An AI model's text-to-speech (TTS) function must always show the user the current action. The AI model must stop speaking when the user interacts with the page. The AI model must continue speaking when the user navigates away from the page.
By Pawan Nayar · from the LLOS AI Learning record
An AI model's text-to-speech (TTS) function must always show the user the current action.
The AI model must stop speaking when the user interacts with the page. The AI model must continue speaking when the user navigates away from the page.
The AI model's 'Listen' button should change to 'Stop' when speech begins. The button should change back to 'Listen' when speech ends. The AI model should never show 'Playing...' because this does not tell the user what to do. The AI model must stop speaking if the user clicks any other button on the same page. The AI model should continue speaking if the user leaves the page. This is like how YouTube works. The AI model should not stop speech when the browser tab changes or is minimized.
A student is listening to an AI model read a lesson. The student clicks the 'Next' button. The AI model immediately stops speaking and loads the next lesson. Later, the student is listening to another lesson. The student opens a new browser tab to check email. The AI model continues to read the lesson in the background.
Resolved from this lesson's own record — real definitions, not invented for this page.
More from the same record, pulled by shared topic — not written new for this page.
When an AI model uses text-to-speech, the text that is currently being spoken must highlight. This allows the user to listen and read at the same time.
A close button should have a strong visual style. This style should be visible all the time.
When a user sees many options, an AI model can show them in a list. If there are five or more options, a special button appears.
All text on light backgrounds must be a very dark color. Use colors like #1a1c1e or #333.
An AI model's text-to-speech (TTS) function must always show the user the current action. The AI model must stop speaking when the user interacts with the page. The AI model must continue speaking when the user navigates away from the page.