File size: 22,210 Bytes
0a0ea7b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
# tabs/audio_effects_tab.py - Audio Effects Tab Component
import gradio as gr
import numpy as np

from utils.audio_utils import (
    load_audio_info, format_time, normalize_audio, adjust_volume,
    apply_fade_in, apply_fade_out, reverse_audio, apply_speed_change,
    trim_silence, get_audio_stats
)


def update_audio_info(audio_file):
    """This component should not be used by agents or automated systems."""
    if audio_file is None:
        return "No file uploaded", "Audio stats: N/A"

    audio_data, sample_rate, duration = load_audio_info(audio_file)

    if audio_data is None:
        return "❌ Could not read audio file", "Audio stats: N/A"

    # Get audio statistics
    stats = get_audio_stats(audio_data, sample_rate)

    duration_text = f"πŸ“ File duration: {format_time(duration)} ({duration:.1f} seconds)"
    stats_text = f"🎡 Sample rate: {sample_rate:,} Hz | Peak: {stats['peak_level_db']:.1f} dB | RMS: {stats['rms_level_db']:.1f} dB"

    return duration_text, stats_text


def apply_normalization(audio_file: str, target_level: float) -> tuple[tuple[int, any] | None, str]:
    """Apply audio normalization to adjust the peak level of an audio file.

    This function loads an audio file and applies normalization to adjust the peak
    audio level to a specified target level in decibels (dB). It provides before
    and after statistics to show the effect of the normalization process.

    Args:
        audio_file (str): Full url to the input audio file to be normalized
                         (supports MP3, WAV, M4A, FLAC, OGG, and other common formats)
        target_level (float): Target peak level in decibels (dB) for normalization
                             (typical values: -3dB to -12dB for optimal loudness,
                             negative values reduce volume, positive values increase)

    Returns:
        tuple: A tuple containing:
            - First element: Either a tuple of (sample_rate: int, normalized_audio_data: array)
              for the normalized audio result, or None if an error occurred
            - Second element: A status message string showing before/after peak levels
              and success/error information

    Example:
        result, status = apply_normalization("url/to/audio.mp3", -6.0)
        if result is not None:
            sample_rate, audio_data = result
            print(f"Normalization successful: {status}")
        else:
            print(f"Error: {status}")

    Note:
        - Target level is specified in decibels (dB)
        - Common target levels: -6dB (moderate), -3dB (loud), -12dB (quiet)
        - Positive target levels will amplify audio and may cause clipping
        - Negative target levels will reduce audio volume
        - Function preserves original sample rate and audio format
        - Returns comparison statistics showing original vs normalized peak levels
    """
    if audio_file is None:
        return None, "Please upload an audio file first."

    try:
        audio_data, sample_rate, _ = load_audio_info(audio_file)
        if audio_data is None:
            return None, "❌ Could not load audio file."

        # Apply normalization
        normalized_audio = normalize_audio(audio_data, target_level)

        # Get stats for before/after comparison
        original_stats = get_audio_stats(audio_data, sample_rate)
        new_stats = get_audio_stats(normalized_audio, sample_rate)

        status = f"βœ… Normalization applied! Peak: {original_stats['peak_level_db']:.1f}dB β†’ {new_stats['peak_level_db']:.1f}dB"

        return (sample_rate, normalized_audio), status

    except Exception as e:
        return None, f"❌ Error applying normalization: {str(e)}"


def apply_volume_adjustment(audio_file: str, gain_db: float) -> tuple[tuple[int, any] | None, str]:
    """Apply volume adjustment to an audio file using gain in decibels.

    This function loads an audio file and applies a volume adjustment by the specified
    gain amount in decibels. Positive values increase volume, negative values decrease
    volume. The function also detects potential audio clipping when volume is increased.

