What if I need both sound and text from smart glasses?
Look for a workflow that coordinates the two outputs. Having speakers and a display does not guarantee that an application uses them together or preserves context when you switch between them.
Give each output a clear job
Use speech for an explanation and text for details worth keeping: a name, address, time or choice. Reading a full transcript while hearing the same response can create unnecessary competition for attention. The useful combination is often a short visual summary that remains available after the spoken answer ends.
Imagine asking about a restaurant. Audio can describe the options while the display holds the selected name and distance. A follow-up should refer to that same selection. If the screen changes to a different result while speech continues, the interface has created a coordination problem even though both outputs technically work.