Adds Xiaomi MiMo, Doubao, Breeze and browser speech to DSH, with external provider and local model adapters, text filtering, streaming read-aloud, audio downloads, sound effects, desktop pets, QQ Bot and AI Passport integration.
Install
# from npm (prebuilt)
dsh plugin --profile web add dsh-xiaomi-tts
# from GitHub (first run asks for allowBuilds approval — follow the hint, retry)
dsh plugin --profile web add github:ppy-web/dsh-plugin-xiaomi-mimo-tts
Any plugin you install runs third-party code with your own permissions — it can read your files, use your credentials, and reach the network, and tool approvals don’t sandbox it. GitHub-sourced plugins also run build scripts at install time — pnpm blocks those until you allow them, so an install can stop with ERR_PNPM_GIT_DEP_PREPARE_NOT_ALLOWED or ERR_PNPM_IGNORED_BUILDS; dsh prints the exact key to add under allowBuilds in your profile’s pnpm-workspace.yaml, and the install works on the next run. Allowing a build is a trust decision: only install sources you trust, and pin a commit (github:owner/repo#sha).
README
This plugin publishes its README in Chinese only.

小米MIMO、豆包语音、BreezeBlue、浏览器语音 - 音色随心配,支持连接10+供应商或本地语音模型,文本过滤、实时流式朗读、音频下载、音效、桌宠联动及 QQ Bot、AI Passport 联动
🎨 在线预览
QQ 群 交流·建议:
1104616387
✨ 功能
- 一键朗读、自动播报;
- 自动过滤网址、代码等内容,减少资源消耗,体验更好;
- 内置 小米 MiMo
免费、豆包语音、BreezeBlue、DeepSeek。自由选择和定义音色; - 支持 浏览器、MOSS本地模型兜底。还能通过外部适配器接入供应商...
- 可选 UI 音效、宿主事件播报;
- 语速、音量、朗读范围调节,音频历史试听和下载;
- 支持多种插件联动,dsh-pet桌宠、 QQ Bot、AI Passport...
🚀 安装与使用
需要 DSH 0.2.2 以上、Node.js 24.9+,当前适配目标为 DSH 0.2.2-rc.5。
直接在 DSH 插件管理面板搜索
dsh-xiaomi-tts安装;安装插件市场后搜索
xiaomi-mimo-tts。Web 端可使用命令:
dsh plugin --profile web add dsh-xiaomi-tts@latest卸载:
dsh plugin --profile web remove dsh-xiaomi-tts
快速设置:
- 侧边栏插件-已安装插件-音色工坊-进入设置页,默认使用小米 MiMo,可在右上角卡片切换豆包 Key、 Breeze Key或DeepSeek(在播报台开启)
- 在“调音台”选择模型、音色,在“播报台”试听;服务商的密钥、音色与模型自独立保存,先保存,后试听。
- 稳定使用 Breeze 需要科学上网,推荐 ✈️𝘾𝙤𝙠𝙚𝘾𝙡𝙤𝙪𝙙
📖 用户手册
配置要点与详细使用说明见用户手册。
🔌 插件联动
本插件向外部提供查询和调用接口,完整接入方式见开放能力接口文档。
浏览器插件:通过
ctx.xiaomiMimoTts.play(text)在当前页面播放,使用stop()停止。宿主插件:注入
speechSynthesis,通过ctx.speechSynthesis查询能力、合成或导出音频,也可注册交付渠道或外部语音供应商。DSH Agent:挂载
dsh-xiaomi-tts/speech-agent,使用speak、synthesize_speech和speech_mode工具。外部程序或设备:配置
openApiToken后,通过 HTTP 查询能力、导出音频并使用限时 URL 下载。dsh-whale-musume · 元气鲸鱼娘桌宠 支持互动气泡播报
已联动dsh-pet · 蓝色大肥鱼桌宠 支持播报碎碎念,闲聊消息
已联动dsh-qqbot · 腾讯官方QQ机器人 支持向 QQ 推送语音和表情包
已联动dsh-novel · 小说阅读与听书 使用本插件朗读里面的小说
已联动dsh-music-panel · 音乐播放器 播报时可以自动降低播放器的音量
已适配dsh-Go · dsh 移动端移植 在移动端也可使用本插件
已适配dsh-audio-reactive · 音频响应 随流式播报显示跳动的频谱背景
已适配dsh-speech-provider-adapter · 供应商适配器 接入你想要的语音供应商
已适配WhaleTalk Passport · 鲸语通行证 AI Passport 硬件连接,和你的鲸鱼娘实时语音对话
一个简单的调用示例:
import type { XiaomiMimoTtsService } from 'dsh-xiaomi-tts/client-api'
const tts = ctx.get('xiaomiMimoTts') as XiaomiMimoTtsService | undefined
tts?.play('欢迎回来')
// tts?.stop()
🔒 隐私
- API Key 由 DSH Host 保存,浏览器只读取配置状态;三家服务商均由 Host 代理,文本和音色 ID 仅提交给所选服务商,费用按服务商政策计算。
- 本地语音使用 Web Speech API,音色与离线能力取决于浏览器和系统;在线音色可能向其语音服务发送文本。
- 云端音频存于浏览器 IndexedDB,最多 100 条 / 100 MB,可试听、下载;流式 PCM 保存为 24 kHz 单声道 WAV,本地语音无法导出。
🛠️ 开发
pnpm install --frozen-lockfile
pnpm dev # 设置预览
pnpm build # 构建插件
pnpm typecheck
pnpm test
pnpm dev:build # 构建预览
pnpm pack:check # 检查打包内容
Links
More in this category
Yuuyuko-uu/dsh-tts-bridge★ 263
Reads DSH conversations aloud using the DeepSeek web page's built-in read-aloud, driven by a small browser extension.
Fishsb/dsh-voice-prompt-enhancer★ 133
Rewrites a composer draft into a clearer, structured prompt (5 modes, model fallback chain, optional multi-round memory) and adds stop-on-silence, hotkey and filler-word cleanup to DSH voice input; transcription stays with the official speechToText, the plugin ships no engine.
PolinniZhong/dsh-omi-voice★ 75
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.
1624318455/dsh-plugin-tts★ 63
Reads assistant replies aloud via free Edge TTS or your own RVC voice models: read-aloud buttons + auto-read, adaptive chunked progressive playback (gapless long reads), one-click voice-pack installs from a registry, and a portable RVC runtime.
beiyege-01/dsh-voice-ai-girlfriend-plugin★ 61
Voice AI girlfriend for the Web UI: FunASR mic input, Qwen3-TTS spoken replies, companion animation window, and two-way QQ chat (text/voice/image push) via NapCat.
SAOS-3624/dsh-watch-together★ 54
Watch a video together with a text-only agent: with ffmpeg and the bundled browser extension reporting your real playback position (not a timer), it hands over one segment at a time just before that segment ends. It ships no TTS engine — it emits timed speech events, and speaking them aloud needs your own voice/TTS setup.
Community comments
Comments are public GitHub Discussions. Loading them connects to GitHub and Giscus; a GitHub account is required to post.