
A live session, not a chat box
Tap Start and the microphone streams to the model. What is said appears as a transcript; what the assistant has to say appears beside it. Semantic voice detection knows when a speaker has finished, and you can interrupt the answer by talking. Answers come in brief, balanced or detailed length.
- OpenAI Realtime API, gpt-realtime-2
- Transcript and answers side by side
- Interrupt by speaking
- Brief, balanced or detailed answers





