Plugin directory / AI Models / @uniwell9797/dsh-voice-f9

@uniwell9797/dsh-voice-f9

Unverified

View on GitHub ↗ ← Back to plugin directory

0Stars
AI ModelsCategory
GitHubSource

What it does

Global hold-to-talk voice input for Windows, driven by a local SenseVoice model via sherpa-onnx. Hold F9 to speak in any application, release to insert the text at the caret; no network, no GPU.

⏳
Our take
Unverified — not yet install-tested; try it in your own environment.

“Verified” means our CI ran dsh plugin add in a clean profile and it booted — not a security audit and not an endorsement of third-party code.

Install

🧩 Let your agent install it (recommended)

Install the catalog once, then ask DeepSeek Harness to find and install this plugin.

dsh plugin add dshbase-catalog

Web profile:

dsh plugin --profile web add github:uniwell9797/dsh-voice-f9

View on GitHub ↗