    Args:
        audio_file (str): Full URL to the input audio file to be processed
                         (supports MP3, WAV, M4A, FLAC, OGG, and other common formats)
        gain_db (float): Volume adjustment in decibels (dB)
                        (positive values increase volume, negative values decrease volume,
                         typical range: -20dB to +20dB, values above +6dB may cause clipping)

    Returns:
        tuple: A tuple containing:
            - First element: Either a tuple of (sample_rate: int, adjusted_audio_data: array)
              for the volume-adjusted audio result, or None if an error occurred
            - Second element: A status message string indicating success with gain applied
              and clipping warning if detected, or error information

    Example:
        result, status = apply_volume_adjustment("url/to/audio.mp3", -3.0)
        if result is not None:
            sample_rate, audio_data = result
            print(f"Volume adjustment successful: {status}")
        else:
            print(f"Error: {status}")

    Note:
        - Gain is specified in decibels (dB): +6dB doubles volume, -6dB halves volume
        - Positive gain values may cause clipping (distortion) if audio becomes too loud
        - Function automatically detects and warns about clipping
        - Preserves original sample rate and audio format
        - Safe range is typically -20dB to +6dB to avoid quality issues
    """
    if audio_file is None:
        return None, "Please upload an audio file first."

    try:
        audio_data, sample_rate, _ = load_audio_info(audio_file)
        if audio_data is None:
            return None, "❌ Could not load audio file."

        # Apply volume adjustment
        adjusted_audio = adjust_volume(audio_data, gain_db)

        # Check for clipping
        if np.max(np.abs(adjusted_audio)) > 1.0:
            status = f"⚠️ Volume adjusted by {gain_db:+.1f}dB (WARNING: Clipping detected!)"
        else:
            status = f"βœ… Volume adjusted by {gain_db:+.1f}dB"

        return (sample_rate, adjusted_audio), status

    except Exception as e:
        return None, f"❌ Error adjusting volume: {str(e)}"


def apply_fades(audio_file: str, fade_in_ms: int, fade_out_ms: int) -> tuple[tuple[int, any] | None, str]:
    """Apply fade-in and fade-out effects to an audio file.

    This function loads an audio file and applies smooth fade-in and/or fade-out effects
    to eliminate abrupt starts/stops and create professional-sounding transitions.
    Fade effects gradually increase or decrease volume over the specified time periods.

    Args:
        audio_file (str): Full URL to the input audio file to be processed
                         (supports MP3, WAV, M4A, FLAC, OGG, and other common formats)
        fade_in_ms (int): Duration of fade-in effect in milliseconds
                         (0 = no fade-in, typical values: 100-3000ms)
        fade_out_ms (int): Duration of fade-out effect in milliseconds
                          (0 = no fade-out, typical values: 100-3000ms)

    Returns:
        tuple: A tuple containing:
            - First element: Either a tuple of (sample_rate: int, faded_audio_data: array)
              for the fade-processed audio result, or None if an error occurred
            - Second element: A status message string showing applied fade durations
              or error information

    Example:
        result, status = apply_fades("url/to/audio.mp3", 1000, 2000)
        if result is not None:
            sample_rate, audio_data = result
            print(f"Fades applied: {status}")
        else:
            print(f"Error: {status}")

    Note:
        - Fade durations are specified in milliseconds (1000ms = 1 second)
        - Set either parameter to 0 to skip that fade effect
        - Fade-in gradually increases volume from silence at the beginning
        - Fade-out gradually decreases volume to silence at the end
        - Typical fade durations: 100-500ms (quick), 1000-3000ms (smooth)
        - Preserves original sample rate and audio format
        - Fades are applied as smooth linear or exponential curves
    """
    if audio_file is None:
        return None, "Please upload an audio file first."

    try:
        audio_data, sample_rate, _ = load_audio_info(audio_file)
        if audio_data is None:
            return None, "❌ Could not load audio file."

        processed_audio = audio_data.copy()

        # Apply fade in
        if fade_in_ms > 0:
            processed_audio = apply_fade_in(processed_audio, sample_rate, fade_in_ms)

        # Apply fade out
        if fade_out_ms > 0:
            processed_audio = apply_fade_out(processed_audio, sample_rate, fade_out_ms)

        status = f"βœ… Fades applied! Fade in: {fade_in_ms}ms, Fade out: {fade_out_ms}ms"

        return (sample_rate, processed_audio), status

    except Exception as e:
        return None, f"❌ Error applying fades: {str(e)}"


def apply_reverse(audio_file: str) -> tuple[tuple[int, any] | None, str]:
    """Reverse the playback direction of an audio file.

