STT_Google_Speech_API

#!/usr/bin/python
# -*- coding: utf-8 -*-
"""
__author__ = 'm'
__time__ = '15-4-20'
网络限制，未测试
"""
import os
import re
import wave
import pyaudio
import requests

CHUNK = 1024
FORMAT = pyaudio.paInt16
CHANNELS = 2
RATE = 8000
RECORD_SECONDS = 5
WAVE_OUTPUT_FILENAME = "output.wav"


# 录音并写入文件
def record_wave():
    p = pyaudio.PyAudio()

    stream = p.open(format=FORMAT,
                    channels=CHANNELS,
                    rate=RATE,
                    input=True,
                    frames_per_buffer=CHUNK)

    print("* recording")

    frames = []

    for i in range(0, int(RATE / CHUNK * RECORD_SECONDS)):
        data = stream.read(CHUNK)
        frames.append(data)

    print("* done recording")

    stream.stop_stream()
    stream.close()
    p.terminate()

    wf = wave.open(WAVE_OUTPUT_FILENAME, 'wb')
    wf.setnchannels(CHANNELS)
    wf.setsampwidth(p.get_sample_size(FORMAT))
    wf.setframerate(RATE)
    wf.writeframes(b''.join(frames))
    wf.close()


def speech2text(flac_file, rate, yourkey):
    """
    使用Google Speech API进行语音识别
    """
    url = 'https://www.google.com/speech-api/v2/recognize?output=json&lang=zh-CN&key=' + yourkey
    files = {'file': open(flac_file, 'rb')}
    headers = {'Content-Type': 'audio/x-flac; rate='+str(rate)+';'}
    # 网络不通，则可设置requests代理，https://requests-docs-cn.readthedocs.org/zh_CN/latest/user/advanced.html#id11
    # Socks5代理需要使用额外的包，http://blog.gohjkl.com/coder/2015/03/09/Python-Requests-socks-proxy/
    return_text = requests.post(url, files=files, headers=headers).text
    # 获取识别的文本内容
    trans_text = re.findall('transcript\":\"(.*?)\"', return_text)
    return ''.join(trans_text)


def text2cmd(cmds):
    if cmds.find("谷歌") > -1:
        os.system("chrome https://www.google.com")
    if cmds.find("百度") > -1:
        os.system("chrome https://www.baidu.com")


if __name__ == '__main__':
    while True:
        """
        Enter your Google API Key
        """
        key = 'xxxxxxxxxxxxxxxxxxxx'
        # 录音并写入文件
        record_wave()
        # 转换
        os.system('flac output.wav')
        # 语音识别
        cmds_text = speech2text('output.flac', RATE, key)
        # 执行指令
        text2cmd(cmds_text)