AudioSegment.silent()

创建一段没有声音的音频片段

from pydub import AudioSegment

ten_second_silence = AudioSegment.silent(duration=10000)

参数：

duration ：持续时间（毫秒）

frame_rate ：频率（默认 11025 (11.025 kHz)）

AudioSegment.from_mono_audiosegments()

将两个单声道合并为一个多声道音频

from pydub import AudioSegment

left_channel = AudioSegment.from_wav("sound1.wav")
right_channel = AudioSegment.from_wav("sound1.wav")

stereo_sound = AudioSegment.from_mono_audiosegments(left_channel, right_channel)

AudioSegment(…).dBFS

取得音频文件音量分贝数

from pydub import AudioSegment
sound = AudioSegment.from_file("sound1.wav")

loudness = sound.dBFS

AudioSegment(…).channels

取得音频文件声道数

from pydub import AudioSegment
sound = AudioSegment.from_file("sound1.wav")

channel_count = sound.channels

AudioSegment(…).sample_width

取得音频文件采样宽度

from pydub import AudioSegment
sound = AudioSegment.from_file("sound1.wav")

bytes_per_sample = sound.sample_width

AudioSegment(…).frame_rate

取得音频文件采样频率

from pydub import AudioSegment
sound = AudioSegment.from_file("sound1.wav")

frames_per_second = sound.frame_rate

AudioSegment(…).frame_width

frame_width=sample_width*channels

from pydub import AudioSegment
sound = AudioSegment.from_file("sound1.wav")

bytes_per_frame = sound.frame_width

AudioSegment(…).rms

获取音频音量大小，该值通常用来计算分贝数（dB= 20×lgX）

from pydub import AudioSegment
sound = AudioSegment.from_file("sound1.wav")

loudness = sound.rms

AudioSegment(…).max

取得音频中的最大振幅

from pydub import AudioSegment
sound = AudioSegment.from_file("sound1.wav")

normalized_sound = sound.apply_gain(-sound.max_dBFS)

AudioSegment(…).duration_seconds

取得音频的持续时间，同 len()

from pydub import AudioSegment
sound = AudioSegment.from_file("sound1.wav")

assert sound.duration_seconds == (len(sound) / 1000.0)

AudioSegment(…).raw_data

取得音频数据

from pydub import AudioSegment
sound = AudioSegment.from_file("sound1.wav")

raw_audio_data = sound.raw_data

AudioSegment(…).frame_count()

取得音频的frame数量

from pydub import AudioSegment
sound = AudioSegment.from_file("sound1.wav")

number_of_frames_in_sound = sound.frame_count()

number_of_frames_in_200ms_of_sound = sound.frame_count(ms=200)

参数：

ms：0~ms 毫秒内的frame数

AudioSegment(…).append()

拼接sound1与sound2，返回一个新的AudioSegment实例

from pydub import AudioSegment
sound1 = AudioSegment.from_file("sound1.wav")
sound2 = AudioSegment.from_file("sound2.wav")

# default 100 ms crossfade
combined = sound1.append(sound2)

# 5000 ms crossfade
combined_with_5_sec_crossfade = sound1.append(sound2, crossfade=5000)

# no crossfade
no_crossfade1 = sound1.append(sound2, crossfade=0)

# no crossfade
no_crossfade2 = sound1 + sound2

参数：

cossfade：交叉渐变间隔

AudioSegment(…).overlay()

把sound2覆盖在sound1上，两个音频文件会叠加，如果sound2较长，则会被截断。

from pydub import AudioSegment
sound1 = AudioSegment.from_file("sound1.wav")
sound2 = AudioSegment.from_file("sound2.wav")

played_togther = sound1.overlay(sound2)

sound2_starts_after_delay = sound1.overlay(sound2, position=5000)

volume_of_sound1_reduced_during_overlay = sound1.overlay(sound2, gain_during_overlay=-8)

sound2_repeats_until_sound1_ends = sound1.overlay(sound2, loop=true)

sound2_plays_twice = sound1.overlay(sound2, times=2)

# assume sound1 is 30 sec long and sound2 is 5 sec long:
sound2_plays_a_lot = sound1.overlay(sound2, times=10000)
len(sound1) == len(sound2_plays_a_lot)

参数：

position：覆盖起始位置（毫秒）

loop：是否循环覆盖（true/false）

times：重复覆盖次数（默认1）

gain_during_overlay：调整被覆盖音频的音量（eg，-6.0）

AudioSegment(…).apply_gain(`gain`)

调整音量大小

from pydub import AudioSegment
sound1 = AudioSegment.from_file("sound1.wav")

# make sound1 louder by 3.5 dB
louder_via_method = sound1.apply_gain(+3.5)
louder_via_operator = sound1 + 3.5

# make sound1 quieter by 5.7 dB
quieter_via_method = sound1.apply_gain(-5.7)
quieter_via_operator = sound1 - 5.7

AudioSegment(…).fade()

淡出

from pydub import AudioSegment
sound1 = AudioSegment.from_file("sound1.wav")

fade_louder_for_3_seconds_in_middle = sound1.fade(to_gain=+6.0, start=7500, duration=3000)

fade_quieter_beteen_2_and_3_seconds = sound1.fade(to_gain=-3.5, start=2000, end=3000)

# easy way is to use the .fade_in() convenience method. note: -120dB is basically silent.
fade_in_the_hard_way = sound1.fade(from_gain=-120.0, start=0, duration=5000)
fade_out_the_hard_way = sound1.fade(to_gain=-120.0, end=0, duration=5000)

