Local audio understanding for DeepSeek Harness: transcription (whisper medium), rhythm, melody, chords, structure - six tools, fully offline. Needs a Python 3.10-3.12: point DSH at an existing environment (e.g. ComfyUI), or let the plugin create and install its own. Vocal separation runs UVR MDX-Net on onnxruntime, so torch is not required.
Inline video and audio for DeepSeek Harness chats: the player appears under the reply, with compact cards, Range streaming and auto-play. · DSH 对话里直接播放视频和音频。
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, offline, audio never leaves the machine. | DSH 长按说话语音输入插件:输入框上按住鼠标说话,浮层边说边出字,松手把文字写进输入框,上滑取消;识别在本机跑,免密钥、离线、音频不出本机。