What exactly does the Gemini CLI integration do?

It adds a hook to your Gemini CLI config. When Gemini CLI finishes a turn or asks a question, wispa shows a reply window where you answer by voice or text, and sends your answer back into the session.

Do I have to edit config files by hand?

No. Flip the Gemini CLI switch in wispa's Integrations tab and it writes the hook for you; toggle it off to remove it cleanly. Start a new Gemini CLI session for the change to take effect.

Does it pop up on every single message?

By default, it only pops up when the agent's message looks like a question or asks for input, so it stays out of the way the rest of the time. You can switch it to appear on every turn if you prefer.

Does my answer go back into the same session?

Yes. Continuation mode returns your reply straight into the running session and works even when the terminal is in the background. You can also choose Paste, which types it into the terminal like a normal dictation.

Can I fix a mistake before it sends?

Always. The window opens with a text field, so you can speak or type, correct anything, and nothing is sent until you press Send or Enter. Esc dismisses it without answering.

Does this work with Claude Code and Codex?

Yes. The same reply overlay supports Claude Code and Codex too, each with its own page. This one covers Gemini CLI.

wispa for coding agents

Answer Gemini CLI by voice.

When Gemini CLI needs your input, wispa pops up right where you are working. Answer by voice; it lands straight back in the session.

Download for Mac

Requires wispa for macOS 13+. Free in beta, no account.

Gemini is waiting

wispa-landing/api

The contact form posts to /api/contact, which doesn’t exist yet.

Do you want me to:

Create the API route with email forwarding
Store submissions in the database for now
Add validation with error messages first

Let me know which direction you’d prefer.

Cancel esc Speak ⌘L Send ⏎

How it works

Set it up once, then just talk.

Turn on the Gemini CLI hook

Open wispa, go to Integrations, and flip the Gemini CLI switch. It writes the hook for you; start a new session to activate.
Gemini CLI pauses and asks

When your agent needs you, the reply window appears over whatever app you are in, with its message and project.
Answer out loud

Hold your dictation key and speak, or just type. Hit Send, and your answer lands back in the session.