Hi!
I have reduced down and added a few features into the SAPI 5 speech
module I have created. You can now save and read wav files.
The test module tests most of the features I have in it at the moment.
I added the ability inside the Create method to set all the voice
parameters. You can change the voice, volume, rate, and pitch in the Create
method. They are dict values and just assign the values you want. Pitch and
rate are from -10 to 10 with 0 the norm. Where the volume is from 0% to 100%
but do not use the (%) symbol, just the integer number.
The default for change is 0 for any of the values and the default voice
will be the first on the list, which is Sam if you are using the Microsoft
SAPI 5 voices.
The names are listed in the test. So assignment depends on what you have
installed onto your machine. I have not changed any usage of eSpeak voices
to allow pitch adjustment yet. An error comes up for those voices because I
have not looked into what it wants.
This SAPI 5 engine will at least allow you to get started and includes
the methods saving and reading a wav file.
The wav methods are .SpeakToWav and SpeakFromWav so you could use it for
other possible things, such as web sites and games.
Enjoy testing it. I have not played with the bookmark method yet.
Bruce
#DRIVERS FOR SAPI 5 AND VOICES!
#NOTE THE CONSTANTS AND IN THE SPEAK FUNCTION AND THE ADDING/OR OF THE VALUES.
from comtypes.client import CreateObject
import _winreg
class constants4tts:
Wait = -1
Sync = 0
Async = 1
Purge = 2
Is_filename = 4
XML = 8
Not_XML = 16
Persist = 32
Punc = 64
class SynthDriver():
name="sapi5"
description="Microsoft Speech API version 5 (sapi.SPVoice)"
_voice = 0
_pitch = 0
_voices = []
_wait = -1 #WAIT INDEFINITELY
_sync = 0 #WAIT UNTIL SPEECH IS DONE.
_async = 1 #DO NOT WAIT FOR SPEECH
_purge = 2 #CLEAR SPEAKING BUFFER
_is_filename = 4 #OPEN WAV FILE TO SPEAK OR SAVE TO WAV FILE
_xml = 8 #XML COMMANDS, PRONUNCIATION AND GRAMMER.
_not_xml = 16 #NO XML COMMANDS
_persist_xml = 32 #Changes made in one speak command persist to other calls
to Speak.
_punc = 64 #PRONOUNCE ALL PUNCTUATION!
def check(self):
try:
r=_winreg.OpenKey(_winreg.HKEY_CLASSES_ROOT,"SAPI.SPVoice")
r.Close()
return True
except:
return False
#INITIALIZE ENGINE!
def init(self):
try:
self.tts = CreateObject( 'sapi.SPVoice')
self._voice=0
self._voiceCount = len(self.tts.GetVoices())
for v in range(self._voiceCount):
self._voices.append( self.tts.GetVoices()[v])
return True
except:
return False
#TERMINATE INSTANCE OF ENGINE!
def terminate(self):
del self.tts
#NUMBER OF VOICES FOR ENGINE!
def getVoiceCount(self):
return len(self.tts.GetVoices())
#NAME OF A VOICE BY NUMBER!
def getVoiceNameByNum(self, num):
return self.tts.GetVoices()[num-1].GetDescription()
#NAME OF A VOICE!
def getVoiceName(self):
return self.tts.GetVoices()[ self._voice].GetDescription()
#WHAT IS VOICE RATE?
def getRate(self):
"MICROSOFT SAPI 5 RATE IS -10 TO 10"
return (self.tts.rate)
#WHAT IS THE VOICE PITCH?
def getPitch(self):
"PITCH FOR MICROSOFT SAPI 5 IS AN XML COMMAND!"
return self._pitch
#GET THE ENGINE VOLUME!
def getVolume(self):
"MICROSOFT SAPI 5 VOLUME IS 1% TO 100%"
return self.tts.volume
#GET THE VOICE NUMBER!
def getVoiceNum(self):
return self._voice
#SET A VOICE BY NAME!
def setVoiceByName(self, name):
"VOICE IS SET BY NAME!"
for i in range( self._voiceCount):
if self.tts.GetVoices()[ i].GetDescription().find( name) >= 0:
self.tts.Voice = self._voices[i]
# self.tts.Speak( "%s Set!" % name)
self._voice=i
break
if i >= self._voiceCount:
self.tts.Speak( "%s Not Found!" % name)
#USED FOR BOOKMARKING AND USE LATER!
def _get_lastIndex(self):
bookmark=self.tts.status.LastBookmark
if bookmark!="" and bookmark is not None:
return int(bookmark)
else:
return -1
#NOW SET ENGINE PARMS!
