MIT 协议、DSH 原生的语音听写插件,面向 DeepSeek Harness 网页输入框;以 SenseVoice 离线优先,支持浏览器 / 云端 ASR 回退,并可复用 DSH 模型做可选润色。
DSH 适配
原生运行时
作者声明
安全审计
未审计
最后核验
2026-09-06
许可证
MIT
01它能帮你完成什么?
Dictate text hands-free into the DeepSeek Harness web composer
Transcribed speech inserted at the composer cursor as editable text
DeepSeek Harness (dsh) web users who want voice-to-text input
Transcribe speech with the best available engine (offline-first)
Text via SenseVoice offline (audio never leaves the machine) or browser / cloud ASR fallback
Privacy-conscious dsh users and those behind restricted networks
02如何接入 DeepSeek Harness?
安装步骤
- 01
$ dsh plugin --profile web add dsh-voice-scribe # 重启 dsh web 后生效
验证接入成功
作者未说明
03DSH 适配与能力边界
Installed via the official `dsh plugin --profile web add` command; injects voice dictation into the dsh web composer
Alt hotkey & microphone button dictation
Speech via microphone (tap/hold Alt, or click the 🎤 button)→Transcribed text inserted at the composer cursor
Multi-engine recognition (offline-first)
Microphone audio→Text via SenseVoice offline / browser Web Speech / cloud ASR service chain
First use auto-downloads the SenseVoice model (~230MB, one-time)Hold-to-talk mode
Hold the hotkey to record→Auto-transcribe on release
Hot-word replacement table
Edit $DSH_HOME/voice/hot.txt→Corrected transcription (literal + regex rules) applied to all engines
Optional LLM polish (reuses the DSH model)
Raw transcript + custom polish prompt→Cleaned text via local rule pre-polish then the DSH LLM
Polish prompt and transcript are sent to the DSH model
04适合谁?何时不该用?
适合
- DeepSeek Harness (dsh) web users who want voice-to-text input
- Privacy-conscious dsh users and those behind restricted networks
不适合
- Unofficial community plugin, not affiliated with DeepSeek / 深度求索; read SECURITY.md before use.
- Browser Web Speech relies on external services (Chrome is blocked in mainland China, Edge Stable has known regressions); local recognition is the default.
05兼容性、维护与安全提示
- Unofficial community plugin, not affiliated with DeepSeek / 深度求索; read SECURITY.md before use.
- Browser Web Speech relies on external services (Chrome is blocked in mainland China, Edge Stable has known regressions); local recognition is the default.
- Maximum recording length is ~4 minutes on the local engine and 10 minutes on cloud ASR; recording auto-stops at the limit.
- The cloud ASR service chain requires configuring an API key in settings; the key is stored server-side only.
readme_verified
06常见问题
如何为 DeepSeek Harness 安装 dsh-voice-scribe?
在终端运行 `dsh plugin --profile web add dsh-voice-scribe`,重启 dsh web 后插件即可生效。它会作为 web 配置档插件安装。
怎么开始语音输入?
点击输入框右侧的 🎤 麦克风按钮,或先点输入框、按 **Alt** 开始说话、再按 **Alt** 结束并转写。备选热键 **Alt+空格** 可在设置中切换。
它能离线、保护隐私吗?
默认可以。本地 SenseVoice 引擎离线运行、零配置零密钥,且音频不出本机;浏览器 Web Speech 与云端 ASR 都是可选回退。
识别错的人名 / 术语怎么修正?
编辑热词替换表 `$DSH_HOME/voice/hot.txt`(每行一条),支持字面 `正确词=错误词1|错误词2` 与正则 `/模式/替换/` 两种规则,对所有引擎统一生效。
这是 DeepSeek 官方插件吗?
不是。它是非官方社区插件,与 DeepSeek / 深度求索公司无关联,使用前请阅读 SECURITY.md。
07相关的 DSH 工作流
vox-director
作者 alisa0808
将主题自动生成 Vox 拼贴风解说或广告视频的智能体技能,全流程在 Atlas Cloud 与 ffmpeg 上自动完成。
dsh-voice-ai-girlfriend
作者 beiyege-01
语音 AI 女友(Voice AI girlfriend for DeepSeek Harness):Whisper 语音输入 + Qwen3-TTS 声音克隆 + 句子级流式朗读 + 数字人动画窗。插话/排队双模式,说话即打断。
dsh-plugin-tts
作者 1624318455
Edge TTS 语音朗读插件:朗读回复、自动朗读开关,免费无需 API key
dsh-speak
作者 alan2z
一种能让你的harness开口说话的方案/Make your AI harness speak — a verified voice-announcement solution
08数据与来源
DSH 专属语音输入插件:**点按或按住 Alt 说话、松开/再点按转文字**,插入输入框光标处。
页面基于项目公开文档、仓库元数据和 DSH Plugins 的结构化解析生成;最后核验于 2026-09-06。发现错误?提交更正。
最佳 DeepSeek Harness 插件
从全目录挑出的 12 个值得优先安装的插件,覆盖各个分类。