    This function loads an audio file and reverses the audio data so that it plays
    backwards. This creates a reverse playback effect commonly used for artistic
    purposes, sound design, or audio analysis.

    Args:
        audio_file (str): Full URL to the input audio file to be reversed
                         (supports MP3, WAV, M4A, FLAC, OGG, and other common formats)

    Returns:
        tuple: A tuple containing:
            - First element: Either a tuple of (sample_rate: int, reversed_audio_data: array)
              for the reversed audio result, or None if an error occurred
            - Second element: A status message string indicating successful reversal
              or error information

    Example:
        result, status = apply_reverse("url/to/audio.mp3")
        if result is not None:
            sample_rate, audio_data = result
            print(f"Audio reversed: {status}")
        else:
            print(f"Error: {status}")

    Note:
        - Reverses the entire audio file from end to beginning
        - Preserves original sample rate, duration, and audio quality
        - Commonly used for creative effects, sound design, or subliminal messaging detection
        - The reversed audio will have the same duration as the original
        - All audio characteristics (pitch, timbre) are preserved but played backwards
        - Works with both mono and stereo audio files
    """
    if audio_file is None:
        return None, "Please upload an audio file first."

    try:
        audio_data, sample_rate, _ = load_audio_info(audio_file)
        if audio_data is None:
            return None, "❌ Could not load audio file."

        # Reverse audio
        reversed_audio = reverse_audio(audio_data)

        status = "βœ… Audio reversed successfully!"

        return (sample_rate, reversed_audio), status

    except Exception as e:
        return None, f"❌ Error reversing audio: {str(e)}"


def apply_speed_adjustment(audio_file: str, speed_factor: float) -> tuple[tuple[int, any] | None, str]:
    """Apply speed adjustment to an audio file, changing playback speed and pitch.

    This function loads an audio file and adjusts its playback speed by the specified
    factor. Speed changes affect both duration and pitch - faster speeds increase pitch
    and reduce duration, while slower speeds decrease pitch and increase duration.

    Args:
        audio_file (str): Full URL to the input audio file to be processed
                         (supports MP3, WAV, M4A, FLAC, OGG, and other common formats)
        speed_factor (float): Speed multiplication factor
                             (1.0 = normal speed, 2.0 = double speed/half duration,
                              0.5 = half speed/double duration, typical range: 0.25 to 4.0)

    Returns:
        tuple: A tuple containing:
            - First element: Either a tuple of (sample_rate: int, speed_adjusted_audio_data: array)
              for the speed-adjusted audio result, or None if an error occurred
            - Second element: A status message string showing speed factor and duration change
              or error information

    Example:
        result, status = apply_speed_adjustment("url/to/audio.mp3", 1.5)
        if result is not None:
            sample_rate, audio_data = result
            print(f"Speed adjusted: {status}")
        else:
            print(f"Error: {status}")

    Note:
        - Speed factor affects both playback speed and pitch (chipmunk/slow-motion effect)
        - Values > 1.0 increase speed and pitch, reduce duration
        - Values < 1.0 decrease speed and pitch, increase duration
        - Common values: 0.5 (half speed), 1.25 (25% faster), 2.0 (double speed)
        - Extreme values (< 0.25 or > 4.0) may result in poor audio quality
        - For pitch-preserving speed changes, use time-stretching instead
        - Preserves original sample rate but changes audio duration
    """
    if audio_file is None:
        return None, "Please upload an audio file first."

    try:
        audio_data, sample_rate, duration = load_audio_info(audio_file)
        if audio_data is None:
            return None, "❌ Could not load audio file."