#SET THE VOICE RATE!
def setRate(self, rate):
"MICROSOFT SAPI 5 RATE IS -10 TO 10"
if rate > 10: rate = 10
if rate < -10: rate = -10
self.tts.Rate = rate
#SET PITCH OF THE VOICE!
def setPitch(self, value):
"MICROSOFT SAPI 5 pitch is really controled with xml around speECH TEXT
AND IS -10 TO 10"
if value > 10: value = 10
if value < -10: value = -10
self._pitch=value
#SET THE VOICE VOLUME!
def setVolume(self, value):
"MICROSOFT SAPI 5 VOLUME IS 1% TO 100%"
self.tts.Volume = value
#CREATE ANOTHER INSTANCE OF A VOICE!
def createVoice(self, name):
num = 0
for i in range( self._voiceCount):
if self.tts.GetVoices()[ i].GetDescription().find( name) >= 0:
num=i
break
new_tts = CreateObject( 'sapi.SPVoice')
new_tts.Voice = self._voices[ num]
return (new_tts)
#SPEAKING TEXT!
#SPEAK TEXT USING BOOKMARKS AND PITCH!
def SpeakText(self, text, wait=False, index=None):
"SPEAK TEXT AND XML FOR PITCH MUST REPLACE ANY <> SYMBOLS BEFORE USING
XML BRACKETED TEXT"
flags = constants4tts.XML
text = text.replace( "<", "<")
pitch = ((self._pitch*2)-100)/10
if isinstance(index, int):
bookmarkXML = "<Bookmark Mark = \"%d\" />" % index #NOTE \" FOR XML
FORMAT CONVERSION!
else:
bookmarkXML = ""
flags = constants4tts.XML
if wait is False:
flags += constants4tts.Async
self.tts.Speak( "<pitchabsmiddle = \"%s\">%s%s</pitch>" % (pitch,
bookmarkXML, text), flags)
#CANCEL SPEAK IN PROGRESS!
def cancel(self):
#if self.tts.Status.RunningState == 2:
self.tts.Speak(None, 1|constants4tts.Purge)
#SET AUDIO STREAM FOR OUTPUT TO A FILE!
def SpeakToWav(self, filename, text, voice):
"""THIS METHOD ASSUMES THE IMPORT OF COMTYPES.CLIENT createObject SO
A VOICE AND FILE STREAM OBJECT ARE CREATED WITH THE PASSING IN OF 3
STRINGS:
THE FILE NAME TO SAVE THE VOICE INTO, THE TEXT, AND THE VOICE
SPOKEN IN.
ONCE THE TEXT IS SPOKEN INTO THE FILE, IT IS CLOSED AND THE OBJECTS
DESTROYED!"""
num = 0
for i in range( self._voiceCount):
if self.tts.GetVoices()[ i].GetDescription().find( voice) >= 0:
num=i
break
stream = CreateObject("SAPI.SpFileStream")
tts4file = CreateObject( 'sapi.SPVoice')
tts4file.Voice = self._voices[ num]
from comtypes.gen import SpeechLib
stream.Open( filename, SpeechLib.SSFMCreateForWrite)
tts4file.AudioOutputStream = stream
tts4file.Speak( text, 0)
stream.Close()
del tts4file
del stream
#NOW SPEAK THE WAV FILE SAVED!
def SpeakFromWav(self, filename, sync=0, async=0, purge=0):
"SPEAKING A WAV FILE ONLY!"
self.tts.Speak( filename, sync |async |purge |self._is_filename)
#SPEAK TEXT!
def Speak(self, text, wait=0, sync=0, async=0, purge=0, isfile=0, xml=0,
not_xml=0, persist=0, punc=0):
"SAPI 5 HAS NO PITCH SO HAS TO BE IN TEXT SPOKEN!"
pitch=self._pitch
self.tts.Speak( "<pitch absmiddle='%s'/>%s" % (pitch, text), wait |sync
|async |purge |isfile |xml |not_xml |persist |punc)
#SPEAK TEXT WITHOUT PITCH!
def Speaking(self, text, wait=0, sync=0, async=0, purge=0, isfile=0, xml=0,
not_xml=0, persist=0, punc=0):
"SPEAKING A FILE WITHOUT PITCH"
self.tts.Speak( text, wait |sync |async |purge |isfile |xml |not_xml
|persist |punc)
#SET THE VOICE BY VALUE!
