speech-to-text.py

def speech_to_text(bucket_name, audio_blob_name):
    client = speech_v1p1beta1.SpeechClient()
    # storage_uri = 'gs://cloud-samples-data/speech/brooklyn_bridge.mp3'
    storage_uri = 'gs://' + bucket_name + '/' + audio_blob_name
    # The language of the supplied audio
    language_code = "en-GB"
    # Sample rate in Hertz of the audio data sent
    sample_rate_hertz = 44100

    encoding = enums.RecognitionConfig.AudioEncoding.MP3
    config = {
        "language_code": language_code,
        "sample_rate_hertz": sample_rate_hertz,
        "encoding": encoding,
        "enable_word_time_offsets": True
    }
    audio = {"uri": storage_uri}

    response = client.recognize(config, audio)
    for result in response.results:
        # First alternative is the most probable result
        alternative = result.alternatives[0]
        for word in alternative.words:
            print("Start Time: {}".format(word.start_time))
            print("End Time: {}".format(word.end_time))

        print(u"Transcript: {}".format(alternative.transcript))
    return alternative.transcript