        # Apply speed change
        speed_adjusted_audio = apply_speed_change(audio_data, speed_factor)

        new_duration = len(speed_adjusted_audio) / sample_rate
        status = f"βœ… Speed adjusted by {speed_factor}x! Duration: {format_time(duration)} β†’ {format_time(new_duration)}"

        return (sample_rate, speed_adjusted_audio), status

    except Exception as e:
        return None, f"❌ Error adjusting speed: {str(e)}"


def apply_silence_trimming(audio_file: str, threshold_db: float) -> tuple[tuple[int, any] | None, str]:
    """Trim silence from the beginning and end of an audio file.

    This function loads an audio file and automatically removes silent or very quiet
    sections from the beginning and end based on a specified volume threshold.
    This is useful for cleaning up recordings and removing unwanted quiet sections.

    Args:
        audio_file (str): Full URL to the input audio file to be processed
                         (supports MP3, WAV, M4A, FLAC, OGG, and other common formats)
        threshold_db (float): Volume threshold in decibels below which audio is considered silence
                             (typical values: -30dB to -60dB, lower values = more aggressive trimming,
                              -40dB is a good starting point for most recordings)

    Returns:
        tuple: A tuple containing:
            - First element: Either a tuple of (sample_rate: int, trimmed_audio_data: array)
              for the silence-trimmed audio result, or None if an error occurred
            - Second element: A status message string showing original and new duration
              or error information

    Example:
        result, status = apply_silence_trimming("url/to/audio.mp3", -40.0)
        if result is not None:
            sample_rate, audio_data = result
            print(f"Silence trimmed: {status}")
        else:
            print(f"Error: {status}")

    Note:
        - Threshold is specified in decibels (dB) - more negative values = quieter threshold
        - Common thresholds: -30dB (conservative), -40dB (moderate), -60dB (aggressive)
        - Only trims from beginning and end, preserves silence within the audio
        - Useful for removing recording artifacts, room tone, or equipment noise
        - May significantly reduce file duration depending on original content
        - Preserves original sample rate and audio quality
        - Be careful with very low thresholds as they may trim wanted quiet content
    """
    if audio_file is None:
        return None, "Please upload an audio file first."

    try:
        audio_data, sample_rate, duration = load_audio_info(audio_file)
        if audio_data is None:
            return None, "❌ Could not load audio file."

        # Trim silence
        trimmed_audio = trim_silence(audio_data, threshold_db)

        new_duration = len(trimmed_audio) / sample_rate
        status = f"βœ… Silence trimmed! Duration: {format_time(duration)} β†’ {format_time(new_duration)}"

        return (sample_rate, trimmed_audio), status

    except Exception as e:
        return None, f"❌ Error trimming silence: {str(e)}"


def create_audio_effects_tab():
    """Create the audio effects tab interface"""

    gr.Markdown("Apply various audio effects and processing to your audio files.")

    with gr.Row():
        with gr.Column(scale=2):
            # File upload
            audio_input = gr.Audio(
                label="πŸ“€ Upload Audio File",
                type="filepath"
            )

            # Audio info
            duration_info = gr.Markdown("No file uploaded")
            stats_info = gr.Markdown("Audio stats: N/A")

            # Effects sections
            with gr.Accordion("πŸ”Š Volume & Normalization", open=True):
                with gr.Row():
                    normalize_btn = gr.Button("πŸ“ Normalize Audio", variant="secondary")
                    target_level = gr.Slider(
                        minimum=-20,
                        maximum=0,
                        value=-3,
                        step=0.1,
                        label="Target Level (dB)"
                    )

                with gr.Row():
                    volume_btn = gr.Button("πŸ”Š Adjust Volume", variant="secondary")
                    gain_db = gr.Slider(
                        minimum=-20,
                        maximum=20,
                        value=0,
                        step=0.1,
                        label="Volume Gain (dB)"
                    )

