I would love to use this cool features. Is it possible to use an ip cam or webcam for face detection and amazon echo for tts? For example, i would like to have a cam in the floor and if someone enters the face detection starts, after detection maybe output text trough tts on amazon echo in floor. So could i also give Alexa things to do when entering maybe.
Or could i place a raspberry pi with a cam to send images to the face detection module and output voice from tts on raspberry pi?
Alexa is a definitive no. At the moment alexa is only able to “answer” to you so unless you trigger it it can not speak. Face recognition should work with any camera input registered in HA.
The tts via raspberry pi is possible but I currently don’t know which way would be the best here. But I will check with the tts components source to see what’s possible there.
I did a quick check. And you can only send TTS voice data to a media player to play. So if you wanted to let the raspberry pi speak you would need to do the TTS part on the raspberry pi AFAIK.
I read about that and I am currently using NotifyMyAndroid to get Text across which works…but the Android TTS engine is just aweful. Lannouncer does use it as well doesn’t it?