参数：

to_gain：淡出结束时音频音量下降到的分贝数

from_gain：设置淡出前的所有音频分贝数

start：淡出的起始位置

end：淡出的结束位置

duration：淡出持续时间

AudioSegment(…).fade_out()

淡出到无声

参数：

duration：淡出持续时间

AudioSegment(…).reverse()

生成一个该音频反向播放的音频

AudioSegment(…).set_sample_width()

生成一个该音频的新副本，同时改变采样宽度，增加该值不会丢失精度，而减少该值会丢失精度

AudioSegment(…).set_frame_rate()

创建一个该音频的副本，同时改变采样率，增加该值不会丢失精度，而减少该值会丢失精度

AudioSegment(…).set_channels()

创建一个该音频的副本，同时改变声道数，单声道到多声道不会降低音频质量，多声道到单声道时，若左右声道不同，则会降低质量

AudioSegment(…).split_to_mono()

把一个多声道音频分解成两个单声道

index[0]为左声道

index[1]为右声道

AudioSegment(…).apply_gain_stereo()

调整多声道音频的左右声道音量

如果单声道音频调用此方法，它将先被转换为多声道

from pydub import AudioSegment
sound1 = AudioSegment.from_file("sound1.wav")

# make left channel 6dB quieter and right channe 2dB louder
stereo_balance_adjusted = sound1.apply_gain_stereo(-6, +2)

AudioSegment(…).pan()

左右声道平衡，按百分比增大一边，减小另一边

from pydub import AudioSegment
sound1 = AudioSegment.from_file("sound1.wav")

# pan the sound 15% to the right
panned_right = sound1.pan(+0.15)

# pan the sound 50% to the left
panned_left = sound1.pan(-0.50)

A

AudioSegment(…).get_array_of_samples()

取得音频文件原始数据samples数组

如果是多声道文件则返回类似 [sample_1_L, sample_1_R, sample_2_L, sample_2_R, …].

from pydub import AudioSegment
sound = AudioSegment.from_file(“sound1.wav”)

samples = sound.get_array_of_samples()

# then modify samples...

new_sound = sound._spawn(samples)

将samples数组转回音频

import array
import numpy as np
from pydub import AudioSegment

sound = AudioSegment.from_file(“sound1.wav”)
samples = sound.get_array_of_samples()

shifted_samples = np.right_shift(samples, 1)

# now you have to convert back to an array.array
shifted_samples_array = array.array(sound.array_type, shifted_samples)

new_sound = sound._spawn(shifted_samples_array)

AudioSegment(…).get_dc_offset()

取得一个channel的直流偏移量，返回值=偏移分贝/最大分贝

很多声音处理工具都是默认声音的平衡位置在中间的，如果偏移了，就会造成效果上的变化。

参数：

channel：1 左声道，2 右声道，单声道音频无此参数

AudioSegment(…).remove_dc_offset()

消除直流偏移。该方法基于audioop。bias()，可能会产生溢出

参数：

channel：1/2/None ，1 左声道，2 右声道，None 所有声道

offset：偏移量百分比， -1.0~1.0

AudioSegment(…).invert_phase()

基于DSP的渲染

产生一个反向信号的副本，来消除反相位波，或者降低噪音

python pydub 用法（2）

AudioSegment.silent()

AudioSegment.from_mono_audiosegments()

AudioSegment(…).dBFS

AudioSegment(…).channels

AudioSegment(…).sample_width

AudioSegment(…).frame_rate

AudioSegment(…).frame_width

AudioSegment(…).rms

AudioSegment(…).max

AudioSegment(…).duration_seconds

AudioSegment(…).raw_data

AudioSegment(…).frame_count()

AudioSegment(…).append()

AudioSegment(…).overlay()

AudioSegment(…).apply_gain(`gain`)

AudioSegment(…).fade()

AudioSegment(…).fade_out()

AudioSegment(…).reverse()

AudioSegment(…).set_sample_width()

AudioSegment(…).set_frame_rate()

AudioSegment(…).set_channels()

AudioSegment(…).split_to_mono()

AudioSegment(…).apply_gain_stereo()

AudioSegment(…).pan()

A

AudioSegment(…).get_dc_offset()

AudioSegment(…).remove_dc_offset()

AudioSegment(…).invert_phase()

猜你喜欢

python pydub 用法 （2）

AudioSegment.silent()

AudioSegment.from_mono_audiosegments()

AudioSegment(…).dBFS

AudioSegment(…).channels

AudioSegment(…).sample_width

AudioSegment(…).frame_rate

AudioSegment(…).frame_width

AudioSegment(…).rms

AudioSegment(…).max

AudioSegment(…).duration_seconds

AudioSegment(…).raw_data

AudioSegment(…).frame_count()

AudioSegment(…).append()

AudioSegment(…).overlay()

AudioSegment(…).apply_gain(gain)

AudioSegment(…).fade()

AudioSegment(…).fade_out()

AudioSegment(…).reverse()

AudioSegment(…).set_sample_width()

AudioSegment(…).set_frame_rate()

AudioSegment(…).set_channels()

AudioSegment(…).split_to_mono()

AudioSegment(…).apply_gain_stereo()

AudioSegment(…).pan()

A

AudioSegment(…).get_dc_offset()

AudioSegment(…).remove_dc_offset()

AudioSegment(…).invert_phase()

猜你喜欢

python pydub 用法（2）

AudioSegment(…).apply_gain(`gain`)