# coding=utf-8
import sys
import json
#判断python版本 从而加载库
IS_PY3 = sys.version_info.major == 3
if IS_PY3:
from urllib.request import urlopen
from urllib.request import Request
from urllib.error import URLError
from urllib.parse import urlencode
from urllib.parse import quote_plus
else:
import urllib2
from urllib import quote_plus
from urllib2 import urlopen
from urllib2 import Request
from urllib2 import URLError
from urllib import urlencode
#百度API的接口
API_KEY = '4E1BG9lTnlSeIf1NQFlrSq6h'
SECRET_KEY = '544ca4657ba8002e3dea3ac2f5fdd241'
#合成的文本
TEXT = "欢迎使用百度语音合成。"
# 发音人选择, 0为普通女声,1为普通男生,3为情感合成-度逍遥,4为情感合成-度丫丫,默认为普通女声
PER = 4
# 语速,取值0-15,默认为5中语速
SPD = 5
# 音调,取值0-15,默认为5中语调
PIT = 5
# 音量,取值0-9,默认为5中音量
VOL = 5
# 下载的文件格式, 3:mp3(default) 4: pcm-16k 5: pcm-8k 6. wav
AUE = 3
#合成的文件格式
FORMATS = {3: "mp3", 4: "pcm", 5: "pcm", 6: "wav"}
FORMAT = FORMATS[AUE]
#用户唯一标识,用来区分用户,计算UV值。建议填写能区分用户的机器 MAC 地址或 IMEI 码,长度为60字符以内。
CUID = "123456PYTHON"
TTS_URL = 'http://tsn.baidu.com/text2audio'
class DemoError(Exception):
pass
""" TOKEN start """
#百度服务器
TOKEN_URL = 'http://openapi.baidu.com/oauth/2.0/token'
SCOPE = 'audio_tts_post' # 有此scope表示有tts能力,没有请在网页里勾选
#f获取令牌开始
def fetch_token():
print("fetch token begin")
#参数收集
params = {'grant_type': 'client_credentials',
'client_id': API_KEY,
'client_secret': SECRET_KEY}
#对服务器请求数据进行编码 基于字符编码
post_data = urlencode(params)
#判断 如果是python3 进行字符串转码
if (IS_PY3):
post_data = post_data.encode('utf-8')
#向服务器请求数据
req = Request(TOKEN_URL, post_data)
#异常处理
try:
f = urlopen(req, timeout=5)
result_str = f.read()
except URLError as err:
print('token http response http code : ' + str(err.code))
result_str = err.read()
if (IS_PY3):
result_str = result_str.decode()
#打印收集的参数
print(result_str)
#解析打印收集的参数
result = json.loads(result_str)
#打印解析打印收集的参数
print(result)
if ('access_token' in result.keys() and 'scope' in result.keys()): #判断是否有秘钥和端口开启
if not SCOPE in result['scope'].split(' '): #端口没有开启或开启错误报错
raise DemoError('scope is not correct')
#访问成功 打印令牌信息 过期时间信息
print('SUCCESS WITH TOKEN: %s ; EXPIRES IN SECONDS: %s' % (result['access_token'], result['expires_in']))
return result['access_token']
else:
raise DemoError('MAYBE API_KEY or SECRET_KEY not correct: access_token or scope not found in token response')
""" TOKEN end """
if __name__ == '__main__':
token = fetch_token()
#quote_plus()将url数据获取之后,并将其编码,从而适用与URL字符串中,使其能被打印和被web服务器接受
tex = quote_plus(TEXT) # 此处TEXT需要两次urlencode
print(tex)
params = {'tok': token, 'tex': tex, 'per': PER, 'spd': SPD, 'pit': PIT, 'vol': VOL, 'aue': AUE, 'cuid': CUID,
'lan': 'zh', 'ctp': 1} # lan ctp 固定参数
data = urlencode(params) #转换合成数据
#浏览器测试 +url+数据
print('test on Web Browser' + TTS_URL + '?' + data)
#请求数据
req = Request(TTS_URL, data.encode('utf-8'))
has_error = False
#异常处理
try:
#处理接收信息
f = urlopen(req)
result_str = f.read()
headers = dict((name.lower(), value) for name, value in f.headers.items())
has_error = ('content-type' not in headers.keys() or headers['content-type'].find('audio/') < 0)
except URLError as err:
print('asr http response http code : ' + str(err.code))
result_str = err.read()
has_error = True
#保存文件 + 格式 {3: "mp3", 4: "pcm", 5: "pcm", 6: "wav"}
save_file = "error.txt" if has_error else 'result.' + FORMAT
#写文件
with open(save_file, 'wb') as of:
of.write(result_str)
if has_error:
if (IS_PY3):
result_str = str(result_str, 'utf-8')
print("tts api error:" + result_str)
print("result saved as :" + save_file)
百度语音-语音识别 API-百度智能云
https://cloud.baidu.com/doc/SPEECH/ASR-API.html#.E6.8E.A5.E5.8F.A3.E8.BF.94.E5.9B.9E.E5.8F.82.E6.95.B0