Awesome DeepSeek Harness Plugin

A curated list of DeepSeek Harness (dsh) plugins.

Listing 155 plugins · What is DeepSeek Harness? ↗

dsh-market — browse and install everything on this list inside DeepSeek Harness
__INDEX_LINE__
  1. Local + online music player for DeepSeek Harness: multi-root library, NetEase / QQ Music / KuGou / Navidrome, synced playlists and lyrics, audio cache, EBU R128 leveling, 10-band EQ with AutoEQ headphone curves, smart crossfade, in-list search, and tag / cover editing. Online sources keep login cookies and tokens in ~/.dsh/music/providers.json (mode 0600); ticking Save password for Navidrome writes that password there in plain text.

    Voice & Audio
    Install ▾
  2. 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.

    Voice & Audio
    Install ▾
  3. 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.

    Voice & Audio
    Install ▾
  4. Full-duplex voice mode for the DeepSeek Harness Web UI: toggle (2s-pause auto-send) or hold-to-talk dictation into an editable draft with zipformer2 streaming ASR, optional wake word; sentence-by-sentence Edge TTS read-aloud with live captions, and speaking interrupts playback and the running turn (true barge-in). On-device ASR, no API key.

    Voice & Audio
    Install ▾
  5. Voice tools: free edge-tts neural speech synthesis, OpenAI-compatible ASR transcription, voice list, batch voice preview and health self-check.

    Voice & Audio
    Install ▾
  6. Voice input for the web UI: dictation chunked by pauses and voice messages, each with its own provider fallback chain (Deepgram, Groq, HuggingFace, local whisper.cpp, or an OpenAI-compatible endpoint).

    Voice & Audio
    Install ▾
  7. 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.

    Voice & Audio
    Install ▾
  8. 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.

    Voice & Audio
    Install ▾
  9. Reads DSH conversations aloud using the DeepSeek web page's built-in read-aloud, driven by a small browser extension.

    Voice & Audio
    Install ▾
  10. Real-time local TTS for DeepSeek Harness: voice presets, auto-read, engine setup assistant, a read-aloud button, and a settings panel for the GSV-TTS-Lite engine.

    Voice & Audio
    Install ▾
  11. Voice I/O for DeepSeek Harness — speech-to-text and text-to-speech over the microphone and audio output.

    Voice & Audio
    Install ▾
  12. 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.

    Voice & Audio
    Install ▾
  13. Voice input for the DSH web UI: tap or hold Alt to dictate into the composer. Local SenseVoice ASR by default — offline, zero config, zero key; auto-fallback to browser Web Speech, optional OpenAI-compatible ASR chain, polish through DSH-configured models, settings UI.

    Voice & Audio
    Install ▾
  14. Doubao-style voice chat for DSH: press-and-hold mic in the composer converts speech to text and auto-sends, and AI replies are read aloud. Optional LLM condensing (long replies summarized into short spoken lines, following the current conversation model), TTS-friendly text cleaning, selectable Edge TTS voices, adjustable silence auto-stop, and settings embedded in DSH settings dialog.

    Voice & Audio
    Install ▾
  15. YuMS/dsh-duet

    16 4,458

    Full-duplex Chinese voice interaction for DSH Web: dictate and edit tasks, submit requests, manage sessions, answer DSH questions, and hear concise task-completion announcements.

    Voice & Audio
    Install ▾
  16. Adds a fish-ear microphone to DSH that transcribes speech locally, estimates tone and emotion, and lets BigFish reply with an emotion-aware prompt.

    Voice & Audio
    Install ▾
  17. Alan2Z/dsh-speak

    19 3,734

    Zero-dependency, event-driven voice announcement plugin: no extra model, no token cost. Speaks with the system's built-in natural voice, supporting both Windows and macOS; final-reply announcements, approval & question alerts, optional event announcements (turn end, command done, goal change, tool errors, todo updates), replayable final replies, and a bilingual visual settings page.

    Voice & Audio
    Install ▾
  18. Reads assistant replies aloud via Fish Audio API only (bring your own key): per-message read-aloud, auto-read toggle, and a settings page for model, voice reference_id, encrypted API key, and proxy.

    Voice & Audio
    Install ▾
  19. Local offline prosody analysis for DeepSeek Harness: reports how something was said — speed, pitch, pauses, energy — alongside the transcript.

    Voice & Audio
    Install ▾
  20. Agent-initiated voice calls: `offer_call` rings the human (接听/拒接/稍后再说); accepted calls synthesize and play locally via CrispASR + Qwen3-TTS (9 speakers, 2 Chinese dialects), rejected calls return the decision to the agent.

    Voice & Audio
    Install ▾
  21. Local GPT-SoVITS text-to-speech that reads DeepSeek Harness assistant replies aloud, with a draggable mascot toggle and a one-click installer. Requires Python 3.10–3.12 preinstalled (the installer only locates it, it does not install Python); about 5 GB of disk and a GPU are recommended.

    Voice & Audio
    Install ▾
  22. Voice or sound cue when a turn finishes and a failure cue when a tool call or turn errors; user aborts stay silent and subagent sessions are skipped by default. Three modes: voice (Volcengine TTS with cloned or preset voices, fingerprint reuse so unchanged text is not re-synthesised), effects (20 built-in sounds assignable to done, fail and approval, with per-row preview and no API key; the approval slot has no automatic trigger, so it plays only manually) and off. Plays through winmm without touching system volume. Windows only. Adapts DSH kernel 0.2.2-rc.1.

    Voice & Audio
    Install ▾
  23. DSH has its own audio workstation too: real recordings, multiple TTS engines and genuine sound effects, with every generated sound landing as its own clip on one visible timeline that you can audition, balance and fine-tune track by track. Use it for scoring animation, producing audiobooks and radio drama, composing and mixing on your own, making ASMR, and whatever else you come up with. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.

    Voice & Audio
    Install ▾
  24. Two-way voice for the DSH web app: dictate with the unified composer, hear replies with speaker buttons and auto-read, on any device. Needs DSH 0.1.7+, Node 22+, Python 3 with numpy and requests, a TTS model, and a microphone.

    Voice & Audio
    Install ▾
No plugins match.

Installing

# from npm (prebuilt)
dsh plugin --profile web add <npm-package>

# from GitHub (first run asks for allowBuilds approval — follow the hint, retry)
dsh plugin --profile web add github:owner/repo

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).

Get your plugin listed

Open a PR against awesome-dsh-plugin — one YAML file under data/plugins/ is the whole submission; the READMEs and this site regenerate automatically. Add the dsh-plugin topic to your repo too.