dsh-voice-enhance

Voice dictation and prompt enhancement for DeepSeek Harness (dsh) — two controls added to the message composer.

中文说明

What it does

Hold Alt to dictate. Press and hold Alt, speak, release. The recording is transcribed on the Host, then passed through the Host model to fix the mistakes speech recognition usually makes — homophones, wrong characters, missing punctuation — and the result is inserted at the cursor.

✨ Enhance prompt. The sparkle button at the left of the composer, immediately before the model selector, rewrites the current draft into a clearer, more specific prompt using the same default model. The result replaces the draft, with an Undo control to get the original back.

A status pill appears below the composer card while either control is working: elapsed seconds, a "send on release" switch, an Insert button when a transcript could not be placed, and an Undo button after an enhancement.

Key / control	Behaviour
Alt (press and hold)	Start recording
release Alt	Stop, transcribe, correct, insert
Alt + any other key	Treated as a shortcut (Alt+Tab, IME chords); the capture is discarded
Esc while recording	Cancel
✨ button	Enhance the draft

Requirements

• The recording is transcribed by the Harness Voice Input plugin (dsh-experimental-voice-input-bundle), which must be enabled and its SenseVoice model prepared. Without it the plugin reports that the speech service is unavailable.
• Correction and prompt enhancement run on the Host through the llm service, using the composition's default model route. No API key is configured or read by this plugin.
• The browser needs microphone access (HTTPS or 127.0.0.1, plus OS permission).

Install

dsh plugin --profile <profile> add github:owner/dsh-voice-enhance

Or from the Web UI: Settings → Plugins, then install the bundle by package name or from a local directory.

Notes

• Nothing is persisted except one browser-local preference: the "send on release" switch (localStorage key dsh-voice-enhance.autoSend). Recordings are discarded after transcription; no audio is written to disk.
• The audio pipeline is bounded end to end: microphone permission, recorder flush, decoding, resampling and transcription each have a timeout, so a wedged browser API surfaces as an error message rather than an endless "transcribing" state.
• Two Remote calls cross the wire, both of them one-shot text rewrites: promptTools/refine with mode: "correct" for a transcript, mode: "enhance" for a draft.
• The custom element styles use the host theme tokens (--dsw-alias-*), so light and dark themes need no separate artwork.

Licence

MIT — see LICENSE.