Hi!
I am giving you the Python version of creating SAPI methods and properties
and of course you can change the names of the definitions if you so desire to
your liking.
Below is a class setup. You will note several things in this, one of which
is
the key word "self" which is used to point to the object created by the class
inside
of it's self...
All procedures first parm is the object itself and since it is it's self, that
is
what is placed as the first parm.
I added a constants class and use it for XML commands mostly.
This also uses the Windows Registry and that is the second thing imported for we
are only creating an object and looking for a registry key for SAPI installation
on the computer. Of course this registry check could be done for Windoweyes as
well and you could make up your own Properties/Methods list for Windoweyes.
You will note that the parms inside the parameter list have assigned values,
that is the default if no values are passed in. This allows you to set defaults.
I also give you a procedure to making a .wav file of speech being said. You
can
create an audio file of any spoken text.
Note:
I did not mention before but the next line below a def statement that has quotes
is a description of the procedure which also can be displayed when asking for a
description of a property/method,
so it is used when exposing the method.
You will also note triple quotes (""") this allows multiple lines with line
breaks
to be displayed. This comes in handy when making a long help/description list
having many lines.
I also have methods for bookmarks and spelling, misspelling and all that stuff.
Methods
for most of the SAPI object.
Bruce
#Global Stuff:
#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 for SAPI constants:
class constants4tts:
Wait = -1
Sync = 0
Async = 1
Purge = 2
Is_filename = 4
XML = 8
Not_XML = 16
Persist = 32
Punc = 64
#Class for SAPI object, properties and methods:
class SynthDriver():
name="sapi5"
description="Microsoft Speech API version 5 (sapi.SPVoice)"
_pitch = 0 #SAPI itself has no pitch, it is an XML Command
_voices = [] #Storage for voice list.
_words = {} #Dictionary storage for word pronounciation substitution.
_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!
#Check to see if SAPI is installed on your computer:
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 NUMBER!
def getVoiceName(self, num):
return self.tts.GetVoices()[num].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 pronounce.
def Pronounce(self):
return (wordPronounce)
#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 THE VOICE BY VALUE!
def setVoice(self,value):
"SET VOICE AND SAY ITS DESCRIPTION!"
if value < 1:
value=0
if value >= self._voiceCount:
value = self._voiceCount - 1
self.tts.Voice = self._voices[ value]
vd = self.tts.GetVoices()[ value].GetDescription().find( " ")
# self.tts.Speak( vd[ vd.find(" "):])
self._voice=value
#SET THE VOICE BY ORDINAL VALUE!
def setVoiceByNum(self,value):
"SET VOICE BY ITS ORDINAL VALUE STARTING AT 0 AND SAY ITS DESCRIPTION!"
self.setVoice( value)
#SET A VOICE BY NAME!
def setVoiceByName(self, name):
"VOICE IS SET BY NAME!"
t=-1
for i in range( self._voiceCount):
if self.tts.GetVoices()[ i].GetDescription().find( name) >= 0:
t=i
self.tts.Voice = self._voices[i]
# self.tts.Speak( " %s " % "Now") #name)
self._voice=i
break
if t == -1:
self.tts.Voice = self._voices[i]
self._voice=i
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%"
if value > 100: value = 100
if value <= 0: value = 0
self.tts.Volume = value
#CREATE ANOTHER INSTANCE OF A VOICE!
def createVoice(self, voice):
num = 0
for i in range( self._voiceCount):
if self.tts.GetVoices()[ i].GetDescription().find( voice) >= 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)
try:
self.tts.Speak( "<pitchabsmiddle = \"%s\">%s%s</pitch>" % (pitch,
bookmarkXML,
text), flags)
# self.tts.Speak( "<pitch absmiddle='%s'/>%s" % (pitch, text), wait
|sync
|async |purge |isfile |xml |not_xml |persist |punc)
except:
# Error probably due to no class for voice.
self.setVoice( 0)
self.tts.Speak( "<pitchabsmiddle = \"%s\">%s%s</pitch>" % (pitch,
bookmarkXML,
text), flags)
#pass
#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
#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
try:
self.tts.Speak( "<pitch absmiddle='%s'/>%s" % (pitch, text), wait
|sync
|async |purge |isfile |xml |not_xml |persist |punc)
except:
# Error probably due to no class for voice.
self.setVoice( 1)
self.tts.Speak( "<pitch absmiddle='%s'/>%s" % (pitch, text), wait
|sync
|async |purge |isfile |xml |not_xml |persist |punc)
#pass
# self.tts.Speak( 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"
try:
self.tts.Speak( text, wait |sync |async |purge |isfile |xml |not_xml
|persist |punc)
except:
# Error probably due to no class for voice.
self.setVoice( 1)
self.tts.Speak( text, wait |sync |async |purge |isfile |xml |not_xml
|persist |punc)
#pass
#READ ALL THE VOICES IN THE ENGINE!
def read_Voices(self):
self.tts.Speak( "Voices are:")
for i in range( self._voiceCount):
print self.getVoiceName(i)
self.tts.Voice = self.tts.GetVoices()[i]
vd = self.tts.GetVoices()[ i].GetDescription()
self.tts.Speak( "%d) %s" % (i, vd[ vd.find(" "):]))
#Add words to the pronounciation list:
def add2Pronounce(self, word, misspelling):
self._words[ word] = misspelling
#Replace word in sentence before speaking:
def doPronounce(self, sentence):
for word, misspelling in self._words.items():
sentence = sentence.replace( word, misspelling)
return (sentence)
---
This email has been checked for viruses by Avast antivirus software.
https://www.avast.com/antivirus
_______________________________________________
Any views or opinions presented in this email are solely those of the author
and do not necessarily represent those of Ai Squared.
For membership options, visit
http://lists.window-eyes.com/options.cgi/scripting-window-eyes.com/archive%40mail-archive.com.
For subscription options, visit
http://lists.window-eyes.com/listinfo.cgi/scripting-window-eyes.com
List archives can be found at
http://lists.window-eyes.com/private.cgi/scripting-window-eyes.com
