Talk, do not dictate
Voice activity detection understands when your turn ends and keeps the conversation moving.
A voice layer for DeepSeek Harness. Talk naturally, hear the answer while it arrives and keep the conversation with you anywhere on the desktop.
DSH KITT is built for conversation, not dictation. It detects when you stop speaking, sends the message, waits for the agent and reads the reply sentence by sentence — without breaking your flow.


Voice activity detection understands when your turn ends and keeps the conversation moving.
A compact overlay stays above your work so you can talk from the editor or any other application.
Select microphone, audio output, language and voice, with neural, system and local options.
Global shortcuts keep listening, mute and playback controls accessible beyond the browser.
Free and open source, MIT licensed. Listed in the DeepSeek Harness plugin catalogue.
dsh plugin --profile web add dsh-kitt-voice