dsh-voice-call
Voice call assistant for the DSH Web GUI: a draggable floating call ball, browser-side VAD that sends each utterance after a pause, FunASR HTTP or streaming speech recognition, MiniMax or OpenAI-compatible TTS replies, an optional wake-word mode with auto-sleep, and task dispatch to separate subagent sessions with progress, stop, and spoken completion reports.
DSH Web GUI 的个人语音通话助手：可拖拽悬浮球通话面板、浏览器端 VAD（停顿自动发送）、FunASR HTTP 或流式语音识别、MiniMax / OpenAI 兼容 TTS 语音回复、可开关的唤醒词模式（沉默自动休眠），以及把任务分发给独立子代理会话并跟踪进度、停止与完成播报。
How to install
dsh plugin add @biliye/dsh-voice-call About
dsh-voice-call 语音通话助手 DSH Web GUI 的个人语音通话助手插件：悬浮球通话面板、FunASR 语音识别（流式/HTTP）、云端 TTS 语音回复、子代理任务分发与进度跟踪。 ✨ 功能 🗂 **专属工作区与专属会话**：安装并打开后自动创建专属工作区「语音通话」（目录 $DSH_HOME/voice-call）与专属会话 voice-call-main；**所有语音通话固定保存在该会话，本体重启后依然延续同一会话**（自动 resume） ⚡ **快速回复**：专属会话自带「快速、简短回复」提示词，并限制重型工具（bash/pwsh/run_code/工作流/子代理等），需要执行任务时一律通过 voice_task 分发给独立子代理会话 🎙 **悬浮球通话面板**：页面最顶层悬浮球，可拖拽，点击展开通话/任务/设置面板 🗣 **语音识别**：FunASR Server HTTP（新版 v1.x，默认）/ FunASR 流式 ws://（旧版 2pass）/ 云端 API（OpenAI 兼容），设置可切换 ⏹ **停止任务**：对执行中的任务提供面板「⏹ 停止」按钮、voice_task（action=stop）以及 HTTP POST /api/voice-call/task-stop 三种停止入口；停止后任务状态为「已停止」并语音播报 🔎 **任…
Recommendation signals
Meta
- License
- MIT
- Language
- JavaScript
- GitHub stars
- 2
- mo. downloads
- 392
- Last push
- 2026-09-15
- Created
- 2026-08-16
Basic safety check
- Findings
- None
- Sources
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
- Topics
- deepseek-harness-plugin, dsh, dsh-plugin, speech-recognition, subagents, text-to-speech, vader-sentiment-analysis, voice-assistant-ai, voice-chat, wake-word
Related plugins
dsh-voice-scribe
PensiveFei/dsh-voice-scribe
Voice input for the web UI: tap Alt (or Alt+Space) to start/stop dictation, browser Web Speech (zero-config) or OpenAI-compatible cloud ASR, optional polish through DSH-configured LLM, settings UI.
dsh-tts
GooDAnDReaDY/dsh-tts
Speaks agent replies in the DeepSeek Harness web UI through a provider fallback chain (OpenAI, ElevenLabs, Google, Azure, Groq, Deepgram, OpenRouter, Edge, Piper, eSpeak), so a failing or rate-limited provider falls through to the next instead of going silent.
dsh-ears
WizisCool/dsh-ears
Voice input plugin for DeepSeek Harness (dsh): a microphone button in the composer turns speech into a draft transcript, with a choice of speech-recognition backends, optional polish through dsh own LLM routes, and a native settings page.
dsh-omi-voice
PolinniZhong/dsh-omi-voice
In-chat read-aloud for DeepSeek Harness: tap to read, pause and resume AI replies with natural Doubao TTS voices (BYOK), reading only the final answer with code, tables and diagrams filtered; local engine, plugin keeps no API key.