by maxwell-feng

Local OCR for attached images via Tesseract: only the recognized text is sent to the model, never the image bytes; vision passthrough is opt-in.

by OMSociety

DSH Plugin: Connect the Xiaoai speaker to DeepSeek Harness. Call out the wake word, and the answer is read out through the speaker.

by shinjiyu

Vision sidecar for DeepSeek Harness: accept pasted images on text-only models.

by QT-Chen

DSH Web ?????????:??? Web Speech API ????,????/??????????????????Microphone voice input plugin for the DeepSeek Harness Web UI (browser Web Speech API).

by 54xkeee

Eyes for text-only DeepSeek on DeepSeek Harness: model-invokable vision tool + wrapper adapters + general VLM channels (OpenAI-compatible / Gemini / local Ollama)

by lsjspl

Gives dsh the ability to generate images and videos through the grok2api API.

by wangzhanchao883

Hold-to-talk voice input for the DeepSeek Harness web composer: hold the mouse on the input box, speak, release to insert the text into the draft. Local SenseVoice ASR via sherpa-onnx: no API key, off

by supersyh-sss

Voice assistant for dsh web: say the wake phrase (e.g. "Little Whale") to activate hands-free dictation — what you say is transcribed and typed into the chat box automatically. Supports spoken edit commands (se

by xiaoyuink

Image Recognition Plugin for DeepSeek Harness: Automatically detects the current model’s image recognition capability; supports managing and detecting vision models from multiple vendors

by baisama-cloud

Speech-to-text voice input plugin for DeepSeek Harness (DSH) web GUI: click the mic in the composer to turn speech into text in the input box. Browser Web Speech API + OpenAI-compatible Whisper (OpenA

by Nothree-code

DeepSeek Harness (dsh web) Voice Input Plugin: Integrates VocoType local offline recognition, automatically inserting recognition results into the chat input box (auto-deployment / anti-duplication / continuous input)

by jerryqx

Listen to Ximalaya podcasts and audiobooks inside the DSH web UI: search albums, browse paginated tracks, and play through a now-playing bar (prev/play/next, seek, volume, rate). After QR login the "M

by jryang1997

Hold-to-talk dictation for the DeepSeek Harness composer: long-press the input box, release to transcribe into the draft.

by WSL043

Upgrades DSH image viewing with pointer-centered zoom, pan, galleries, downloads, keyboard support, and inline region notes (Beta).

by huguangyu666

Notification outbox: agent proactively notifies via toast / Chinese TTS voice / sound effects (explosion, victory, alarm), 60s confirmation window voice-calls you back, volume boost, settings panel.

by QXingYShu

DeepSeek Harness plugin that drives a local ComfyUI image workflow (Z-Image-Turbo, Qwen-Image-2.1) from the agent

by shimingming520

AI audio generation for the DeepSeek Harness web GUI — multi-vendor TTS, music, sound effects and voice design with a sidebar panel, model comparison, resource library and Agent tools.

by moon09300731

DeepSeek Harness Vision Capabilities Full Bundle: vision_understand Tool + Image Recognition via Three Entry Points (Paste/Drag-Drop/Button)

by Einskyle

DeepSeek vision bridge for dsh: route image attachments to a vision model (Qwen3-VL via pi-ai/llama.cpp) and continue on a text-only LLM (DeepSeek)

by Jesse-njx

Voice notes in, spoken answers out — dictate audio that becomes user messages (transcribe), have the agent read replies aloud (speak), and leave walk-away narration on long headless runs. Local-first:

by lgquan

Continuous voice conversations for DSH with hands-free listening, push-to-talk, speech recognition, TTS replies, and background Agent delegation.

by haiziyao

Vision routing and image generation for DeepSeek Harness through a fixed Mix model.

by taxueseek

Integrated visual creation toolchain for DSH: prompt reverse-engineering and audit optimization plus multi-provider image generation with async background rendering.

by MaRi23333

Fish Audio TTS plugin for DeepSeek Harness — per-reply read-aloud, auto-read toggle, BYOK, third-party. Text-to-speech plugin: per-reply read-aloud, auto-read toggle; only supports Fish Audio API, requires your own Key; third-party unofficial.