mirror of
https://github.com/linyqh/NarratoAI.git
synced 2025-12-10 18:02:51 +00:00
feat(audio): 增强音量管理和智能音量调整功能
更新AudioVolumeDefaults类，提升原声音量至1.2以平衡TTS音量，并允许最大音量达到2.0。新增智能音量调整功能，自动分析和调整音频轨道音量，确保音量在合理范围内。优化任务处理逻辑，结合用户设置和推荐音量配置，提升音频合成效果和用户体验。
This commit is contained in:
linyq
parent
e7ad308875
commit
04ffda297f
220
app/config/audio_config.py
Normal file
220
app/config/audio_config.py
Normal file
@ -0,0 +1,220 @@
|
||||
#!/usr/bin/env python
|
||||
# -*- coding: UTF-8 -*-
|
||||
|
||||
'''
|
||||
@Project: NarratoAI
|
||||
@File : audio_config
|
||||
@Author : 小林同学
|
||||
@Date : 2025/1/7
|
||||
@Description: 音频配置管理
|
||||
'''
|
||||
|
||||
from typing import Dict, Any
|
||||
from loguru import logger
|
||||
|
||||
|
||||
class AudioConfig:
|
||||
"""音频配置管理类"""
|
||||
|
||||
# 默认音量配置
|
||||
DEFAULT_VOLUMES = {
|
||||
'tts_volume': 0.8, # TTS音量稍微降低
|
||||
'original_volume': 1.3, # 原声音量提高
|
||||
'bgm_volume': 0.3, # 背景音乐保持较低
|
||||
}
|
||||
|
||||
# 音频质量配置
|
||||
AUDIO_QUALITY = {
|
||||
'sample_rate': 44100, # 采样率
|
||||
'channels': 2, # 声道数（立体声）
|
||||
'bitrate': '128k', # 比特率
|
||||
}
|
||||
|
||||
# 音频处理配置
|
||||
PROCESSING_CONFIG = {
|
||||
'enable_smart_volume': True, # 启用智能音量调整
|
||||
'enable_audio_normalization': True, # 启用音频标准化
|
||||
'target_lufs': -20.0, # 目标响度 (LUFS)
|
||||
'max_peak': -1.0, # 最大峰值 (dBFS)
|
||||
'volume_analysis_method': 'lufs', # 音量分析方法: 'lufs' 或 'rms'
|
||||
}
|
||||
|
||||
# 音频混合配置
|
||||
MIXING_CONFIG = {
|
||||
'crossfade_duration': 0.1, # 交叉淡化时长（秒）
|
||||
'bgm_fade_out': 3.0, # BGM淡出时长（秒）
|
||||
'dynamic_range_compression': False, # 动态范围压缩
|
||||
}
|
||||
|
||||
@classmethod
|
||||
def get_optimized_volumes(cls, video_type: str = 'default') -> Dict[str, float]:
|
||||
"""
|
||||
根据视频类型获取优化的音量配置
|
||||
|
||||
Args:
|
||||
video_type: 视频类型 ('default', 'educational', 'entertainment', 'news')
|
||||
|
||||
Returns:
|
||||
Dict[str, float]: 音量配置字典
|
||||
"""
|
||||
base_volumes = cls.DEFAULT_VOLUMES.copy()
|
||||
|
||||
# 根据视频类型调整音量
|
||||
if video_type == 'educational':
|
||||
# 教育类视频：突出解说，降低原声
|
||||
base_volumes.update({
|
||||
'tts_volume': 0.9,
|
||||
'original_volume': 0.8,
|
||||
'bgm_volume': 0.2,
|
||||
})
|
||||
elif video_type == 'entertainment':
|
||||
# 娱乐类视频：平衡解说和原声
|
||||
base_volumes.update({
|
||||
'tts_volume': 0.8,
|
||||
'original_volume': 1.2,
|
||||
'bgm_volume': 0.4,
|
||||
})
|
||||
elif video_type == 'news':
|
||||
# 新闻类视频：突出解说，最小化背景音
|
||||
base_volumes.update({
|
||||
'tts_volume': 1.0,
|
||||
'original_volume': 0.6,
|
||||
'bgm_volume': 0.1,
