Plugin directory / UI Enhancements / dsh-voice
dsh-voice
Verified · installs & boots on dsh zhuiyueya/dsh-voice ↗
What it does
Voice for DeepSeek Harness（dsh） — speech-to-text input + read-aloud TTS for text-only DeepSeek, zero API key.
Works — verified, early-stage project
Voice for DeepSeek Harness（dsh） — speech-to-text input + read-aloud TTS for text-only DeepSeek, zero API key. It installs cleanly and boots without issues in our testing. It's early-stage but functional.
Install
This plugin is GitHub source (not published to npm) — install it straight from the repo:
dsh plugin --profile web add github:zhuiyueya/dsh-voice- Install pnpm once:
npm install -g pnpm. - Add it from GitHub:
dsh plugin --profile web add github:zhuiyueya/dsh-voice. - Restart
dsh web.
Note: plugins that ship a prepare build script may prompt pnpm to allow the build — add the key it prints under allowBuilds in pnpm-workspace.yaml, then re-run.
Test report
Verified: installed from GitHub, activated in the profile, and booted a task successfully.
Repository
github.com/zhuiyueya/dsh-voice ↗