Plugins

A conversational voice frontend Agent for dsh: speak naturally over ByteDance Duplex, delegate requests to background tasks, and hear their asynchronous results reported by voice.

China-ready voice input for the composer. Requires a local Python bridge (pip install dashscope websockets, run bridge/voice-bridge.py) — the plugin alone does not work. Browser mic streams 16 kHz PCM to the bridge, which runs Alibaba Cloud DashScope ASR (paraformer-realtime-v2); interim text fills the draft at the cursor, silence auto-stop, optional auto-send.

Local-first, full-duplex voice for DeepSeek Harness, orchestrated by Muxiva

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.

Four-pointed star (FPS) adds long-task status, tool summaries, session outputs, persistent attachment drafts, native voice integration, provider usage, compatibility checks, and optional image generation to DSH.

Reads assistant replies aloud while they stream: sentence-by-sentence speech with highlighted lines in a sidebar player, pause, mute and stop controls, and automatic quieting for code blocks. Speech uses the operating system's local voices; its HTTP routes have no DSH access check.

Reads each reply aloud through the BreezeBlue / Breeze TTS 2 API. Synthesis starts as soon as the reply first sentence is complete rather than after the whole reply, and the audio is streamed as raw PCM into Web Audio so it plays continuously while it arrives. Needs a BreezeBlue API key, entered on the settings page or via BREEZE_API_KEY; a key saved on the settings page is stored as plain text in ~/.dsh/breeze-speak.json. By default only the first sentence of each reply (up to 120 characters) is spoken, and that text is sent to api.breeze.blue. The default voice is just an example, so pick one available to your account on the settings page.

Local Russian speech-to-text for DeepSeek Harness voice input: GigaAM v3 (ONNX int8) on CPU via sherpa-onnx

MiniMax voice studio for DeepSeek Harness: clone a voice from an audio sample, preview it from the audio returned by the clone request itself (no extra synthesis call, so the per-voice fee stays uncharged), synthesize text to local mp3 files, transcribe audio to text with asr-1.0, and manage the voice library, API key and these actions from a settings panel; four agent tools and a local HTTP API.

Pocket Harness: the phone side of DSH. Continue the same DSH session from your phone, with the same history, projects, goal, queue and pending questions, connected over your LAN, your own domain or a relay you run (no author-run server, no account). Needs the Android companion app (APK from the repo's releases) paired by QR code; an optional pixel-whale desktop pet can talk and listen, and neural voice and local speech recognition are optional extras. Formerly dsh-pet-voice.

Download watermark-free Douyin and Xiaohongshu videos, transcribe them with local or cloud speech recognition, proofread the text against a term list, and export Markdown, DOCX, SRT, VTT and other formats from a settings panel or agent tools. Needs Python 3.10+ with pip packages (playwright, python-docx, numpy, and sherpa-onnx for the default local SenseVoice engine, which also downloads a ~228 MB model on first use), ffmpeg on PATH, and Chrome or Edge.

Pocket Harness：DSH 手机端。手机上接着用电脑里的同一份 DSH —— 会话、项目、目标、队列状态一致；语音与桌宠可选。

A local AI voice studio for DeepSeek Harness with nine local TTS engines for voice design, voice cloning, emotional performance, a reference-audio library and audio export. It only registers /ai-voice/api routes; the UI lives in the companion-memory plugin's integrations page, and every engine needs its own Python virtualenv and downloaded model weights, which are not bundled.

One-line song cover: fetch a track or take a local file, split stems, derive a key shift, run RVC conversion through Applio, align the vocal, mix three variants and gate the master — nine stages across three tools, zero npm dependencies. Requires a local Applio install (Python, ffmpeg, yt-dlp), a voice model and a CUDA GPU.

Text-to-speech for the dsh-go native phone UI: long-press an assistant reply to read it aloud through Xiaomi MiMo TTS or ByteDance Doubao Seed TTS. The reply is segmented and pre-synthesized in the background after each turn, so one tap hands the app a single continuous MP3 instead of one short chunk per tap; playback has a stable lease so stop works, a status strip and progress bar give live feedback, and audio can be exported to phone storage. Keys stay on the device (0600) and are never rendered, committed, or sent to the model.

Text-to-speech service with Doubao TTS 2.0, Alibaba Bailian and OpenAI-compatible providers and a user-chosen voice; the agent speaks through tts_service_say, split into segments with an optional tone each, and other plugins can reuse ctx.ttsService.

Click the chibi mascot and it reads the assistant reply aloud through your local IndexTTS 2.5 install. One character = one reference clip; a missing portrait just shows a placeholder. Ships no voices or artwork — the library lives on the user's own machine. Requires a local IndexTTS 2.5 install.

Turn a script into a narrated explainer video: text-card slides by default (fast and exact for tutorials) or AI-generated footage per segment (needs AGNES_API_KEY); 14 online neural Chinese voices plus 3 offline Windows voices, with a one-command sample pack for picking a voice by ear. Requires ffmpeg, and the bundled video-remix skill copied to <workspace>/.dsh/skills/video-remix with npm install run there for the online voices.

A fork of dsh-livestream (MIT) — install it instead of that plugin, not alongside it. Lets DSH host a Bilibili livestream: chat and gift replies, queued viewer video requests on a skinnable stage, Doubao TTS voice; needs OBS Studio 28+ and a Bilibili live room, and the voice stays silent until you add a Doubao TTS API key.

Let DSH speak: every reply is rewritten into natural spoken language before being read aloud, with code, tables, and Markdown handled gracefully. Works out of the box with system TTS; Doubao (third-party API) adds dialects and expressive voices; the local Kokoro engine runs offline to keep content on your device. Supports both DSH desktop and dsh web. Optional session sounds tell you when the agent is working, finished, or waiting for your answer — with swappable built-in tones and support for your own audio.

Qwen media tools: multimodal video and audio understanding, text-to-speech with preset voices, and scene audio generation, through Alibaba Cloud DashScope.

Hands-free voice for DSH on Windows: local wake word, local Chinese speech-to-text inserted and sent into the composer, and spoken replies that can be interrupted and resumed. Requires a one-time run of the bundled install.ps1 (Python speech dependencies plus microphone pick) and a SenseVoice model already downloaded by the DSH voice input (or placed under models/sensevoice-onnx).

Adds a terminology-aware correction pass to the built-in local speech-to-text: keeps DSH's own microphone and SenseVoice engine (audio never leaves the machine) and fixes homophones, domain terms and malformed numbers in the finished transcript.

Reads each reply aloud after rewriting it into spoken style: system TTS, Doubao speech synthesis, or an optional local Kokoro model.