dsh-voice
Voice input plugin for DeepSeek Harness that transcribes microphone speech and submits it as normal chat messages.
Install
$ dsh plugin --profile web add @nn12138/dsh-voicePlugin 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 a microphone button to the web composer and supports a configurable global hotkey (Ctrl+Space by default).
- Streams partial transcripts while speaking and submits finalized speech as a normal chat message.
- Uses host-native sherpa-onnx recognition with Silero VAD when optional models are installed.
- Falls back to browser Web Speech in automatic mode when native recognition is unavailable.
- Keeps voice input separate from agent presets, personas, and system prompts.
Useful For
- Dictating chat prompts in DeepSeek Harness.
- Using speech as an alternative to keyboard input across standard, code, minimal, and custom presets.
- Using local/offline native recognition after installing the optional runtime and models.
Who It Fits
- DeepSeek Harness web users who want microphone-based prompt input.
- Users who prefer voice dictation without changing agent behavior.
- Users able to configure optional local ASR models for native recognition.
Documented Limitations
- It is input-only and does not modify agent presets, personas, or system prompts.
- Native offline recognition requires the optional sherpa-onnx-node runtime and a separate model download of approximately 100 MB.
- Without an available native model, automatic mode uses browser Web Speech.
- The package targets the DeepSeek Harness web profile and requires Node.js ^22.19.0 or >=24.0.0.
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 1 runtime, 8 development, 1 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
- 3274375092/dsh-voice
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- ceab3e7 · 2026-09-16
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
- 7GitHub stars
- Forks
- 0
- Open issues
- 0
- Last commit
- 2026-08-21
- Last release
- No release detected
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Full context lifecycle management, visualization dashboard, and /context command for DeepSeek Harness.
View plugin →A DeepSeek Harness Web UI sidebar for tracking artifacts and browsing workspace files, with a pop-out tab view.
View plugin →VSCode-like modular sidebar and bottom panel workbench for DeepSeek Harness with terminal, editor, git, and plugin extension API.
View plugin →Generative UI plugin for DeepSeek Harness that renders interactive components and charts inline from assistant responses.
View plugin →