A simple Google Speech API sample for Python2.

transcribe.py

# coding:utf-8

import argparse
import base64
import json

from googleapiclient import discovery
import httplib2
import Tkinter as tk
import tkFileDialog


DISCOVERY_URL = ('https://{api}.googleapis.com/$discovery/rest?'
                 'version={apiVersion}')

def get_speech_service():
    http = httplib2.Http()

    return discovery.build(
        'speech', 'v1beta1', http=http, discoveryServiceUrl=DISCOVERY_URL, developerKey='<API Key>')


def main(speech_file):
    """Transcribe the given audio file.

    Args:
        speech_file: the name of the audio file.
    """
    with open(speech_file, 'rb') as speech:
        speech_content = base64.b64encode(speech.read())

    service = get_speech_service()
    service_request = service.speech().syncrecognize(
        body={
            'config': {
                'encoding': 'LINEAR16',  # raw 16-bit signed LE samples
                'sampleRate': 44100,  # 16 khz
                'languageCode': 'ja-JP',  # a BCP-47 language tag
            },
            'audio': {
                'content': speech_content.decode('UTF-8')
                }
            })
    response = service_request.execute()
    
    f = tkFileDialog.asksaveasfile(mode='w', defaultextension=".txt")
    if f is None: # asksaveasfile return `None` if dialog closed with "cancel".
        return
    f.write(response['results'][0]['alternatives'][0]['transcript'].encode('utf-8'))
    f.close()

def onCancel():
    exit()

if __name__ == '__main__':
    root = tk.Tk()
    root.title("transcriber")
    root.option_add('*font', ('FixedSys', 14))
    tk.Label(text="transcribing...").pack()

    root.update()

    file_path = tkFileDialog.askopenfilename()
    main(file_path)