File size: 8,352 Bytes
78360e7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
"""Add commentMore actions

Notification sounds for Wan2GP video generation application

Pure Python audio notification system with multiple backend support

"""

import os
import sys
import threading
import time
import numpy as np


def generate_notification_beep(volume=50, sample_rate=44100):
    """Generate pleasant C major chord notification sound"""
    if volume == 0:
        return np.array([])
    
    volume = max(0, min(100, volume))
    
    # Volume curve mapping: 25%->50%, 50%->75%, 75%->100%, 100%->105%
    if volume <= 25:
        volume_mapped = (volume / 25.0) * 0.5
    elif volume <= 50:
        volume_mapped = 0.5 + ((volume - 25) / 25.0) * 0.25
    elif volume <= 75:
        volume_mapped = 0.75 + ((volume - 50) / 25.0) * 0.25
    else:
        volume_mapped = 1.0 + ((volume - 75) / 25.0) * 0.05  # Only 5% boost instead of 15%
    
    volume = volume_mapped
    
    # C major chord frequencies
    freq_c = 261.63  # C4
    freq_e = 329.63  # E4  
    freq_g = 392.00  # G4
    
    duration = 0.8
    t = np.linspace(0, duration, int(sample_rate * duration), False)
    
    # Generate chord components
    wave_c = np.sin(freq_c * 2 * np.pi * t) * 0.4
    wave_e = np.sin(freq_e * 2 * np.pi * t) * 0.3
    wave_g = np.sin(freq_g * 2 * np.pi * t) * 0.2
    
    wave = wave_c + wave_e + wave_g
    
    # Prevent clipping
    max_amplitude = np.max(np.abs(wave))
    if max_amplitude > 0:
        wave = wave / max_amplitude * 0.8
    
    # ADSR envelope
    def apply_adsr_envelope(wave_data):
        length = len(wave_data)
        attack_time = int(0.2 * length)
        decay_time = int(0.1 * length)
        release_time = int(0.5 * length)
        
        envelope = np.ones(length)
        
        if attack_time > 0:
            envelope[:attack_time] = np.power(np.linspace(0, 1, attack_time), 3)
        
        if decay_time > 0:
            start_idx = attack_time
            end_idx = attack_time + decay_time
            envelope[start_idx:end_idx] = np.linspace(1, 0.85, decay_time)
        
        if release_time > 0:
            start_idx = length - release_time
            envelope[start_idx:] = 0.85 * np.exp(-4 * np.linspace(0, 1, release_time))
        
        return wave_data * envelope
    
    wave = apply_adsr_envelope(wave)
    
    # Simple low-pass filter
    def simple_lowpass_filter(signal, cutoff_ratio=0.8):
        window_size = max(3, int(len(signal) * 0.001))
        if window_size % 2 == 0:
            window_size += 1
        
        kernel = np.ones(window_size) / window_size
        padded = np.pad(signal, window_size//2, mode='edge')
        filtered = np.convolve(padded, kernel, mode='same')
        return filtered[window_size//2:-window_size//2]
    
    wave = simple_lowpass_filter(wave)
    
    # Add reverb effect
    if len(wave) > sample_rate // 4:
        delay_samples = int(0.12 * sample_rate)
        reverb = np.zeros_like(wave)
        reverb[delay_samples:] = wave[:-delay_samples] * 0.08
        wave = wave + reverb
    
    # Apply volume first, then normalize to prevent clipping
    wave = wave * volume * 0.5
    
    # Final normalization with safety margin
    max_amplitude = np.max(np.abs(wave))
    if max_amplitude > 0.85:  # If approaching clipping threshold
        wave = wave / max_amplitude * 0.85  # More conservative normalization
    
    return wave


def play_audio_with_pygame(audio_data, sample_rate=44100):
    """Play audio using pygame backend"""
    try:
        import pygame
        # Initialize pygame mixer only if not already initialized
        if not pygame.mixer.get_init():
            pygame.mixer.pre_init(frequency=sample_rate, size=-16, channels=2, buffer=1024)
            pygame.mixer.init()
        else:
            # Reinitialize with new settings if needed
            current_freq, current_size, current_channels = pygame.mixer.get_init()
            if current_freq != sample_rate or current_channels != 2:
                pygame.mixer.quit()
                pygame.mixer.pre_init(frequency=sample_rate, size=-16, channels=2, buffer=1024)
                pygame.mixer.init()
        
        audio_int16 = (audio_data * 32767).astype(np.int16)
        
