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.
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。
How to install
dsh plugin add dsh-omi-voice About
让 DeepSeek Harness（DSH）桌面端里的 AI 回复，用**豆包自然音色**读给你听。语音由你本机常驻的 Omi 引擎合成，**豆包 API Key 只留在你自己的钥匙串里（BYOK）**。 快速概览 | 项目 | 说明 | |---|---| | 插件名称 | dsh-omi-voice | | 适配平台 | DeepSeek Harness（dsh web，含桌面端）+ macOS 上的 Omi 引擎 v0.1.3+ | | 解决的问题 | DSH 内置朗读（系统语音 / Edge TTS）音色机械、像上个时代的播报腔；通用剪贴板工具又要先复制再读 | | 工作方式 | 点回复旁 🔊 朗读/暂停/继续；只读最终回答，工具日志/代码/表格/图形朗读前自动过滤 | | 语音能力 | 豆包 TTS 1.0（seed-tts-1.0），自然中文音色，支持暂停/继续（从暂停处续播） | | 隐私特性 | API Key 存入 Omi 引擎的 macOS Keychain；插件零 Key；仅本机 127.0.0.1 通信 | | 成本 | BYOK，按字符计费；内存 LRU 缓存 + 去重，避免重复请求 | | 开源协议 | MIT License | 三步开始朗读 1. 安装插件 + 构建并打开 Omi 引擎（见下方「获取豆包 API Key」与「安装」）。 2. 在 …
Recommendation signals
Meta
- License
- MIT
- Language
- Swift
- GitHub stars
- 74
- mo. downloads
- 387
- Last push
- 2026-08-28
- Created
- 2026-08-18
Basic safety check
- Findings
- None
- Sources
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
- Topics
- chinese, deepseek-harness, dsh-plugin, read-aloud, text-to-speech, tts, voice
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-voice-call
biliye/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.