The conversation cycle
Each exchange follows a cycle:
- You speak — your voice is captured by the microphone
- Speech recognition — your words are converted to text
- AI thinking — the tutor processes what you said and formulates a response
- Speech synthesis — the tutor's response is converted to speech
- You hear — the tutor speaks through your device or headphones
This cycle happens in seconds, creating a natural back-and-forth conversation.
Barge-in (interrupting the tutor)
When using headphones, you can interrupt the tutor at any time by speaking. This is called barge-in. The tutor stops, listens to what you say, and responds.
On loudspeaker, barge-in is disabled because the microphone picks up the tutor's own voice. Headphones are strongly recommended for the best conversational experience.
Text transcript
Everything the tutor says appears as text on screen. This helps you follow along, especially for:
- New vocabulary words you might not catch by ear
- Complex explanations that benefit from reading and listening
- Language learning, where seeing the written form reinforces the spoken form