← DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

dsh-speak

Text-to-speech voice announcement plugin for DeepSeek Harness on Windows and macOS.

Terminal & TUIDeveloper ToolsSecurity & PolicyRemote Execution
11GitHub Stars1ForksUpdated2026-09-26

Install

$ dsh plugin --profile web add dsh-speak

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-speak provides automatic voice announcements and speech synthesis for DeepSeek Harness. It listens to session event streams to read final assistant replies, approval requests, and interactive user questions using native operating system voices (Windows SAPI5 / natural voices and macOS built-in say). It also integrates into the DSH Web UI with a message replay button, live queue synchronization, and a dedicated settings configuration pane.

Key Capabilities

  • Automatic speech synthesis for final assistant replies with text cleaning and throttling
  • Voice alerts for approval requests and interactive user questions (ask_user_question)
  • Turn-tail replay action button integrated directly into the DSH Web UI conversation view
  • Host speech queue management preventing audio overlap and syncing state via WebSocket
  • Configurable event announcements for turn completion, command execution, goal modifications, tool errors, and todo updates
  • Native visual settings panel inside DeepSeek Harness Web UI

Useful For

  • Auditory notification when long-running agent tasks or commands finish
  • Hands-free awareness of pending permission approvals or user questions
  • Replaying assistant responses directly from the Web UI action bar

Who It Fits

  • DeepSeek Harness developers working on multi-tasking or background workflows
  • Users on Windows or macOS wanting voice feedback and accessibility announcements from AI agents

Documented Limitations

  • Requires native PowerShell/SAPI5 environment on Windows and the built-in say command on macOS
  • Windows speech ceiling defaults to 300 characters to prevent silent SAPI failure, requiring fallback messages or headings for long text
  • Volume control is supported on Windows only (macOS follows system output volume)

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 1 runtime, 0 development, 1 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
Alan2Z/dsh-speak
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin
Source checked
5c23e7d · 2026-09-27

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
11GitHub stars
Forks
1
Open issues
0
Last commit
2026-09-26
Last release
2026-09-26
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