我嘗試利用百度語音雲API來實現一個包含TTS的桌面服務。已經成功取得回傳MP3,並且快取在cStringIO中,但不知道如何播放。程式碼播放拋出錯誤。
參考了http://guzalexander.com/2012/... 中提到的pywave/pyaudio/pyglet等方法。
程式碼如下:
#!/usr/bin/env python
#encoding=utf-8
#import wave
import pyaudio
import pyglet
import urllib, urllib2, pycurl
import base64
import json
import cStringIO
import binascii
## get access token by api key & secret key
def get_token():
apiKey = "xxxxxxxxxx"
secretKey = "yyyyyyyyyyyyyyyyyyyyy"
auth_url = "https://openapi.baidu.com/oauth/2.0/token?grant_type=client_credentials&client_id=" + apiKey + "&client_secret=" + secretKey;
res = urllib2.urlopen(auth_url)
json_data = res.read()
return json.loads(json_data)['access_token']
def dump_res(buf):
#print buf
pass
## post audio to server
def use_cloud(token):
fp = wave.open('vad_0.wav', 'rb')
nf = fp.getnframes()
f_len = nf * 2
audio_data = fp.readframes(nf)
cuid = "xxxxxxxxxx" #my xiaomi phone MAC
srv_url = 'http://vop.baidu.com/server_api' + '?cuid=' + cuid + '&token=' + token
http_header = [
'Content-Type: audio/pcm; rate=8000',
'Content-Length: %d' % f_len
]
c = pycurl.Curl()
c.setopt(pycurl.URL, str(srv_url)) #curl doesn't support unicode
#c.setopt(c.RETURNTRANSFER, 1)
c.setopt(c.HTTPHEADER, http_header) #must be list, not dict
c.setopt(c.POST, 1)
c.setopt(c.CONNECTTIMEOUT, 30)
c.setopt(c.TIMEOUT, 30)
c.setopt(c.WRITEFUNCTION, dump_res)
c.setopt(c.POSTFIELDS, audio_data)
c.setopt(c.POSTFIELDSIZE, f_len)
c.perform() #pycurl.perform() has no return val
def get_audio(token):
cuid = "00030DAF5784" # MAC address
text = "从前有座山,山上有个庙,庙里有个老和尚和小和尚,老和尚对小和尚说:"
#baidu_url = "http://tsn.baidu.com/text2audio?tex=" + urllib.urlencode(text) + "&lan=zh&cuid=" + cuid + "&ctp=1&tok=" + token
baidu_url = "http://tsn.baidu.com/text2audio?tex=" + urllib.quote(text) + "&lan=zh&cuid=" + cuid + "&ctp=1&tok=" + token
print("URL:\t{0}".format(baidu_url))
buf = cStringIO.StringIO()
c = pycurl.Curl()
c.setopt(c.URL, str(baidu_url)) #curl doesn't support unicode
#c.setopt(c.HTTPHEADER, http_header) #must be list, not dict
#c.setopt(c.GET, 1)
c.setopt(c.WRITEFUNCTION, buf.write)
c.setopt(c.CONNECTTIMEOUT, 30)
c.setopt(c.TIMEOUT, 30)
c.setopt(c.WRITEFUNCTION, dump_res)
c.perform() #pycurl.perform() has no return val
#print "type:\t{0}".format(c.CONTENT_TYPE)
print(c.getinfo(c.CONTENT_TYPE))
#print buf.getvalue()
song = pyglet.media.load(buf)
song.play()
buf.close()
if __name__ == "__main__":
token = get_token()
print("token:\t{0}".format(token))
#use_cloud(token)
get_audio(token)
拋出錯誤如下:
Traceback (most recent call last):
File "C:\BOM_Planner\source\soldering_assistant_mvp.py", line 87, in <module>
get_audio(token)
File "C:\BOM_Planner\source\soldering_assistant_mvp.py", line 79, in get_audio
song = pyglet.media.load(buf)
File "C:\Python27\lib\site-packages\pyglet\media\__init__.py", line 1429, in load
source = get_source_loader().load(filename, file)
File "C:\Python27\lib\site-packages\pyglet\media\__init__.py", line 1410, in load
return riff.WaveSource(filename, file)
File "C:\Python27\lib\site-packages\pyglet\media\riff.py", line 185, in __init__
file = open(filename, 'rb')
TypeError: coercing to Unicode: need string or buffer, cStringIO.StringO found
你寫的Python3就推薦pygame,可以用pygame.mixen.music來播放本機mp3檔。
當時我也找了很多都沒有成功,最後用pygame播放的。
這是我寫的一個例子。可以看看,我是把網路音樂儲存到本機mp3檔案再播放的,readme裡面有相關資訊。
https://github.com/kompasim/p...
如果是Linux環境下解決方案就比較多了,如果要實現跨平台建議用pygame。