Voice for DeepSeek Harness（dsh）
zhuiyueya/dsh-voice · skills
Voice for DeepSeek Harness（dsh） — speech-to-text input + read-aloud TTS for text-only DeepSeek, zero API key.
★ 4GitHub stars
3Forks
2026-09-03Last updated
JavaScriptLanguage
MITLicense
Key features
- Voice input (STT) — Web UIA mic button in the composer tool row.
- slopus/happy (23k★) — realtime voice interaction UX
- the transcript is written straight into the input box via the browser Web Speech API.
- Read-aloud (TTS) — Web UIA speaker button on every assistant reply.
- Zero API key for the Web UI — pure browser speech, works out of the box.
Install command
dsh plugin --profile web add github:zhuiyueya/dsh-voice