dsh-web-speech-input
Web UI microphone input plugin that converts speech into an editable DeepSeek Harness prompt draft.
Install
$ dsh plugin --profile web add github:leozou320-ai/dsh-web-speech-inputPlugin Overview & Capabilities
AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.
Key Capabilities
- Adds one-click microphone start and stop controls to the Web conversation composer.
- Transcribes interim and final speech-recognition results into the existing editable draft.
- Selects recognition language from the page language, then browser language, with zh-CN fallback.
- Displays listening, unsupported browser, permission, microphone, and network states.
- Provides keyboard focus, ARIA labels, reduced-motion support, and unload cleanup.
Useful For
- Dictating a prompt into the DeepSeek Harness Web composer.
- Creating a draft by voice, then reviewing and editing it before manual submission.
- Using voice input for Chinese or other languages supported by the browser recognition service.
Who It Fits
- DeepSeek Harness Web profile users.
- Users who want browser-provided speech-to-text in the prompt composer.
- Users who require review before a voice-created prompt is sent.
Documented Limitations
- Requires DeepSeek Harness Web profile 0.1.0-rc.5 or a compatible developer-preview build.
- Requires a browser with SpeechRecognition or webkitSpeechRecognition and microphone permission.
- Firefox normal releases do not currently expose a compatible API.
- Recognition availability, quality, languages, punctuation, privacy behavior, and local versus remote processing depend on the browser and OS service.
- Some browser recognition services may require internet access; the current Web UI slot API may change during developer preview.
DSH Compatibility
Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.
Security Signals
Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.
package.json declares 0 runtime, 0 development, 0 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
GitHub reports the repository license as MIT.
A root package.json was captured and can be inspected by the registry.
Public GitHub source metadata is available for this registry snapshot.
Source & Registry Notes
Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.
- Source repository
- leozou320-ai/dsh-web-speech-input
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- 8b14507 · 2026-08-16
This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.
Repository Activity
- GitHub stars
- 1GitHub stars
- Forks
- 1
- Open issues
- 0
- Last commit
- 2026-08-16
- Last release
- No release detected
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Session lifecycle manager for DeepSeek Harness with search, restore, idle cleanup, and diagnosis.
View plugin →Agent skill for DeepSeek Harness that turns ideas, plans, and codebases into interactive architecture diagrams.
View plugin →Full office suite integration for DeepSeek Harness supporting spreadsheets, docs, slides, bases, and canvases.
View plugin →Vision routing and pixel-level tools for text-only DeepSeek Harness agents with built-in free fallback.
View plugin →