I was super excited when learning that Google has finally released its official speech API for developers. I have always been amazed by how great Google's speech recognition works in Android, Chrome, and other products.
I created a Google Cloud account, enabled the speech API, and created a few testing scripts following the Google Speech API documentation. The accuracy is super high, but the speed is insanely slow. An 18-second audio file would take their engine around 16 seconds to transcribe! Microsoft Bing Speech API only needs 3-4 seconds to do it!
Has anyone experienced the same? Or is it a problem of my configurations? Any help is highly 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"}}'