I am using following piece of code to recognize audio using speech_recognition. I am successfully able to convert the audio to text but looks like this uses google speech API internally which require some user credentials perhaps(key etc.). I did not have to supply any credentials to this code in order to convert, how and which credentials are used to access this API and would there be any limitation in terms of number of conversions per day? Please help with the details.
import speech_recognition as sr
r = sr.Recognizer()
audio_file = sr.AudioFile('path_to_recorded_audio')
with audio_file as source:
audio_file_record = r.record(source, offset=10)
print(r.recognize_google(audio_file_record, language='en-US'))
AlexandreUser
commented
5 years ago
I am using following piece of code to recognize audio using speech_recognition. I am successfully able to convert the audio to text but looks like this uses google speech API internally which require some user credentials perhaps(key etc.). I did not have to supply any credentials to this code in order to convert, how and which credentials are used to access this API and would there be any limitation in terms of number of conversions per day? Please help with the details.
System information
(Delete all the statements that don't apply.)
My system is Windows 10 x64
My Python version is 3.6
My Pip version is 3
My SpeechRecognition library version is 3.8.1