dsh-tts-flash
Reads AI replies aloud as they stream, with voiced waiting phrases while the model thinks. Edge TTS built in, any OpenAI-compatible cloud engine supported.
AI 回复流式 TTS 朗读插件，思考等待期有文字与语音同步的趣味短语反馈。内置 Edge TTS，支持任意 OpenAI 兼容云端引擎。
How to install
dsh plugin add github:2021Heei/dsh-tts-flash About
dsh-tts-flash https://github.com/user-attachments/assets/640a8def-641a-4845-aa93-9acf6cc0e0a1 给 DeepSeek Harness（DSH）桌面端做的 **LLM 回复语音朗读插件**：AI 边流式输出，本地边把句子合成语音播放，随读随停；AI 思考等待期间还有"文字+语音"双通道的趣味短语反馈。 **零配置可用**：内置微软 edge-tts，能联网就能用（几十种音色） **云端引擎即插即用**：任何 OpenAI 兼容 TTS 服务（OpenAI / 小米 MiMo / 硅基流动…）在设置面板里填 baseURL + API Key + 模型 id 即可添加，双协议自适应 **等待期语音**：模型思考时浮条轮换趣味短语并同步朗读（"让子弹飞一会…"），等待不再干瞪眼 --- 功能总览 | 模块 | 说明 | |---|---| | 无损流式朗读 | llm/stream 旁路 tap → 中英日分句 → 短句合并 → 串行合成 → SSE 推送；队列带背压上限，长回复自动追赶 | | 多引擎 | edge-tts（内置）+ OpenAI 兼容云端 TTS（双协议自适应：/audio/speech → chat/completions） | | 引擎即插即用 | 设置面板二级弹窗添加，或…
Recommendation signals
Meta
- License
- MIT
- Language
- TypeScript
- GitHub stars
- 0
- mo. downloads
- –
- Last push
- 2026-09-10
- Created
- 2026-09-09
Links
Basic safety check
- Findings
- curated 收录但无 npm 包/安装命令
- Sources
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
- Topics
- deepseek-harness-plugins, dsh, dsh-plugin, tts, typescript, 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-dingo
february2015/dsh-dingo
Sound reminders with one-click jump for concurrent sessions: the current session gets crisp dang/dang-dang tones, other sessions a soft ding/ding-ding plus a top-right card that jumps straight to the replying conversation.
dsh-voice-assistant
supersyh-sss/dsh-voice-assistant
Voice assistant for dsh web: say the wake phrase (e.g. "小鲸") to activate hands-free dictation — what you say is transcribed and typed into the chat box automatically. Supports spoken edit commands (send, clear, new line, stop reading) and reads assistant replies aloud in Chinese. Speech recognition runs locally in-browser via sherpa-onnx WASM, so it works offline without an API key.
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.