agent-heartbeat sonification for DeepSeek Harness: a calm lub-dub hum while agents work, ticks on streaming output, chime when a session awaits your input
长任务完成语音提醒插件:子任务完成响"嘟"、整轮完成响"叮",阈值/音量/多会话全局可配置(纯前端、零 host 改动)
DSH Web plugin: play a chime when the agent finishes a turn, with a settings page to enable it, pick the volume and upload your own audio file. Host-stored configuration, no core changes.
System-audio driven UI visualizer for DeepSeek Harness: a draggable 48-band spectrum chip plus a frame-wide bass glow (memory-only FFT).
让 DSH 的「轮次导航」导轨跟着系统正在播放的声音实时律动(Windows)。宿主端走 WASAPI 回环采集,零授权、不弹窗、不碰麦克风;浏览器端只注入 CSS 变量,不改动官方组件,关闭后完全恢复默认样式。