DeepSeek-Harness (DSH) 插件:✨ 提示词一键增强(5 模式·模型链·记忆链)+ 💬 语音输入增强(热键·说完自动停·口水词清理·语音纠错)
GITHUB TOPIC
speech-to-text
10个项目包含此标签
10 个项目
GitHub Topic 精确匹配
dsh-voice-scribe
PensiveFei
DSH voice input plugin: tap or hold Alt to talk, text lands in the composer. Local SenseVoice ASR by default — offline, zero config, zero key. Auto-fallback to browser Web Speech, optional OpenAI-compatible ASR chain, polish via DSH models.
dsh-soundtry
CixiSVesper
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.
dsh-talk
PerryLink
Voice-first session loop for DeepSeek Harness: a composer microphone button with browser/local speech-to-text (Web Speech, FunASR, whisper.cpp), a speak tool for text-to-speech replies (browser, edge-tts, piper), event announcements with mute, and speak-to-interrupt.
dsh-speech
allmodels-io
Real-time voice input and spoken answer summaries for DeepSeek Harness.
dsh-vidlens
cctv2333
DSH plugin: 18 local tools that watch a public video the way a person does - metadata, chapters, timestamped frames, subtitle-first transcripts, and 527-class sound events - without downloading the whole video.
voco-input-sh
Nothree-code
DeepSeek Harness (dsh web) 语音输入插件:集成 VocoType 本地离线识别,识别结果自动插入聊天输入框(自动部署/防重复/持续输入)
dsh-voice-ru
ripls56
Local Russian speech-to-text provider for DeepSeek Harness voice input: NVIDIA Nemotron 3.5 ASR 0.6B (GGUF) on transcribe.cpp. Model and native runtime download on first use, sha256-verified.
dsh-hold-to-talk
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, 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。
dsh-voice-doubao
FYZB2020
Cloud speech recognizers for the DeepSeek Harness voice-input picker (Volcengine Doubao), with an optional LLM tidy-up pass. · 给 DeepSeek Harness 的语音输入加豆包云端识别,可选再用大模型把口语顺成通顺的书面句子。