A FACE. A VOICE. A CONVERSATION.
A little company.
A little expression.
Getting my ears ready…
Meet Robby. Talk naturally, interrupt whenever you need to.
Microphone off. Click Start talking and allow microphone access.
Speech recognition: waiting for audio.
Talk to Robby, not the background
Say “Hey Robbie, I’m Christoph” or “Hey Robby, ich bin Christoph.” Another person can join the same way. Robby remembers each voice for this session and submits after about one second without that speaker.
Experimental voice matching, not authentication. Overlapping speech can still be uncertain. Typed messages bypass voice enrollment.
Explore and blend all 40 ↗
Luna’s sentence-level acting directions drive the face. Audio only moves the mouth.
Camera tracking stays in your browser. Voice is processed on this server.
Conversation text is sent to the configured Luna API. Speaker cues are not authentication.