I want to do prototype a voice interface. Adobe XD would be the perfect fit because you can use specific phrases to trigger elements and also play speech really easy. Unfortunately you need to hold your finger on the screen to "activate" the microphone when I view the screens on my phone. Is there a specific tool that offers a "always listening" function, while the prototype is opened? I can't believe it is that hard to find something, Protopie for example only offers the option to listen to general sound, not specific voice commands.
General sound - no it won't work - will react to any sound wave (conversation, impact etc.)
For example: You talking with co-workers - and interface activate (when it shouldn't).
The specific voice command seem better solution - like "Hey Siri".
It's possible to work on specific wave of voice (of the person) or sound. (the interface can only react to the tone of the owner's voice)
Instagram work as You mentioned - after click & hold (2s)
You will not find this ability within any prototyping tool. It is a somewhat difficult feature as it needs to start by default to listen and identify a trigger catchphrase.
A workaround would be to have the design illustrate that it is waiting for a verbal command and while presenting you can click on a white area to activate the feature and you can explain the stakeholders of what the correct flow or functionality would be there.