Web   ·   Wiki   ·   Activities   ·   Blog   ·   Lists   ·   Chat   ·   Meeting   ·   Bugs   ·   Git   ·   Translate   ·   Archive   ·   People   ·   Donate
summaryrefslogtreecommitdiffstats
path: root/Speak.activity/face.py
blob: e77fe8f7a05590e67e02c85b8c2648f9c22f56ce (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
# Speak.activity
# A simple front end to the espeak text-to-speech engine on the XO laptop
# http://wiki.laptop.org/go/Speak
#
# Copyright (C) 2008  Joshua Minor
# This file is part of Speak.activity
#
# Parts of Speak.activity are based on code from Measure.activity
# Copyright (C) 2007  Arjun Sarwal - arjun@laptop.org
# 
#     Speak.activity is free software: you can redistribute it and/or modify
#     it under the terms of the GNU General Public License as published by
#     the Free Software Foundation, either version 3 of the License, or
#     (at your option) any later version.
# 
#     Speak.activity is distributed in the hope that it will be useful,
#     but WITHOUT ANY WARRANTY; without even the implied warranty of
#     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
#     GNU General Public License for more details.
# 
#     You should have received a copy of the GNU General Public License
#     along with Speak.activity.  If not, see <http://www.gnu.org/licenses/>.


import sys
import os
from urllib import (quote, unquote)
import subprocess
import random
from sugar.activity import activity
from sugar.datastore import datastore
from sugar.presence import presenceservice
import logging 
import gtk
import gobject
import pango
import cjson
from gettext import gettext as _

# try:
#     sys.path.append('/usr/lib/python2.4/site-packages') # for speechd
#     import speechd.client
# except:
#     print "Speech-dispatcher not found."

from sugar.graphics.toolbutton import ToolButton
from sugar.graphics.toolcombobox import ToolComboBox
from sugar.graphics.combobox import ComboBox
import sugar.graphics.style as style

import pygst
pygst.require("0.10")
import gst

import audio
import eye
import glasses
import mouth
import voice
import fft_mouth
import waveform_mouth

logger = logging.getLogger('speak')

PITCH_MAX = 100
RATE_MAX = 100
FACE_PAD = 2

class Status:
    def __init__(self):
        self.voice = voice.defaultVoice()
        self.pitch = PITCH_MAX/2
        self.rate = RATE_MAX/2
        self.eyes = [eye.Eye] * 2
        self.mouth = mouth.Mouth

    def serialize(self):
        eyes    = { eye.Eye : 1,
                    glasses.Glasses : 2 }
        mouths  = { mouth.Mouth : 1,
                    fft_mouth.FFTMouth : 2,
                    waveform_mouth.WaveformMouth : 3 }

        return cjson.encode({
            'voice' : { 'language'  : self.voice.language,
                        'gender'    : self.voice.gender,
                        'name'      : self.voice.name },
            'pitch' : self.pitch,
            'rate'  : self.rate,
            'eyes'  : [eyes[i] for i in self.eyes],
            'mouth' : mouths[self.mouth] })

    def deserialize(self, buf):
        eyes    = { 1: eye.Eye,
                    2: glasses.Glasses }
        mouths  = { 1: mouth.Mouth,
                    2: fft_mouth.FFTMouth,
                    3: waveform_mouth.WaveformMouth }

        data = cjson.decode(buf)
        self.voice.language = data['voice']['language']
        self.voice.gender = data['voice']['gender']
        self.voice.name = data['voice']['name']
        self.pitch = data['pitch']
        self.rate = data['rate']
        self.eyes = [eyes[i] for i in data['eyes']]
        self.mouth = mouths[data['mouth']]

class View(gtk.EventBox):
    def __init__(self, fill_color=style.COLOR_BUTTON_GREY):
        gtk.EventBox.__init__(self)

        self.status = Status()
        self.fill_color = fill_color

        self.connect('size-allocate', self._size_allocate_cb)

        self._audio = audio.AudioGrab()
        self._synth = None
        # try:
        #     self._synth = speechd.client.SSIPClient("Speak.activity")
        #     try:
        #         # Try some speechd v0.6.6 features
        #         print "Output modules:", self._synth.list_output_modules()
        #         print "Voices:", self._synth.list_synthesis_voices()
        #     except:
        #         pass
        # except:
        #     self._synth = None
        #     print "Falling back to espeak command line tool."

        # make an empty box for some eyes
        self._eyes = None
        self._eyebox = gtk.HBox()
        self._eyebox.show()
        
        # make an empty box to put the mouth in
        self._mouth = None
        self._mouthbox = gtk.HBox()
        self._mouthbox.show()
        
        # layout the screen
        box = gtk.VBox(homogeneous=False)
        box.pack_start(self._eyebox)
        box.pack_start(self._mouthbox, False)
        box.set_border_width(FACE_PAD)
        self.modify_bg(gtk.STATE_NORMAL, self.fill_color.get_gdk_color())
        self.add(box)

        self.update()
        
    def look_ahead(self):
        if self._eyes:
            map(lambda e: e.look_ahead(), self._eyes)

    def look_at(self, x, y):
        if self._eyes:
            map(lambda e, x=x, y=y: e.look_at(x,y), self._eyes)

    def update(self, status = None):
        if not status:
            status = self.status
        else:
            self.status = status

        if self._eyes:
            for eye in self._eyes:
                self._eyebox.remove(eye)
        if self._mouth:
            self._mouthbox.remove(self._mouth)

        self._eyes = []

        for i in status.eyes:
            eye = i(self.fill_color)
            self._eyes.append(eye)
            self._eyebox.pack_start(eye, padding=FACE_PAD)
            #eye.set_size_request(300,300)
            eye.show()

        self._mouth = status.mouth(self._audio, self.fill_color)
        self._mouth.show()
        self._mouthbox.add(self._mouth)

        # enable mouse move events so we can track the eyes while the mouse is over the mouth
        #self._mouth.add_events(gtk.gdk.POINTER_MOTION_MASK)

    def say(self, something):
        if self._audio is None:
            return
        
        logger.debug('%s: %s' % (self.status.voice.name, something))
        pitch = int(self.status.pitch)
        rate = int(self.status.rate)

        if self._synth is not None:
            # speechd uses -100 to 100
            pitch = pitch*2 - 100
            # speechd uses -100 to 100
            rate = rate*2 - 100

            self._synth.set_rate(rate)
            self._synth.set_pitch(pitch)
            self._synth.set_language(self.status.voice.language)
            self._synth.speak(something) #, callback=self._synth_cb)
        else:
            # espeak uses 0 to 99
            pitch = pitch
            # espeak uses 80 to 370
            rate = 80 + (370-80) * rate / 100

            # ideally we would stream the audio instead of writing to disk each time...
            wavpath = "/tmp/speak.wav"
            subprocess.call(["espeak", "-w", wavpath, "-p", str(pitch), "-s", str(rate), "-v", self.status.voice.name, something], stdout=subprocess.PIPE)
            self._audio.playfile(wavpath)
    
    def quiet(self):
        self._audio.stop_sound_device()

    def verbose(self):
        self._audio.restart_sound_device()

    def _size_allocate_cb(self, widget, allocation):
        self._mouthbox.set_size_request(-1, int(allocation.height/2.5))