This gadget would attempt to create subtitles for what the user is saying, feed them into an online translation api, then display the result in front of them so other individual’s gadgets can see them.
Displaying in front of the user from their gadget rather than sent straight to another’s gadget may be good for privacy, but would only be visible from one angle. Alternatively, the app could have an approval function, and then when you speak, it would appear in others’ view like closed captioning in scripted VR games right now. This method would also allow translation to be done on the receivers gadget, allowing a group speaking and listening in more than two languages to communicate.
Who would use this gadget?
Efficacy of digital translation, especially when also dependent on speech to text, is not ideal, so this couldn’t really be used for any serious functions, but as a last resort or in multiplayer games, this could be useful to most people.
Assuming that you're on the team, what other skillsets would you need to make this project happen over a couple days of hacking?
I am not experienced with coding, I’m just trying to provide the concept for consideration.
What will be the toughest part of building this gadget?
The app would need to connect to general translation apis like Google Translate, which is a common thing already, but ideally it would alert the user if they’re speaking too quickly, maybe by showing them the english input as it is turned into text, and let others maybe click a “don’t understand” indicator for when things don’t work as intended.
What would this gadget do?
This gadget would attempt to create subtitles for what the user is saying, feed them into an online translation api, then display the result in front of them so other individual’s gadgets can see them.
Displaying in front of the user from their gadget rather than sent straight to another’s gadget may be good for privacy, but would only be visible from one angle. Alternatively, the app could have an approval function, and then when you speak, it would appear in others’ view like closed captioning in scripted VR games right now. This method would also allow translation to be done on the receivers gadget, allowing a group speaking and listening in more than two languages to communicate.
Who would use this gadget?
Efficacy of digital translation, especially when also dependent on speech to text, is not ideal, so this couldn’t really be used for any serious functions, but as a last resort or in multiplayer games, this could be useful to most people.
Assuming that you're on the team, what other skillsets would you need to make this project happen over a couple days of hacking?
I am not experienced with coding, I’m just trying to provide the concept for consideration.
What will be the toughest part of building this gadget?
The app would need to connect to general translation apis like Google Translate, which is a common thing already, but ideally it would alert the user if they’re speaking too quickly, maybe by showing them the english input as it is turned into text, and let others maybe click a “don’t understand” indicator for when things don’t work as intended.