dsh-qwen-voice
Experimental DeepSeek Harness Web voice-control plugin powered by Qwen Audio Agent.
Install
$ npx.cmd -p @deepseek-ai/[email protected] dsh plugin --profile web add .Repository Intelligence
AI-assisted, source-grounded explanation based on the public repository snapshot. It does not replace compatibility or security verification.
Key Capabilities
- Provides a floating voice orb that stays connected while switching DSH conversations.
- Dispatches tasks to multiple named DSH sessions from a single browser tab.
- Shows live task status, supports playback interruption, and announces completed task results.
- Connects DSH through an ACP bridge and a local Qwen Audio Agent gateway.
- Includes a version-checked setup patch for Qwen Audio Agent 1.10.0.
Useful For
- Voice-driven task dispatch across multiple DeepSeek Harness Web sessions.
- Monitoring and interrupting voice task playback.
- Using Qwen Audio Agent’s realtime voice workflow with DeepSeek Harness Web.
Who It Fits
- DeepSeek Harness Web users experimenting with voice control.
- Developers configuring Qwen Audio Agent alongside DSH.
- Users who need to route spoken tasks to multiple named sessions.
Documented Limitations
- Compatibility is pinned to DeepSeek Harness Web 0.1.0-rc.6 and Qwen Audio Agent 1.10.0.
- Requires installing and configuring Qwen Audio Agent separately, including its credentials.
- The compatibility patch modifies the globally installed Qwen Audio Agent and is temporary.
- Session titles are generated from spoken task objectives and may need manual renaming.
- The ACP bridge accepts loopback DSH URLs only, and the floating client defaults to a local gateway at 127.0.0.1:3101.
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, 7 development, 6 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
A root package.json was captured and can be inspected by the registry.
GitHub reports the repository license as MIT.
Public GitHub source metadata is available for this registry snapshot.
package.json declares 1 runtime, 7 development, 6 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
A root package.json was captured and can be inspected by the registry.
GitHub reports the repository license as MIT.
Public GitHub source metadata is available for this registry snapshot.
Source & Registry Notes
Traceable source and registry metadata for this entry, kept separate from runtime verification.
- Source repository
- leaveimagination/dsh-qwen-voice
- Registry source
- Public GitHub repository
- Source snapshot
- b35a7640d176
- Artifact type
- plugin
- AI enrichment
- gpt-5.6-terra · 2026-08-14
- Prompt version
- dsh-plugin-enrichment-v3
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
- 0
- Forks
- 0
- Open issues
- 0
- Last commit
- 2026-08-14
- Last release
- —
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Adds an OpenAI-compatible vision bridge to DeepSeek Harness, forwarding images to a configured vision model and displaying descriptions in a web panel.
View plugin →A DeepSeek Harness MCP server manager that adds a Settings → MCP page for HTTP and local stdio servers.
View plugin →DeepSeek Harness Plugin and Agent Profile Package Index - Install dsh-plugin with just one command
View plugin →Persona-driven UX walkthrough plugin for DeepSeek Harness (DSH) - scans React + TypeScript source code for UX issues, pinpoints them, and suggests fixes.
View plugin →