dsh-live-voice
DSH Web 的会话绑定单轮语音预览：提供无需凭证的本地合成演示和可选的 Qwen Audio，保持精确会话隔离，并仅在明确操作后将转写写入草稿，不会自动提交。
Consent-bound one-turn voice preview for DSH Web with a credential-free local synthetic demo, optional Qwen Audio, exact Session isolation, and explicit transcript-to-draft handoff without automatic submission.
怎么安装
dsh plugin add dsh-live-voice 简介
DSH Live Voice Try it in two minutes · Watch the 24-second demo · Report the stopping point · Preview release DSH Live Voice is built for one bounded voice turn: speak, hear returned audio, review both transcripts, and decide whether to place your own words into the current draft. It never submits the composer or runs tools for you. Unlike a speech-to-text-only microphone button, the intended experience carries native audio in both directions, binds visible consent to the exact live DSH Session, and requires a second explicit action before your transcript enters the draft. Preview.5 adds the e…
推荐参考
信息
- 协议
- MIT
- 语言
- TypeScript
- GitHub 星标
- 1
- 月下载
- 669
- 最近更新
- 2026-09-05
- 创建于
- 2026-08-25
基础安全检查
- 检查结果
- 无
- 收录来源
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
- 主题标签
- ai-assistant, consent, deepseek, deepseek-harness, dsh-plugin, live-voice, microphone, privacy, privacy-first, qwen, react, realtime-audio, speech-to-text, synthetic-audio, typescript, voice, voice-assistant, websocket
同类推荐
dsh-voice-scribe
PensiveFei/dsh-voice-scribe
面向 Web UI 的语音输入插件：点按 Alt（或 Alt+空格）开始/停止听写，支持浏览器内置 Web Speech（零配置）或 OpenAI 兼容云端 ASR，可选经 DSH 已配置模型润色，带设置页。
dsh-tts
GooDAnDReaDY/dsh-tts
在 DeepSeek Harness 网页 UI 中朗读智能体回复，采用服务商回退链（OpenAI、ElevenLabs、Google、Azure、Groq、Deepgram、OpenRouter、Edge、Piper、eSpeak），某个服务商失败或被限流时自动切换到下一个，而不是直接静音。
dsh-ears
WizisCool/dsh-ears
面向 DeepSeek Harness (dsh) 的语音输入插件：输入框的麦克风按钮把语音转成草稿文本，支持多种语音识别后端，可选经 dsh 自有 LLM 路由润色，并带原生设置页。
dsh-omi-voice
PolinniZhong/dsh-omi-voice
DeepSeek Harness 对话内朗读：点一下即可朗读、暂停、继续 AI 回复，豆包 TTS 自然音色（BYOK），只读最终回答并过滤代码、表格与图形，本地引擎，插件零 Key。