DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

dsh-realtime-voice

Realtime full-duplex voice agent plugin integrating Qwen Audio with DeepSeek Harness WebUI.

UI & ProductivityTerminal & TUIDeveloper ToolsRemote Execution
1GitHub Stars2ForksUpdated2026-08-24

Install

$ dsh plugin --profile web add .

Plugin 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.

source-grounded
dsh-realtime-voice adds a realtime voice agent interface directly into the DeepSeek Harness WebUI without modifying core code or spinning up separate web servers. It connects low-latency Qwen Audio Realtime models for voice conversations with DSH sessions for actual tool and agent execution via function calling, supporting full-duplex barge-in, floating UI windows, and oral approvals.

Key Capabilities

  • Injects a dial button and draggable floating voice window directly into the DSH 3080 WebUI
  • Integrates DashScope Qwen Audio Realtime (Flash/Plus) with full-duplex VAD and instant acoustic barge-in
  • Separates conversation flow from execution flow, delegating actual tasks to bound DSH sessions via function calling
  • Syncs DSH execution status, terminal results, approval requests, and interactive questions back to the voice agent in real time
  • Manages DashScope API credentials safely via DSH write-only credential APIs

Useful For

  • Controlling DSH agents and executing workspace tasks hands-free using natural voice commands
  • Monitoring background agent progress and orally answering interactive DSH questions or approvals
  • Interrupting, steering, or correcting active DSH tasks in real time through spoken dialogue

Who It Fits

  • Developers looking for hands-free voice interaction with DeepSeek Harness workflows
  • DSH users who need real-time voice feedback, status monitoring, and oral task steering

Documented Limitations

  • Requires DashScope API credentials (DASHSCOPE_API_KEY) with Qwen Audio Realtime access
  • Only allows one active voice call globally at any given moment
  • WeChat Mini Program support is limited to foreground realtime audio interactions and verified PCM audio hardware

DSH Compatibility

Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.

Not tested yetNo runtime compatibility tests have been published yet.

Security Signals

Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.

Dependency Counts

package.json declares 2 runtime, 26 development, 18 peer, and 0 optional dependencies.

info
Dsh Bundle Declared

package.json declares DSH bundle metadata.

info
License Declared

GitHub reports the repository license as MIT.

info
Package Manifest Available

A root package.json was captured and can be inspected by the registry.

info
Source Available

Public GitHub source metadata is available for this registry snapshot.

info

Source & Registry Notes

Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.

Source repository
martinbear1/dsh-realtime-voice
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin
Source checked
7a56377 · 2026-09-07

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
2
Open issues
2
Last commit
2026-08-24
Last release
2026-08-23
For maintainers

Maintaining this plugin?

This listing is generated from public repository data. If you maintain this project, you can review the information and share this listing with your users if you find it useful.

Add to README
Listed on DSHPlugin.app