def setVoice(self,value):
"SET VOICE AND SAY ITS DESCRIPTION!"
if value < 1:
value=1
if value > self._voiceCount:
value = self._voiceCount
self.tts.Voice = self._voices[ value-1]
vd = self.tts.GetVoices()[ value-1].GetDescription().find( " ")
# self.tts.Speak( vd[ vd.find(" "):])
self._voice=value-1
#READ ALL THE VOICES IN THE ENGINE!
def read_Voices(self):
self.tts.Speak( "Voices are:")
for i in range( self._voiceCount):
print self.getVoiceNameByNum(i+1)
self.tts.Voice = self.tts.GetVoices()[i]
vd = self.tts.GetVoices()[ i].GetDescription()
self.tts.Speak( "%d) %s" % (i+1, vd[ vd.find(" "):]))
def Create( vs={}):
"CREATE A SAPI VOICE INSTANCE!"
vp = {"name":"Sam", "volume":100, "rate":0, "pitch":0}
for i in vs: vp[i] = vs[i]
newVoice = SynthDriver()
if newVoice.check():
newVoice.init()
newVoice.setVoiceByName( vp["name"])
newVoice.setVolume( vp["volume"])
newVoice.setRate( vp["rate"])
newVoice.setPitch( vp["pitch"])
return newVoice
else:
print "SAPI Engine Is Not Installed On This Computer!"
return Null
import Sapi5, time, os
av = Sapi5.Create()
Mike = Sapi5.Create( {"name":"Mike", "pitch":1, "rate":1})
Mary = Sapi5.Create( {"name":"Mary", "pitch":1, "rate":-1})
SYNC = av._sync
ASYNC = av._async
PURGE = av._purge
ISFILE = av._is_filename
XML = av._xml
NOT_XML = av._not_xml
PERSIST = av._persist_xml
PUNC = av._punc
WAIT = av._wait
av.Speak("Hello!")
av.Speak( "I am speaking in the default voice!")
av.Speak( "Number of voices is: %d" % av.getVoiceCount())
av.read_Voices()
Mike.Speak( "Hello! Now saying the punctuation in this sentence.", PUNC)
time.sleep(.5)
Mary.Speak( "Mary and Mike are saving a wav file!")
time.sleep(.5)
av.SpeakToWav( 'spain.wav', 'Mary says, The rain in Spain falls mainly on the
plain.', 'Mary')
av.SpeakFromWav( 'spain.wav', ASYNC)
av.SpeakToWav( "test.wav", "Mike says, Hello To The World!", "Mike")
av.SpeakFromWav( "test.wav", SYNC)
time.sleep(.5)
av.setVoiceByName( "Mary")
Mike.setPitch(5)
Mike.setVolume( 100)
Mike.Speak( " The Volume Is Set At Speaker Volume!")
av.setRate( 5)
av.setPitch(5)
av.Speak( "Rate At 75%, and Pitch 5 or 75% of maximum pitch!")
time.sleep(1)
av.setPitch(0)
av.setRate(0)
av.Speak( "The rate and pitch are now set for normal!")
#av.setVoiceByName( "eSpeak-EN+M2")
#av.Speak("Hello! I am a eSpeak man!")
av.Speaking( "Spell This! <spell> Spell This! </spell>", XML)
time.sleep(1)
av.setVoiceByName( "Mary")
av.Speak( "Hit enter key to stop speaking!")
Mike.Speak( "Hey! Hit enter key!")
av.setPitch(10)
av.Speak("Pitch 100%", ASYNC)
av.setPitch(5)
av.Speak("Pitch 75%", ASYNC)
av.setPitch(0)
av.Speak("Pitch 50%", ASYNC)
av.setPitch( -5)
av.Speak("Pitch 25%", ASYNC)
av.setPitch( -10)
av.Speak("Pitch 0%", ASYNC)
av.setPitch(0)
Mike.Speak( "Hit enter key!", ASYNC)
hit = raw_input("Hit enter key >")
av.Speak(" Mary Says, Now Good bye", ASYNC, PURGE)
Mike.Speak(" Mike Says, Hey! Good bye", ASYNC, PERSIST)
av.setVoiceByName( "Sam")
av.Speak( "<volume level='50'/> Sam says goodbye")
Mike.Speak( "<volume level='50'/> goodbye")
Mary.Speak( "<volume level='50'/> goodbye")
Mary.terminate()
Mike.terminate()
av.terminate()
_______________________________________________
Tutor maillist - Tutor@python.org
http://mail.python.org/mailman/listinfo/tutor
