This feature uses LOCAL AI stack: Faster Whisper for transcription, Ollama for chat, and Coqui TTS for speech. Fully offline! Click the microphone to record, click again to send.
Session Status:Inactive
Press the microphone button and start speaking. The AI will respond naturally as your conversation flows.
Click to speak
Activity Log
How to Use This Page
Start a Conversation: Click the "Start Session" button. The first time you'll need to approve microphone access in your browser.
Speaking to the AI:
Click the microphone button to START recording
Speak your message (take your time!)
Click the microphone button again to STOP and SEND
Wait for the AI to process and respond
Microphone States:
Gray - Session not started
Yellow - Session active, ready for recording
Pulsing Red - Recording in progress
Change Character: Select different AI characters from the dropdown menu before starting a session.
End Conversation: Click "Stop Session" to end.
Note: This version uses 100% local AI - Faster Whisper for speech-to-text, Ollama for chat, and Coqui TTS for text-to-speech. All processing happens on your server with no external API calls!