- ホーム
- プラグイン
- ビジョン、音声とマルチモーダル
- dsh-voice-input-wb-asr
dsh-voice-input-wb-asr
baibiaowang/dsh-voice-input-wb-asr
Hold-to-talk microphone in the composer that recognizes through the WorkBuddy cloud, using the accounts already signed in on this machine. International and domestic builds are separate settings, international by default. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
インストール
dsh plugin --profile web add github:baibiaowang/dsh-voice-input-wb-asrREADME
dsh-voice-input-wb-asr
Hold-to-talk voice input for DeepSeek Harness — hold the composer microphone (or hold Alt while the caret is in the composer), speak, release, and the text is inserted at the caret.
Recognition runs on the WorkBuddy cloud ASR service, so no local model is downloaded: the shipped SenseVoice recognizer needs ~1 GB of model files, this plugin needs none.
按住说话,松开出字。识别走 WorkBuddy 云端,不用下 1 GB 的本地模型。
What it does
- Hold-to-talk in the composer, with optional diffusion-ring feedback while recording.
- Streams while you hold: raw 16 kHz / 16-bit / mono PCM is pushed to the host half as you speak, so releasing the button only waits for the last syllable instead of the whole clip.
- Registers as a provider for the shipped speech-to-text service when that service is mounted, so a profile that keeps the click-to-start microphone still works. Where it does, the shipped microphone button is disabled so the composer carries one microphone, not two.
- Uses the accounts already signed in on this machine. Tokens are read from the local WorkBuddy account stores; when one is rejected the next account is tried, so a stale token does not break the button.
- International and domestic builds, kept apart. The region decides the endpoint:
www.workbuddy.aifor the international build,www.workbuddy.cnfor the domestic one. International is the default and is the only one that runs until the domestic build is switched on in settings. A token only works on its own region, and the account pool records which one each token belongs to. - No dependencies outside Node built-ins: the WebSocket client and the RIFF/WAVE reader are part of the plugin.
Requirements
- DeepSeek Harness 0.2.x (a profile that can load bundles).
- A WorkBuddy account and an
access_tokenfor its ASR endpoint. The token is yours — the plugin ships with none.
Install
dsh plugin --profile <profile> add <this package>
or from a checkout:
dsh plugin --profile <profile> add github:<owner>/dsh-voice-input-wb-asr
Restart the host (or reload the profile) after installing.
Accounts
The plugin reads the WorkBuddy accounts already signed in on this machine — nothing to configure:
| Source | What it holds |
|---|---|
~/.dsh/.xdpool/accounts.json | Accounts pooled by the dsh-xdpool plugin, with their region. |
~/.wb-switch/accounts.json | Accounts recorded by workbuddy-switch. |
~/.dsh/skills/wb-asr/tokens.json, ~/.workbuddy/skills/wb-asr/tokens.json | The wb-asr skill's own token list. |
~/.dsh/skills/wb-asr/token.txt, ~/.workbuddy-asr/wb-asr-token.txt | A single fallback token, first line. |
Expired and re-login-required entries are sorted last; the account currently signed into the desktop app goes first. If the recognizer rejects a token, the next account is tried automatically — up to every account the machine knows. Files are only read, never written. WORKBUDDY_ASR_ACCOUNTS points the pool at a different file.
To use a token that is not on this machine, set WORKBUDDY_ASR_TOKEN — it is tried first. Never commit a token.
Settings
| Field | Default | Meaning |
|---|---|---|
activeRegion | ai | Which build to use: ai international, cn domestic. Shown as two checkboxes in settings — the ticked one is used. |
accountPool | true | Read the accounts signed in on this machine and fail over between them. |
aiEndpoint | https://www.workbuddy.ai | International recognizer base URL; only change it for a self-hosted gateway. |
cnEndpoint | https://www.workbuddy.cn | Domestic recognizer base URL; only change it for a self-hosted gateway. |
timeoutMs | 30000 | Per-request timeout. Raise it on a slow network. |
minHoldMs | 320 | Presses shorter than this are treated as a mis-tap and are not uploaded. |
effect | true | Show diffusion rings while recording. |
ringColor | #00ff9d | Ring colour, hex. |
Every field is volatile: an edit applies to the running plugin without a restart.
Privacy
- Audio leaves your machine: the recording is streamed to the WorkBuddy endpoint selected by
activeRegion. - Tokens are read from your own account files and stay in the host half: they are never sent to the browser, and the plugin writes nothing back.
- Nothing is stored on disk by the plugin; there is no transcript history.
Notes and limitations
- The ASR protocol is unofficial — reverse engineered from the WorkBuddy web client, the same protocol the
wb-asrskill speaks. It can break when the service changes. - A token belongs to one region: a domestic account fails on the international endpoint and vice versa. That is why the two builds are separate choices rather than one automatic fallback — the plugin never contacts the domestic service unless you tick it.
- The account count shown next to the choices is the number of distinct accounts on that region, deduplicated by account id: the same account appears in several local pools and each re-login leaves a new token, so counting entries would overstate it.
- The pool has no rate-limit awareness: it fails over on rejection, but it does not rotate between takes.
- Chinese and English recognition quality depends on the service, not on this plugin.
- No wake word, no continuous dictation: it is push-to-talk only.
License
MIT.