        # Convert mono to stereo
        if len(audio_int16.shape) == 1:
            stereo_data = np.column_stack((audio_int16, audio_int16))
        else:
            stereo_data = audio_int16
        
        sound = pygame.sndarray.make_sound(stereo_data)
        sound.play()
        pygame.time.wait(int(len(audio_data) / sample_rate * 1000) + 100)
        # Don't quit mixer - this can interfere with Gradio server
        # pygame.mixer.quit()
        return True
        
    except ImportError:
        return False
    except Exception as e:
        print(f"Pygame error: {e}")
        return False


def play_audio_with_sounddevice(audio_data, sample_rate=44100):
    """Play audio using sounddevice backend"""
    try:
        import sounddevice as sd
        sd.play(audio_data, sample_rate)
        sd.wait()
        return True
        
    except ImportError:
        return False
    except Exception as e:
        print(f"Sounddevice error: {e}")
        return False


def play_audio_with_winsound(audio_data, sample_rate=44100):
    """Play audio using winsound backend (Windows only)"""
    if sys.platform != "win32":
        return False
        
    try:
        import winsound
        import wave
        import tempfile
        import uuid
        
        temp_dir = tempfile.gettempdir()
        temp_filename = os.path.join(temp_dir, f"notification_{uuid.uuid4().hex}.wav")
        
        try:
            with wave.open(temp_filename, 'w') as wav_file:
                wav_file.setnchannels(1)
                wav_file.setsampwidth(2)
                wav_file.setframerate(sample_rate)
                
                audio_int16 = (audio_data * 32767).astype(np.int16)
                wav_file.writeframes(audio_int16.tobytes())
            
            winsound.PlaySound(temp_filename, winsound.SND_FILENAME)
            
        finally:
            # Clean up temp file
            for _ in range(3):
                try:
                    if os.path.exists(temp_filename):
                        os.unlink(temp_filename)
                    break
                except:
                    time.sleep(0.1)
            
        return True
        
    except ImportError:
        return False
    except Exception as e:
        print(f"Winsound error: {e}")
        return False


def play_notification_sound(volume=50):
    """Play notification sound with specified volume"""
    if volume == 0:
        return
    
    audio_data = generate_notification_beep(volume=volume)
    
    if len(audio_data) == 0:
        return
    
    # Try audio backends in order
    audio_backends = [
        play_audio_with_pygame,
        play_audio_with_sounddevice,
        play_audio_with_winsound,
    ]
    
    for backend in audio_backends:
        try:
            if backend(audio_data):
                return
        except Exception as e:
            continue
    
    # Fallback: terminal beep
    print(f"All audio backends failed, using terminal beep")
    print('\a')


def play_notification_async(volume=50):
    """Play notification sound asynchronously (non-blocking)"""
    def play_sound():
        try:
            play_notification_sound(volume)
        except Exception as e:
            print(f"Error playing notification sound: {e}")
    
    sound_thread = threading.Thread(target=play_sound, daemon=True)
    sound_thread.start()


def notify_video_completion(video_path=None, volume=50):
    """Notify about completed video generation"""
    play_notification_async(volume)


if __name__ == "__main__":
    print("Testing notification sounds with different volumes...")
    print("Auto-detecting available audio backends...")
    
    volumes = [25, 50, 75, 100]
    for vol in volumes:
        print(f"Testing volume {vol}%:")
        play_notification_sound(vol)
        time.sleep(2)
    
    print("Test completed!")