Speech Recognition
🏆 #6,033 overall#681 of 793 in Speech Recognition🔥 active this week
Fishsb /dsh-voice-prompt-enhancer
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）
$ git clone https://github.com/Fishsb/dsh-voice-prompt-enhancer.gitStars
126
126
This week
—
Forks
13
13
Language
JavaScript
License
Apache-2.0
Created
Aug 13, 2026
0.3 years old
Last push
Nov 13, 2026
🔥 this week
Categories
More in Speech Recognition
Speech Recognition
FlaxXTT/Typeleast🔥 active
TypeLeast：按一下快捷键说话，本机识别（SenseVoice），用你自己的大模型 API Key 整理成通顺文字，直接写进光标处。macOS + Windows 11。
SwiftGPL-3.0updated Nov 11, 2026
Speech Recognition
Open-Less/openless🔥 active
Hold a key, speak, release — AI-polished text appears at your cursor in any app. Open-source voice input for macOS & Windows. (按住快捷键说话，松开即得润色后的文字)
RustAGPL-3.0updated Nov 13, 2026
Speech Recognition
ricky0123/vad
Voice activity detector (VAD) for the browser with a simple API
TypeScriptOtherupdated Sep 12, 2026
Speech Recognition
oxbshw/watch-skill
▲ +21 ★ this week
Give AI agents eyes, ears, and verifiable results. Watch Skill turns video, audio and screen activity into searchable, timestamped evidence and proves work with deterministic contracts, not model opinion. DeepWatch is the agent workspace built on DeepSeek Harness. Python + npm, MCP, CLI, REST, Web.
📄 OCR & Documents
PythonMITupdated Oct 26, 2026
Speech Recognition
SAOS-3624/dsh-video-storyboard🔥 active
Scene-aware storyboard for DeepSeek Harness: 9-16 numbered cells with timestamps + transcript + an audio envelope, packed into ONE image (384 tokens). Two tools: video_storyboard and video_zoom.
JavaScriptApache-2.0updated Nov 11, 2026
Data from GitHub · snapshot Nov 13, 2026