|
||||
})
|
||||
|
||||
logger.info(f"使用 {video_type} 类型的音量配置: {base_volumes}")
|
||||
return base_volumes
|
||||
|
||||
@classmethod
|
||||
def get_audio_processing_config(cls) -> Dict[str, Any]:
|
||||
"""获取音频处理配置"""
|
||||
return cls.PROCESSING_CONFIG.copy()
|
||||
|
||||
@classmethod
|
||||
def get_mixing_config(cls) -> Dict[str, Any]:
|
||||
"""获取音频混合配置"""
|
||||
return cls.MIXING_CONFIG.copy()
|
||||
|
||||
@classmethod
|
||||
def validate_volume(cls, volume: float, name: str) -> float:
|
||||
"""
|
||||
验证和限制音量值
|
||||
|
||||
Args:
|
||||
volume: 音量值
|
||||
name: 音量名称（用于日志）
|
||||
|
||||
Returns:
|
||||
float: 验证后的音量值
|
||||
"""
|
||||
min_volume = 0.0
|
||||
max_volume = 2.0 # 允许原声超过1.0
|
||||
|
||||
if volume < min_volume:
|
||||
logger.warning(f"{name}音量 {volume} 低于最小值 {min_volume}，已调整")
|
||||
return min_volume
|
||||
elif volume > max_volume:
|
||||
logger.warning(f"{name}音量 {volume} 超过最大值 {max_volume}，已调整")
|
||||
return max_volume
|
||||
|
||||
return volume
|
||||
|
||||
@classmethod
|
||||
def apply_volume_profile(cls, profile_name: str) -> Dict[str, float]:
|
||||
"""
|
||||
应用预设的音量配置文件
|
||||
|
||||
Args:
|
||||
profile_name: 配置文件名称
|
||||
|
||||
Returns:
|
||||
Dict[str, float]: 音量配置
|
||||
"""
|
||||
profiles = {
|
||||
'balanced': {
|
||||
'tts_volume': 0.8,
|
||||
'original_volume': 1.2,
|
||||
'bgm_volume': 0.3,
|
||||
},
|
||||
'voice_focused': {
|
||||
'tts_volume': 1.0,
|
||||
'original_volume': 0.7,
|
||||
'bgm_volume': 0.2,
|
||||
},
|
||||
'original_focused': {
|
||||
'tts_volume': 0.7,
|
||||
'original_volume': 1.5,
|
||||
'bgm_volume': 0.2,
|
||||
},
|
||||
'quiet_background': {
|
||||
'tts_volume': 0.8,
|
||||
'original_volume': 1.3,
|
||||
'bgm_volume': 0.1,
|
||||
}
|
||||
}
|
||||
|
||||
if profile_name in profiles:
|
||||
logger.info(f"应用音量配置文件: {profile_name}")
|
||||
return profiles[profile_name]
|
||||
else:
|
||||
logger.warning(f"未找到配置文件 {profile_name}，使用默认配置")
|
||||
return cls.DEFAULT_VOLUMES.copy()
|
||||
|
||||
|
||||
# 全局音频配置实例
|
||||
audio_config = AudioConfig()
|
||||
|
||||
|
||||
def get_recommended_volumes_for_content(content_type: str = 'mixed') -> Dict[str, float]:
|
||||
"""
|
||||
根据内容类型推荐音量设置
|
||||
|
||||
Args:
|
||||
content_type: 内容类型
|
||||
- 'mixed': 混合内容（默认）
|
||||
- 'voice_only': 纯解说
|
||||
- 'original_heavy': 原声为主
|
||||
- 'music_video': 音乐视频
|
||||
|
||||
Returns:
|
||||
Dict[str, float]: 推荐的音量配置
|
||||
"""
|
||||
recommendations = {
|
||||
'mixed': {
|
||||
'tts_volume': 0.8,
|
||||
'original_volume': 1.3,
|
||||
