Plugins

Official Remotion skill ported to DSH: programmatic video with React (animation/audio/captions/3D/charts/fonts, 38 rule files).

DSH Typewriter: ambiente de máquina de escribir con WebAudio, con una API de ajustes propia del plugin y sin archivos de audio

Visor de archivos de audio/vídeo para dsh-better-sidebar: reproducción nativa en línea de mp4/webm/mkv/mov y mp3/flac/wav, servida por una ruta de streaming con soporte de Range.

Tonos de finalización por espacio de trabajo, además de sonidos de atención para eventos de aprobación, pregunta, revisión de plan, objetivo bloqueado y fallo de tarea, con síntesis integrada, voz (TTS) y audio personalizado.

Herramientas de solo lectura de información de dispositivos Windows: una herramienta de agente por cada categoría de dispositivo Win32 (hora, sistema, cpu, memoria, disco, gpu, red, batería, procesos, usb, audio, impresoras) vía colectores WMI/CIM y del módulo os de Node.

Per-file-type multimodal chains: preset processing models per wildcard convert image/video/audio files into prompt tokens before they reach the text-only session model, with per-preset fallback chains and a Multimodal settings page.

Configurable, unobtrusive Agent lifecycle sound cues for DeepSeek Harness (dsh), synthesized with Web Audio.

Cross-platform waiting-for-user and completion sound notifications for the DeepSeek Harness web UI.

Per-event sound notifications: turn completion, approval, question, plan-review, goal-blocked, and task-failure each get their own sound and volume, configurable in the Web UI (built-in synth, mute, or local audio file).

MuApi media-generation tool: a muapi_generate tool that submits and polls jobs against any of MuApi's 100+ image, video, audio, and 3D models through one x-api-key.

Connects DSH to local Beav for Xiaohongshu (RED/RedNote) and social-media AI operations: topic research, knowledge, copywriting, image, audio, and short-video workflows with approval and artifact tracking.

Notas de voz de entrada, respuestas habladas de salida: dicta audio que se convierte en mensajes de usuario (transcribir), haz que el agente lea las respuestas en voz alta (hablar), con prioridad local bajo ~/.dsh/voice.

peon-ping sound notifications for DeepSeek Harness — a faithful port of the pi plugin pi-peon-ping-win (native Windows audio fallback, WinForms popup, OpenPeon sound packs). Beeps only when a task completes or terminates unexpectedly, by default. Settings

DeepSeek Harness plugin: multimodal tools (image/audio/video/document understanding, transcription, image generation) via Gemini API or the local Antigravity CLI.

Short Web Audio cues when a session needs your attention (approval, question, or plan review) and when a task finishes. No popups or OS notifications.

Sound + popup when a task completes: a Web Audio chime, an in-page toast, and a system notification while the page is in the background (browser-only, cross-platform).

Reads assistant replies aloud via Fish Audio API only (bring your own key): per-message read-aloud, auto-read toggle, and a settings page for model, voice reference_id, encrypted API key, and proxy.

Full-duplex voice mode for the Web UI: a composer mic (RMS endpoint detection) transcribes speech with whisper running locally in the browser, assistant replies stream back as spoken audio sentence-by-sentence, and speaking interrupts playback and the running turn (true barge-in). No API key.