dsh-live-voice
DeepSeek Harness live voice preview with exact-session consent, a local synthetic demo, and one bounded manual turn
65 results
DeepSeek Harness live voice preview with exact-session consent, a local synthetic demo, and one bounded manual turn
MiniMax speech-to-text (asr-1.0) and text-to-speech (speech-2.8-hd) as a global DeepSeek Harness plugin: a transcribe_audio tool, an announce_speech tool, a settings card, composer voice input, spoken turn announcements, and handsfree conversation.
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
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
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.
Provider-neutral full-duplex voice Agent capability for DeepSeek Harness.
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.
音频比特率
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.
DSH sound cues: a short Web Audio ding when you need to act (approval / question), and a different one when a task finishes. 需要操作与任务完成时的简短提示音(Web Audio 合成,无弹窗无系统通知)。
Zero-config local vision and realtime audio routing for DeepSeek Harness
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).
Vibe coding时的好伴侣