This module uses Google's newest Gemini 3.8 Live model, built for ultra-low-latency real-time voice conversation: press Start Conversation, allow microphone access, and just speak - the AI replies with natural speech in real time while transcripts of both sides are shown, and you can interrupt it mid-sentence and it will politely stop and listen. Compared with the previous generation, 3.8 Live picks up on your tone and emotion and adapts how it replies, filters out background noise and side conversations so it only responds when you are actually talking to it, and automatically detects and switches between languages mid-conversation with no reconfiguration. Great for language conversation practice, spoken Q&A, brainstorming, thinking out loud, and hands-free scenarios. You can toggle the AI reply transcript in the panel; press Stop Conversation to end. On a phone, the conversation stops automatically when the browser moves to the background, the screen locks, or the browser is closed. Headphones are recommended so the AI voice from your speakers is not picked up by the microphone. Audio input only - text input and file upload are not supported. Please use a recent Chrome or Edge browser with microphone support. Output content formats: Text/Audio Pricing: Medium This module supports continuous conversations. AI can make mistakes. Please verify important information.