DeepSeek Harness Plugin Hub

Publish and manage complete Harness Profiles. Discover Plugins for your next setup.

Explore

PluginsPresetsDocsNews

Community

Publish a pluginContactReport an issue

Resources

Plugin Hub on GitHubDeepSeek HarnessSystem statusPrivacy notice
© 2026 DeepSeek Harness Plugin HubPowered byPaxTech

Independent and unofficial. Not affiliated with, authorized by, or endorsed by DeepSeek.

DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in
← Plugins

dsh-cost-voice

Cost Voice

At the end of each session turn, announces the turn's cost using Alipay or Dabaifan voices; the amount is taken from dsh-cost-meter when available, otherwise estimated based on the model's per-turn price. Per-turn spend voice announcements for DeepSeek Harness with Alipay or Dabaifan voice packs.

The plugin will be installed here. Keep web if you are unsure.

npx -y @deepseek-ai/dsh plugin --profile web add dsh-cost-voice@1.1.1
READMECompatibilityVersions
插件设置页

Compatibility and provenance

Cost Voice is published as dsh-cost-voice and currently resolves to version 1.1.1. The Hub verifies its manifest and preserves the exact installation source for reproducible installs.

DSH compatibility
*
Runtime surfaces
web
Release source
npm
Registry updated
11/4/2026

Versions

1.1.1stable
11/4/2026
1.0.1stable
11/3/2026

Related plugins

Loading related plugins…

Latest
1.1.1
DSH
*
HMR
Process restart
Tree shaking
Safe tree shaking not declared
Unpacked size
1.6 MB
Files
147
Surface
web
License
MIT
Source
npm
GitHub
★ 0
Weekly downloads
0
Last push
11/4/2026
View source ↗
README badge

Click the badge to copy Markdown for your README.

Do you maintain this Plugin?Claim benefit · Priority security scan

Verify the GitHub repository declared in package.json to manage this listing. After you claim it, Hub will prioritize a security scan of the current version and publish the result when it passes.

Claim this Plugin →
Report an issue

Related plugins

More verified plugins in models-usage.

Experimental Cot Translation Bundle@deepseek-ai/dsh-experimental-cot-translation-bundleExperimental machine translation of expanded reasoningWhale Widgetdsh-whale-widgetDeepSeek balance whale widget in the bottom-right corner of the DSH Web interface: balance/today’s usage/peak-off-peak pricing, customizable bubble click sequence (text/balance/today/peak-off-peak/image/random phrases and parallel weighted selection), per-line styles and fonts, floating quick editinOur Free Model@ebony-vinyl/dsh-our-free-modelOur Free Model — Install this plugin in dsh to use cutting-edge models including DeepSeek V4.1 Flash and Kimi K3, with no login, registration, or API Key required. The desktop version also offers an EAC co-payment channel; starting with 2.0, it supports ten account channels: LobsterAI, Qoder, TRAE, Usage@linxin666/dsh-usageUsage statistics plugin for the dsh web GUI: per-provider balance and coding-plan quota detection plus a live token usage ledger, with a compact price glance card above the sidebar's Settings row

README

每轮扣款语音播报 · dsh-cost-voice

吃白饭的蓝色大肥鱼(图标)

每轮会话结束,用支付宝或者「大白饭」的声音报一句本轮花了多少钱——「支付宝到账,零点一二元」。

音频全部打包在插件里,装好就能响:不联网、不调系统语音、不需要任何 TTS 服务。

插件设置页

功能

  • 每轮结束自动播报:一轮做完,报出这一轮的估算花费;刷新页面不会重播,后台标签页漏掉的只补最近一条
  • 连着来也不漏:上一句还没播完时下一轮排队等(最多 4 句);音频先整句取回再播,首句不会卡在我
  • 两种音色:支付宝(收款语音片段拼接);大白饭(小米 MiMo 音色克隆,0.01–1.00 元是整句录音,听起来最顺)
  • 金额有两个来源:装了 dsh-cost-meter 就直接用它记录的每轮费用(没算出来的轮次回落估算);没装则按本轮模型单价估算(随包 354 个模型的价格表)
  • 一个设置页搞定:都在 设置 → 插件 → 每轮扣款语音播报,逐项解释见下方「设置说明」;界面跟随 GUI 语言(中文 / English)
  • 可选,不打扰:静音时段内不响;金额低于设定值时也不响

