Speech side:
Audio Segmenting:
http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0144610#sec008
Then run FFMpeg with -s and -t with subprocess
Google Speech API: https://cloud.google.com/speech/reference/rest/v1beta1/speech/syncrecognize
curl 'https://speech.googleapis.com/v1beta1/speech:syncrecognize?key=AIzaSyBmmqjUsStJat65IP7KgKuH2cz6rRvlIr8' -H 'Referer: https://cloud.google.com/' -H 'Origin: https://cloud.google.com' -H 'User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.75 Safari/537.36' -H 'Content-Type: text/plain;charset=UTF-8' --data-binary '{"config":{"encoding":"LINEAR16","sampleRate":44100,"languageCode":"en-US","maxAlternatives":1},"audio":{"content":"BASE64_BINARY"}}' --compressed
Less than 1 min inline, better if under 30s
 
Video Side:
Thumbnail: https://trac.ffmpeg.org/wiki/Create%20a%20thumbnail%20image%20every%20X%20seconds%20of%20the%20video
Vision API:
curl 'https://vision.googleapis.com/v1/images:annotate?key=AIzaSyBzeghi0W7mGczap8SC8AmNudYOlwfU-KE' -H 'Referer: https://cloud.google.com/' -H 'Origin: https://cloud.google.com' -H 'User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.75 Safari/537.36' -H 'Content-Type: text/plain;charset=UTF-8' --data-binary '{"requests":[{"image":{"content":"BASE64"},"features":[{"type":"TYPE_UNSPECIFIED","maxResults":50},{"type":"TEXT_DETECTION","maxResults":50}]}]}' --compressed
 
CC:
Question: How to difference the zone of CC?
ASS: Put them there.
 
Style:
ASS: {\pos(369.675,206)} with response, 1s
 
Translation:
Toolkit+API+CAT
 
Transcode:
Release: