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.

Kepos Tts — DSH Plugin for DeepSeek Harness
← Plugins
K

@lamplitisles/kepos-tts

Kepos Tts

Alibaba and ByteDance Chinese tagged text-to-speech for DeepSeek Harness Web

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

npx -y @deepseek-ai/dsh plugin --profile web add github:LamplitIsles/kepos-tts#1ea72952afee5c7e2d743c69ba2c06e5918ffb3a
READMECompatibilityVersions

Compatibility and provenance

Kepos Tts is published as @lamplitisles/kepos-tts and currently resolves to version 0.1.0. The Hub verifies its manifest and preserves the exact installation source for reproducible installs.

DSH compatibility
*
Runtime surfaces
web
Release source
github
Registry updated
8/30/2026

Versions

0.1.0stable
8/30/2026

Related plugins

Loading related plugins…

Latest
0.1.0
DSH
*
HMR
Process restart
Tree shaking
Safe tree shaking not declared
Unpacked size
Unavailable
Files
Unavailable
Surface
web
License
Apache-2.0
Source
github
Weekly downloads
0
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
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in

Related plugins

More verified plugins in integrations-communication.

Acp App@deepseek-ai/dsh-acp-appThe dsh ACP profile bundle: automation-only JSON-RPC stdio and process lifecycle over dsh-baseIm@xmanrui/dsh-im把十一种 IM 渠道和公网 AI Office 接入本机 DeepSeek Harness。 Connect eleven IM channels and a public AI Office to a local DeepSeek Harness.Pocketdsh-pocketPut DeepSeek Harness in your pocket: one package, one settings page, and scan a QR code on your phone to access DSH on your computer in sync (LAN + public network, real-time screen mirroring).DSCODE@toddzheng024/dscode-bundleA complete DeepSeek coding agent with persistent shell, Ultra collaboration and automatic permission review.

README

kepos-tts

Dual-provider Chinese tagged text-to-speech for DeepSeek Harness Web. The bundle adds one optional audio-only [[tts:text]]...[[/tts:text]] block to a finalized assistant reply. When that message completes, it immediately prepares its MP3 and replaces the block with the browser's native audio player. Normal replies, malformed tags, and fenced examples remain ordinary visible text.

Build and verify

bun install
bun run typecheck
bun run test
bun run build
bun run pack-smoke

The resulting package contains a host ESM entry, a browser loader entry, and cordis.patch.yml. It is pinned to the DSH 0.1.1-rc.2 contract family.

Settings

Open the native Plugin Settings card from a local loopback DSH Web session and choose Alibaba or ByteDance. The editable Voice ID defaults are Maia and zh_female_sajiaoxuemei_uranus_bigtts; any provider-supported ID up to 128 characters can be entered. Store the selected provider's key using the card's write-only password field. DSH credentials hold Alibaba under KEPOS_TTS_DASHSCOPE_API_KEY and ByteDance under KEPOS_TTS_VOLCENGINE_API_KEY; this plugin never reads or displays saved values. There is no agenix or remote configuration path. In remote DSH Web, an unavailable or memory-backed Settings scope does not render this card; only a ready non-writable Host scope shows it read-only.

Alibaba uses Qwen3-TTS Flash with Chinese MP3 output. ByteDance uses the domestic Volcengine V3 seed-tts-2.0 one-shot SSE endpoint with MP3 at 24 kHz. The host accepts only the finalized passage and framework session identity sent by the browser's trusted Connection RPC; provider and voice are never message overrides.

Audio cache

Each prepared passage is keyed by its normalized text, selected provider profile (provider, model/resource, and Voice ID), and cache format, then written atomically as .dsh/kepos-tts/audio/<sha256>.mp3 below the active session workspace. A refresh or remount resolves the session again and reuses that bounded artifact; the browser only receives a same-origin /kepos-tts/audio/... URL. The cache has no browsing, eviction, migration, or clear UI, and sessions without an absolute workspace are intentionally unavailable.