dsh-dictation
Editable local and desktop dictation for DeepSeek Harness
58 results
Editable local and desktop dictation for DeepSeek Harness
识别植物名称(或所属科, 属, 种或亚种)。
泰山识图 Taishan Vision - 让 DeepSeek Harness 纯文本模型也能识图:GLM 视觉识别 + 所选模型推理(静态插件包,重启永久生效)
识别车牌号、车牌颜色、单/双层车牌、位置框。
Zero-token offline math input for DeepSeek Harness: handwriting recognition, screenshot OCR, LaTeX editor, and inline LaTeX rendering.
Give DeepSeek Harness agents eyes: local image analysis via vision models — um_analyze_img tool + model-capability recognition + hot-switch settings UI
Minimal Chinese voice input plugin for the DeepSeek Harness Web UI
External vision model plugin for image recognition when the active model lacks vision
Full-duplex voice plugin for DeepSeek Harness: local zipformer2 streaming ASR (no API key) → editable draft; Edge TTS or local VITS / Kokoro read-aloud with live captions; true barge-in; hardened HTTP surface + model SHA256 pinning; compatible with all ds
Voice Gateway client surface for DeepSeek Harness: mic status, voiceprint filtering, and auto-speak