Antigravity CLI Introduces Voice Mode
Antigravity CLI now features a voice mode that allows users to interact with the agent using their voice.
Antigravity CLI Introduces Voice Mode
Antigravity CLI has introduced a new feature - voice mode, which can be activated using the command /voice or by pressing F5. This feature allows users to communicate with the agent using their voice, dictate their thoughts, and simply say whatever comes to mind.
The voice mode operates on the new model from Google - Gemini 3.5 Transcribe. This opens up new possibilities for interactive communication with technology, making it more accessible and convenient for users.
Why it matters
AnalysisThis new feature significantly simplifies user interaction with technology, allowing for more natural communication. The use of Google's new model enhances voice recognition accuracy.
Discuss in community
Share your questions and insights with developers
Related in Ecosystem
Practical guides, core terminology, and agent skills
I Love Antigravity Guide
This guide is dedicated to all developers leveraging the Google AI ecosystem, Antigravity IDE/CLI, and Gemini models.
Configuring Gemini via Antigravity & CLIProxyAPI for Hermes on VPS
Andrei Orlov's Complete Practical Engineering Guide: Deploying Gemini via Google Antigravity CLI and CLIProxyAPI to Power a Standalone Hermes Agent on a VPS.
MIT researchers show GPT-6 Astra can improve other AI models by editing their weights
In an experiment, Astra raised Qwen3.5-0.8B's accuracy on MATH-500 from 7.9% to 48.1% by changing only 0.016% of the model's weights.
Agent Skills & Custom Workflows
An architectural pattern for dynamically loading specialized procedural instructions, scripts, and templates (SKILL.md) into an agent's context window on demand (On-Demand Loading).