speech_to_text.py

from google.cloud import speech
from google.cloud.speech import enums
from google.cloud.speech import types


client = speech.SpeechClient()
speech_file = "gcloud_test.wav"

with open(speech_file, 'rb') as audio_file:
    content = audio_file.read()

audio = types.RecognitionAudio(content=content)
config = types.RecognitionConfig(
    encoding=enums.RecognitionConfig.AudioEncoding.LINEAR16,
    sample_rate_hertz=16000,
    language_code='hi-IN')

response = client.recognize(config, audio)

for result in response.results:
        # The first alternative is the most likely one for this portion.
        alternative = result.alternatives[0]
        print(u'Transcript: {}'.format(alternative.transcript))
        print(u'Confidence: {}'.format(alternative.confidence))