I was very excited to learn that Google had finally released its official speech API for developers. I have always been amazed at how Google's excellent speech recognition works in Android, Chrome, and other products.
I created a Google Cloud account, enabled the speech API and created some test scripts following the documentation of the Google Speech API . The accuracy is very high, but the speed is insanely slow. An 18 second sound file will take about 16 seconds to decrypt their engine! The Microsoft Bing Speech API only takes 3-4 seconds to do this!
Has anyone experienced the same thing? Or is it a problem with my configurations? Any help is much appreciated!
Here is the code I used:
BASH:
time curl "https://speech.googleapis.com/v1beta1/speech:syncrecognize?key={MY_API_KEY}" --header "Content-Type: application/json" --data '{"config":{"encoding":"FLAC","sample_rate":16000,"language_code":"en-US"},"audio":{"uri":"gs://accobot-speech/new_record.flac"}}'
source
share