dsh-voice-live
Manifest validLive streaming voice input for DeepSeek Harness — real-time captions in the composer, local SenseVoice + Silero VAD, optional model-assisted correction.
dsh-voice-live
Live streaming voice input for the DeepSeek Harness Web composer.
Speak, and words appear while you talk; press Done and the transcript is corrected once, then inserted into your draft. Recognition runs on your machine — audio never leaves the computer.
The live caption card sits above the composer: settled sentences in normal color, the sentence being recognized in grey.
Features
- Streaming captions — the sentence in progress is re-decoded on a sliding window every ~0.5–0.8 s.
- Sentence-level final decode — when Silero VAD detects an endpoint, the complete sentence is decoded again, so final quality equals whole-clip decoding.
- Clean audio path — 16 kHz PCM straight from the microphone with browser echo cancellation, noise suppression and AGC disabled; SenseVoice ITN (digits) and punctuation enabled.
- Optional model-assisted correction — a minimal-edit pass fixes homophones (查件 → 插件), product names (拼森 → Python), digits and punctuation. It keeps your wording, and silently falls back to the local transcript on timeout or implausible output.
- No manual model setup — the first use asks DSH's own speech service to prepare the SenseVoice model, shows progress, then starts recording automatically.
Requirements
- DSH Desktop
0.2.2-rc.1or newer. Tested on Windows x64; macOS and Linux are expected to work because the engine is resolved from the installation, but are untested. - No npm dependencies:
sherpa-onnxcomes from the DSH installation and the model from DSH's speech service. - About 240 MB of model on disk and ~400 MB RAM while the engine is warm (released after
idleTimeoutMs).
Install
From npm
Install the bundle by its package name — in the Plugins page, or by asking your agent to install it:
dsh-voice-live
From this repository
git clone https://github.com/18301301961/dsh-voice-live.git
Then install that directory as a DSH bundle — either through the plugin manager with the absolute path, or by asking your agent to install it.
From a git source
github:18301301961/dsh-voice-live#v1.1.0
Reload the page once after installing; the microphone button appears to the left of the send button. See PUBLISH.md for the full distribution guide.
Usage
- Hover the microphone to warm the engine (~3–4 s, once per idle period).
- Click it and speak: settled sentences render in normal color, the sentence in progress in grey with a caret.
- Done inserts the text at the cursor; ✕ or
Escdiscards it. - If the composer changed during dictation, the transcript stays on the card and Insert into composer writes it at the current cursor.
Configuration
The bundle row lives in cordis.patch.yml:
| Field | Default | Meaning |
|---|---|---|
language | zh | auto, zh, en, yue, ja, ko |
threads | 4 | ONNX Runtime threads |
partialIntervalMs | 480 | Minimum live-caption refresh interval; widens automatically with decode cost |
partialWindowSeconds | 6 | Audio window used for the sentence in progress |
vadThreshold | 0.5 | Silero VAD threshold; raise it in noisy rooms |
minSilenceSeconds | 0.35 | Silence that ends a sentence |
maxSpeechSeconds | 12 | Longest continuous sentence before a forced break |
idleTimeoutMs | 300000 | Release the engine after this idle time |
polish | final | final corrects the transcript once at the end; off keeps the local text |
vocabulary | [] | Terms the recognizer tends to misspell, for example [DSH, Cordis] |
polishInstructions | empty | One extra sentence appended to the correction prompt |
polishMaxLatencyMs | 8000 | Correction timeout; on timeout the local text is used |
How it works
engine.mjs— Silero VAD segmentation plus SenseVoice decoding; the in-progress sentence is re-decoded on a sliding window, the finished sentence once on its complete audio.worker.mjs— a child process (Electron Node mode) hosting the engine on a random loopback port with a per-process token, so model loading never blocks the Host.index.js— the/voice-live/*routes (same-origin andx-voice-livechecks), sessions, warm-up, model preparation, audio forwarding and finish handling.polish.mjs— the correction pass: cheapest reasoning effort, temperature 0, hard timeout, and two guards (length ratio and character overlap) that reject rewrites.client.js— AudioWorklet capture (linear resampling to 16 kHz when needed), the caption card and draft insertion.
Privacy
Audio is decoded locally and never uploaded. With polish: final, only the finished text is sent to the model configured in DSH — which is where that text was headed anyway.
Limitations
- The recognition model is shared with DSH's built-in voice input; this plugin ships no model of its own.
- Uninterrupted speech is split at
maxSpeechSeconds; the correction pass usually repairs the punctuation seam. - The composer integration depends on DSH client slots and is untested against future releases.
License
MIT — see LICENSE.
Comments
Loading…
Similar plugins
by QDchuan
Voice input for DeepSeek Harness: a microphone seat in the composer and a Web settings page that transcribes through the browser or any OpenAI-compatible /audio/transcriptions endpoint, with a fully o
★ 0
MIT
JavaScript
Sep 12, 2026
dsh plugin --profile web add dsh-voice-inputReal-time speech-to-text inside the DeepSeek Harness composer: a live transcript while you speak, inserted at the caret when you stop, with a microphone picker. Local sherpa-onnx inference, so audio n
★ 0
dsh plugin --profile web add dsh-voice-realtimeby porcelaintech
Voice input plugin for DeepSeek Harness: a minimal mic control in the composer with continuous bilingual recognition, context-aware term correction, punctuation, and a live waveform
★ 3
MIT
TypeScript
Sep 3, 2026
dsh plugin --profile web add @porcelaintech/dsh-plugin-voice-inputby moazzamak
Offline local speech-to-text for the DeepSeek Harness composer: a microphone button that records, transcribes with faster-whisper on your own machine, and inserts the text into the chat draft.
★ 0
MIT
JavaScript
Oct 6, 2026
dsh plugin --profile web add dsh-voice-inputby SuCriss
Voice control for DeepSeek Harness web: speech-to-text into the composer and spoken playback of assistant replies, zero dependencies
★ 0
↓ 75/wk
MIT
JavaScript
Sep 1, 2026
dsh plugin --profile web add dsh-voice-controlby BeepFlyer
Voice chat mode for DeepSeek Harness: always-on VAD listening, local SenseVoice transcription, auto-submit, Edge TTS read-aloud, settings UI and a voice_mode tool.
★ 0
MIT
JavaScript
Nov 10, 2026
dsh plugin --profile web add dsh-voice-chat-mode