Antigravity lets you steer agents by voice

Antigravity now has voice mode, enabled by Gemini Live, in both the Antigravity App and the Antigravity CLI. Turn it on and talk with the agent the way you'd talk to a teammate on a call: give it a task, steer the work while it runs, and answer permission prompts without clicking. The agent answers out loud in real time, and its work appears in the conversation as usual.

Working with an agent has mostly had a different rhythm: you type a prompt, the agent works, you read what it did, and you type again. As agents take on longer tasks, more of that loop is steering. You remember a detail you forgot to mention, answer a permission prompt, or wonder what the agent is doing right now. Each of those moments pulls you back to the keyboard and away from whatever you were looking at.

How voice mode works

Voice mode turns a conversation in the Antigravity App into a spoken, two-way conversation with the agent. Click Start Voice mode in the message box, choose a voice the first time, and start talking. It continues the conversation you're in, so the agent already has the context of everything before, including messages you typed.

The agent still does the real work in the conversation. It reads your code, edits files, runs commands, and shows you the results, so you can keep your eyes on your code while you listen. While you talk, a panel above the message box shows what you're saying, then lights up the agent's reply word by word as it speaks.

Voice mode runs on the Gemini Live model. It hears your voice directly instead of a transcript, so a misheard word in the transcript doesn't mean it misunderstood you. You can interrupt it at any time just by talking.

What you can do

Talk it through. Ask the agent to find the failing test and fix it, and it confirms what it's going to do and gets to work. Quick questions about something it just said get an answer right away; anything that needs your code, files, or tools becomes work in the conversation.

Steer while it works. Add a detail, correct course (“just check it, don't change anything yet”), or ask “What are you doing?” Say “stop” and the agent stops the running task. Say “hold on” when you need a moment to read.

Approve by voice, with guardrails. When the agent needs approval, it reads the request out loud with its recommendation and waits. Say “allow it just this once,” “allow it for this conversation,” or “no, run the tests first,” and the agent confirms with a quick “Done.” Your usual permissions still apply. Destructive actions, such as deleting files, running commands with elevated privileges, or force-pushing to a Git remote, can't be approved by voice; you click Allow on screen. You can still deny them by voice.

Quiet until you need it. By default, the agent works quietly and speaks up only when it has an answer or needs your input. Say “keep me posted” for a short update about every 30 seconds, or ask for a different interval, such as “update me once a minute.” Voice mode starts quiet again every time you turn it on.

Show it, don't just say it. Ask the agent to show you a table or draw a diagram, and it adds it to the conversation and walks you through it out loud instead of reading every cell. When you want an answer word for word, just ask.

Make it yours. Choose from nine voices and set the speaking speed from 0.75x to 2x from the call controls. If you switch to another conversation, voice mode keeps going in a floating dock.

Voice mode in your terminal

In the Antigravity CLI, run /voice live or press F6 in a conversation, and start talking. A status row below the prompt shows how long voice mode has been on and whether the agent is listening, thinking, or speaking. Press F6 to mute your microphone, and press Esc on an empty prompt to hang up when the agent is idle.

Other commands: /voice speaker changes the voice, /voice speed sets how fast the agent talks, and /voice duplex on lets you interrupt the agent by talking. Working over SSH? Run agy mic-serve on your own computer and start the CLI with ANTIGRAVITY_MIC set, and voice mode uses your computer's microphone and speaker.

Built on your conversation

Voice mode doesn't replace the conversation; it gives it a voice. The Gemini Live model can reach only the conversation you started voice mode in, and work on your files, commands, and tools happens in that conversation, under your usual permissions. You can also type a message or attach a screenshot or a log file while you talk; the agent acknowledges it out loud and works on it like a spoken request.

When you're done, say “Bye,” or click End. Everything the agent wrote, edited, or drew stays in the conversation, along with a transcript of what you both said, and any task that's still running keeps going after you hang up.

Key Features at a Glance

• Gemini Live voice: hears your voice directly, not a transcript – a misheard word doesn't mean a misunderstanding.
• Interruptions: talk over the agent at any time – steer without waiting for it to finish.
• Voice approvals: “allow it just this once” or “allow it for this conversation” – no clicking for routine permission prompts.
• Destructive-action guardrail: deleting files, elevated commands, and force-pushing need an on-screen Allow – the riskiest actions always get a second look.
• Quiet by default: the agent speaks only with an answer or a question, with updates about every 30 seconds on request.
• Nine voices, 0.75x to 2x speed: adjust from the call controls to suit how you listen.
• Mute shortcuts: Option+M on macOS or Alt+M on Windows and Linux mutes your microphone; Shift+Option+M or Alt+Shift+M mutes the agent's voice so you can read its replies instead.
• CLI support: /voice live or F6, plus agy mic-serve for SSH sessions.

Availability

Voice mode is available in the Antigravity App and in the Antigravity CLI version 1.5.0 and later.

In the App: start a new conversation or open an existing one, and with the message box empty, click Start Voice mode. Allow microphone access if asked, choose a voice, and start talking.

In the CLI: start it in your project, run /voice live or press F6, and start talking.

See the voice mode documentation to learn more, including how Antigravity handles your voice.

Google Antigravity is available at no charge for individuals, with basic weekly rate limits. Paid access is available through Google AI Pro and Google Cloud business plans; Google Cloud lists Standard and Plus plans starting at $30 USD per seat per month, while pay-as-you-go access has no seat fee and uses consumption-based pricing. Availability and plan terms may vary by country and account.