voice.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# vim: ai ts=4 sts=4 et sw=4 ft=python cc=80

"""
Voice Recognition
=================
Voice recognition using google webservice

See: http://src.chromium.org/viewvc/chrome/trunk/src/content/browser/speech/
* google_one_shot_remote_engine.cc

To convert audio to flac::

    $ sox audiofile.wav audiofile.flac rate 16k
"""

try:
    from urllib.parse import urlencode, urljoin
    from urllib.error import URLError, HTTPError
    from urllib.request import Request, urlopen
except ImportError:  # python2
    from urllib import urlencode                                # noqa
    from urlparse import urljoin                                # noqa
    from urllib2 import urlopen, Request, URLError, HTTPError   # noqa


def process(audiofile, *args, **kwargs):
    params = urlencode({
        'lang': kwargs.pop('lang', 'es-ES'),          # (necessary) language
        'xjerr': '1',                                 # TODO: document
        'output': 'pb',                               # TODO: document
        'pfilter': kwargs.pop('pfilter', '1'),        # profanity filter
        'client': kwargs.pop('client', 'chromium'),   # browser
        'maxresults': kwargs.pop('maxresults', '4'),  # max results
    })
    headers = {
        'Content-Type': 'audio/x-flac; rate=16000',
    }

    url = 'https://www.google.com/speech-api/v1/recognize?{0}'.format(params)
    with open(audiofile, 'rb') as audio:
        data = audio.read()
        req = Request(url, data, headers)

        try:
            response = urlopen(req)
        except HTTPError as e:
            print('We failed to reach a server.')
            print('Reason: ', e.reason)
        except URLError as e:
            print('The server couldn\'t fulfill the request.')
            print('Error code: ', e.code)
        else:
            print(response.read())


def main():
    import argparse
    parser = argparse.ArgumentParser(description='Voice recognition command line.')  # nopep8
    parser.add_argument('audiofile', metavar='audiofile', type=str, help='Audio file in flac to process')  # nopep8
    parser.add_argument('-l', '--lang', dest='lang', default='es-ES', help='Language to recognize voice')  # nopep8
    parser.add_argument('-p', '--pfilter', dest='pfilter', default='1', help='Profanity filter')  # nopep8
    parser.add_argument('-r', '--maxresults', dest='maxresults', default='4', help='Number of results')  # nopep8

    args = vars(parser.parse_args())
    process(**args)

if __name__ == '__main__':
    main()