I’m Running Dextor’s version of Rasbian on a Raspberry 3
and using a Python script (camera-vision-logo.py)
I’m using the Cloud Vision Api to return Logos - using ‘LOGO_DETECTION’ - that works fine
Was wondering how to get the Pi to speak the returned value/response ?
I’m assuming you have to use Espeak which I’ve got working, but I’m just not sure how to covert the returned logo response to speech ?
Update:
have this working now
but if anyone has another way, nicer etc, i’m always interested
Using espeak
within the script I’ve defined the creation of a text file
and am writing the LABEL variable into that file, which is ‘response’ i.e. the logo
Once file is written to and closed
Then have Espeak read the file and speak what ever is in there (the response from Google Vision Api)
that’s it…he says after cpl hours of banging my head
Hey @faisalc, sounds like you got it! Sorry for the confusion and headbanging. Just a couple of quick pointers for anyone else lost on this . . .
We have our Google Vision API tutorials here in Github.
We have an example that uses Google Vision API and Espeak here, the candy sorting robot.
We have a tutorial specifically on using Espeak with the pi here.
http://www.dexterindustries.com/howto/make-your-raspberry-pi-speak/