Plugins

DeepWatch's capabilities, installable into an existing DeepSeek Harness profile

Rewrites a composer draft into a clearer, structured prompt (5 modes, model fallback chain, optional multi-round memory) and adds stop-on-silence, hotkey and filler-word cleanup to DSH voice input; transcription stays with the official speechToText, the plugin ships no engine.

Voice input for the DSH web UI: tap or hold Alt to dictate into the composer. Local SenseVoice ASR by default — offline, zero config, zero key; auto-fallback to browser Web Speech, optional OpenAI-compatible ASR chain, polish through DSH-configured models, settings UI.

Full-duplex voice mode for the DeepSeek Harness Web UI: toggle (2s-pause auto-send) or hold-to-talk dictation into an editable draft with zipformer2 streaming ASR, optional wake word; sentence-by-sentence Edge TTS read-aloud with live captions, and speaking interrupts playback and the running turn (true barge-in). On-device ASR, no API key.

Voice input plugin for DeepSeek Harness (dsh): a microphone button in the composer turns speech into a draft transcript, with a choice of speech-recognition backends, optional polish through dsh own LLM routes, and a native settings page.

Local meeting transcription for DeepSeek Harness on Apple Silicon macOS: dual-track recording, live transcript drafts with speaker labels, and @-referenced summaries into decisions and action items.

Voice I/O for DeepSeek Harness — speech-to-text and text-to-speech over the microphone and audio output.

Bidirectional QQ bridge over OneBot v11 (reverse WebSocket): per-group and per-private-chat sessions, @-quoted voice speech-to-text, private image/animated-sticker viewing, face and sticker tools.

Local-first hands-free AI voice assistant plugin for DeepSeek Harness (DSH), with speech-to-text, text-to-speech, voice commands, and local speech engines.

Mic button in the composer tool row: Web Speech API speech-to-text (Chrome/Edge), language switching, and optional auto-send, zero dependencies.

Hold-to-talk dictation in the composer that ships no recognizer of its own and reuses the speech service the official voice-input bundle already mounts - long-press the input box with mouse or touch, release to write the transcript into the draft, slide up to cancel, and it never sends.

Agent-initiated voice calls: `offer_call` rings the human (接听/拒接/稍后再说); accepted calls synthesize and play locally via CrispASR + Qwen3-TTS (9 speakers, 2 Chinese dialects), rejected calls return the decision to the agent.

Samples a video the way a person does instead of downloading it: metadata and chapters first, then timestamped frames as images, subtitle-first transcripts (local ASR only when the platform carries no subtitles), AudioSet 527-class sound tags and top comments — 21 tools sharing one on-disk cache behind a cross-process lock. Needs Python 3.10+, ffmpeg and the vidlens package (pip install vidlens-mcp); a missing install comes back with the two ways to fix it instead of a bare ImportError.

DeepSeek Harness × Feishu/Lark bridge: chat, cards, approvals, task board, goals and schedules in Feishu — plus fully local (offline) voice transcription with a play bar in the Web GUI.

One-handed, keyboard-free input for the composer: press and hold the mouse on the input box, speak, release — the text lands in the draft, and sliding up cancels without leaving a half sentence behind. No mic button to aim at and no shortcut to remember; the hand never has to leave the input area, which is the point when the other hand is busy. Recognition runs fully offline (SenseVoice via sherpa-onnx, no API key, audio never leaves the machine).

Voice input for the Web UI: a mic button that drives local VocoType offline speech recognition and auto-inserts recognized text into the composer (auto-deploy, dedupe, continuous dictation).

Speech-to-text voice input for the web UI: a mic button in the composer transcribes speech into the draft via the browser Web Speech API (zero-config) or an OpenAI-compatible Whisper API (OpenAI / Groq), with a selectable model and language in Settings.

Voice notes in, spoken answers out: dictate audio that becomes user messages (transcribe), have the agent read replies aloud (speak), local-first under ~/.dsh/voice.

Development-preview DSH plugin to import recordings from compatible BLE recorder cards, with optional transcription and fingerprint-linked archives. Requires recorder hardware, Host Bluetooth and Python dependencies.

Multi-model local speech-to-text for the DSH Web composer: Whistle and Voz, user-selectable, with lazy per-model download. Ships as a DSH bundle.

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.

Audio tools for DSH: inspect audio/video files, transcode or extract the audio track from a video, trim and normalize, and transcribe speech with local whisper.cpp or an OpenAI-compatible API. Requires ffmpeg and ffprobe on PATH (not bundled); local transcription also needs a whisper-cli binary and a ggml model.

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).