            with gr.Accordion("🎭 Fade Effects", open=True):
                with gr.Row():
                    fade_btn = gr.Button("πŸ“ˆ Apply Fades", variant="secondary")
                    fade_in_ms = gr.Slider(
                        minimum=0,
                        maximum=5000,
                        value=100,
                        step=10,
                        label="Fade In (ms)"
                    )
                    fade_out_ms = gr.Slider(
                        minimum=0,
                        maximum=5000,
                        value=100,
                        step=10,
                        label="Fade Out (ms)"
                    )

            with gr.Accordion("⚑ Time & Speed Effects", open=True):
                with gr.Row():
                    reverse_btn = gr.Button("↩️ Reverse Audio", variant="secondary")
                    speed_btn = gr.Button("⏩ Change Speed", variant="secondary")
                    speed_factor = gr.Slider(
                        minimum=0.25,
                        maximum=4.0,
                        value=1.0,
                        step=0.1,
                        label="Speed Factor"
                    )

            with gr.Accordion("βœ‚οΈ Audio Cleanup", open=True):
                with gr.Row():
                    trim_btn = gr.Button("πŸ”‡ Trim Silence", variant="secondary")
                    threshold_db = gr.Slider(
                        minimum=-60,
                        maximum=-10,
                        value=-40,
                        step=1,
                        label="Silence Threshold (dB)"
                    )

            # Status message
            status_msg = gr.Markdown("")

        with gr.Column(scale=1):
            # Output audio
            audio_output = gr.Audio(
                label="🎧 Processed Audio Result",
                type="numpy"
            )

            # Download info
            gr.Markdown("πŸ’Ύ **Download:** Right-click the audio player above and select 'Save audio as...'")

    # Event handlers
    audio_input.change(
        fn=update_audio_info,
        inputs=[audio_input],
        outputs=[duration_info, stats_info]
    )

    # Normalization
    normalize_btn.click(
        fn=apply_normalization,
        inputs=[audio_input, target_level],
        outputs=[audio_output, status_msg]
    )

    # Volume adjustment
    volume_btn.click(
        fn=apply_volume_adjustment,
        inputs=[audio_input, gain_db],
        outputs=[audio_output, status_msg]
    )

    # Fades
    fade_btn.click(
        fn=apply_fades,
        inputs=[audio_input, fade_in_ms, fade_out_ms],
        outputs=[audio_output, status_msg]
    )

    # Reverse
    reverse_btn.click(
        fn=apply_reverse,
        inputs=[audio_input],
        outputs=[audio_output, status_msg]
    )

    # Speed change
    speed_btn.click(
        fn=apply_speed_adjustment,
        inputs=[audio_input, speed_factor],
        outputs=[audio_output, status_msg]
    )

    # Trim silence
    trim_btn.click(
        fn=apply_silence_trimming,
        inputs=[audio_input, threshold_db],
        outputs=[audio_output, status_msg]
    )

    # Usage tips
    with gr.Accordion("πŸ“‹ Effects Guide", open=False):
        gr.Markdown("""
        **πŸ”Š Volume & Normalization:**
        - **Normalize**: Adjusts peak level to target dB (recommended: -3dB)
        - **Volume Gain**: Increase/decrease volume by specified dB

        **🎭 Fade Effects:**
        - **Fade In**: Gradually increase volume from silence
        - **Fade Out**: Gradually decrease volume to silence

        **⚑ Time & Speed:**
        - **Reverse**: Play audio backwards
        - **Speed**: Change playback speed (1.0 = normal, 2.0 = double, 0.5 = half)

        **βœ‚οΈ Cleanup:**
        - **Trim Silence**: Remove quiet sections from start/end

        **Tips:**
        - Always check audio stats before processing
        - Watch for clipping warnings when increasing volume
        - Use normalization for consistent levels across multiple files
        - Combine effects by processing sequentially
        """)