Real conversation sessions
This page calls the TinkySpeak runtime with a live model. Your message and conversation history shape each set of proposed replies. Select your own words; the model cannot speak or choose for you.
Say something to it. Watch the conversation build.
Type what a partner said and the choices appear. Pick one, deliver it, and watch the memory count up — partner turn, your words, partner turn — until you reset it. Then show it a photo and the tiles become what you are looking at.
Drinks
Try
Or show it a photo
Live model · online demo. Messages and photos are sent to the model service. Conversation sessions expire after 30 minutes.
What the app controls
Memory 0
What your app receives
Being precise about this page.
Live photo understanding
The sample photos and your uploads are analyzed by the actual vision pipeline. Replies come from that scan, with no recorded-result replay. Photos are sent to the model service; the session retains observations, not image bytes.
The symbols are the point
Turn on “use my own symbols” and the artwork changes while the words do not. That is the boundary: you bring the symbols, we supply the conversation.
Every control here is an API call.
| On this page | In your code |
|---|---|
| Typing a partner turn | session.hear({text}) |
| Tapping a tile | session.select({choiceId}) |
| Deliver it | session.speak({draftId}) → your speech engine → confirmSpeech({speechId, outcome}) |
| Showing a photo | session.scan({images, mode}) |
| Choices, length, tiles | profile — or setProfile() |
| Reset the conversation | session.reset() |
ContinueSee to Speak