安装

dsh plugin --profile web add dsh-cost-voice

装完重启一次 dsh web,刷新页面,在 设置 → 插件 → 每轮扣款语音播报 里点一次「试听」——这同时解锁浏览器播放声音的权限,之后每轮结束就会响。

设置说明

设置说明
音色支付宝 / 大白饭
金额来源费用插件(优先 dsh-cost-meter)/ 按单价估算
模型价格按模型列出输入、输出单价(元/百万 token);留空用价格表,填写即覆盖
低于此金额不播默认 0,任何金额都播
片段间隔拼接时每段之间的停顿,默认 40 毫秒
音量0–1
只在正常完成的轮次播报关掉后,中断或报错的轮次也会播
静音时段例如 00:00–08:00 不播

听不到声音?

  1. 先在插件页点一次「试听」。浏览器要求页面先被点过一次才允许出声。
  2. 确认标签页停在这个页面:浏览器会把后台页面的定时器压到一分钟一次,播报会延迟。
  3. 看设置里有没有打开「静音时段」,或把「低于此金额不播」设得比实际花费还高。
  4. 系统音量、浏览器标签静音也要看一眼(标签上右键能静音)。

金额怎么算

装了 dsh-cost-meter 时,插件直接读它算好的每轮费用,和费用面板口径一致——推荐这样用。

没装时按本轮实际使用的模型估算:

输入 × 输入价 + 输出 × 输出价 + 缓存读 × 缓存读价 + 缓存写 × 缓存写价(元/百万 token)

单价来自 dsh-cost-meter 随包的 docs/provider-pricing.json(354 个模型,USD 折算汇率 7.2);插件里也带了一份快照,所以没装费用插件也能估。表里没有的模型用「其他模型」兜底,可以在设置里改。

播报的是估算值,不能当账单。真实费用以各厂商账单和 dsh-cost-meter 为准。

已知限制

  • 页面要开着、标签页在前台才会准时响;后台标签页会延迟。
  • 大白饭 1 元以上走片段拼接,会比整句稍微机器感一点;支付宝整套都是拼接。
  • 只支持 Web 版 GUI;桌面壳里同样走浏览器音频。

开发

node scripts/test-core.mjs       # 客户端纯函数:数字/金额读法、费用估算、金额取源
node scripts/test-host.mjs       # 宿主纯函数:费用归一、价格表换算、用量累加
node scripts/smoke-host.mjs      # 宿主半冒烟:轮次折叠、费用、价格目录、音频下发
node scripts/smoke-client.mjs    # 客户端半冒烟:加载器协议、页面树、金额计算、播放拼接
node scripts/shrink-audio.mjs    # 音频统一压到 32 kbps(--check 只看不改)
npm pack --dry-run               # 核对发布内容
路径作用
index.js宿主半:听 turn/end,折叠每轮用量与费用,出 /api/cost-voice/*
client.js客户端半:轮询、金额计算、Web Audio 拼接播放、插件页
assets/voices/三套音色:alipay-zh 18 段、dabaifan-clone 17 段、dabaifan-amounts 100 句整句
assets/pricing.json价格表快照(没装 dsh-cost-meter 时兜底)
scripts/音色渲染、ASR 校验、响度统一、离线冒烟(不随包)
dev/本地素材与截图(不随包、不进仓库)

致谢与声明

  • 支付宝播报片段来自开源项目 Reathin/XVoice(其 README 注明仅供娱乐)。
  • 大白饭音色由小米 MiMo TTS 克隆生成;「大白饭到账」是二创梗,不是真实支付语音。
  • 图标用的是网友二创的「吃白饭的蓝色大肥鱼」梗图(DeepSeek 鲸鱼娘),版权归原作者,这里只作插件配图;与 DeepSeek 官方无关。原作者如不希望被使用,说一声就换掉。
  • 娱乐用途。本插件不联网、无遥测,只读会话的用量和轮次信息,不读写对话正文。

许可

MIT