'bgm_volume': 0.3,
|
||||
},
|
||||
'voice_only': {
|
||||
'tts_volume': 1.0,
|
||||
'original_volume': 0.5,
|
||||
'bgm_volume': 0.2,
|
||||
},
|
||||
'original_heavy': {
|
||||
'tts_volume': 0.6,
|
||||
'original_volume': 1.6,
|
||||
'bgm_volume': 0.1,
|
||||
},
|
||||
'music_video': {
|
||||
'tts_volume': 0.7,
|
||||
'original_volume': 1.8,
|
||||
'bgm_volume': 0.0, # 不添加额外BGM
|
||||
}
|
||||
}
|
||||
|
||||
return recommendations.get(content_type, recommendations['mixed'])
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
# 测试配置
|
||||
config = AudioConfig()
|
||||
|
||||
# 测试不同类型的音量配置
|
||||
for video_type in ['default', 'educational', 'entertainment', 'news']:
|
||||
volumes = config.get_optimized_volumes(video_type)
|
||||
print(f"{video_type}: {volumes}")
|
||||
|
||||
# 测试配置文件
|
||||
for profile in ['balanced', 'voice_focused', 'original_focused']:
|
||||
volumes = config.apply_volume_profile(profile)
|
||||
print(f"{profile}: {volumes}")
|
||||
@ -20,15 +20,18 @@ class AudioVolumeDefaults:
|
||||
VOICE_VOLUME = 1.0
|
||||
TTS_VOLUME = 1.0
|
||||
|
||||
# 原声音量默认值 - 这是修复bug的关键
|
||||
ORIGINAL_VOLUME = 0.7
|
||||
# 原声音量默认值 - 提高原声音量以平衡TTS
|
||||
ORIGINAL_VOLUME = 1.2
|
||||
|
||||
# 背景音乐音量默认值
|
||||
BGM_VOLUME = 0.3
|
||||
|
||||
# 音量范围
|
||||
MIN_VOLUME = 0.0
|
||||
MAX_VOLUME = 1.0
|
||||
MAX_VOLUME = 2.0 # 允许原声音量超过1.0以平衡TTS
|
||||
|
||||
# 智能音量调整
|
||||
ENABLE_SMART_VOLUME = True # 是否启用智能音量分析和调整
|
||||
|
||||
|
||||
class VideoConcatMode(str, Enum):
|
||||
|
||||
314
app/services/audio_normalizer.py
Normal file
314
app/services/audio_normalizer.py
Normal file
@ -0,0 +1,314 @@
|
||||
#!/usr/bin/env python
|
||||
# -*- coding: UTF-8 -*-
|
||||
|
||||
'''
|
||||
@Project: NarratoAI
|
||||
@File : audio_normalizer
|
||||
@Author : 小林同学
|
||||
@Date : 2025/1/7
|
||||
@Description: 音频响度分析和标准化工具
|
||||
'''
|
||||
|
||||
import os
|
||||
import subprocess
|
||||
import tempfile
|
||||
from typing import Optional, Tuple, Dict, Any
|
||||
from loguru import logger
|
||||
from moviepy import AudioFileClip
|
||||
from pydub import AudioSegment
|
||||
import numpy as np
|
||||
|
||||
|
||||
class AudioNormalizer:
|
||||
"""音频响度分析和标准化工具"""
|
||||
|
||||
def __init__(self):
|
||||
self.target_lufs = -23.0 # 目标响度 (LUFS)，符合广播标准
|
||||
self.max_peak = -1.0 # 最大峰值 (dBFS)
|
||||
|
||||
def analyze_audio_lufs(self, audio_path: str) -> Optional[float]:
|
||||
"""
|
||||
使用FFmpeg分析音频的LUFS响度
|
||||
|
||||
Args:
|
||||
audio_path: 音频文件路径
|
||||
|
||||
Returns:
|
||||
float: LUFS值，如果分析失败返回None
|
||||
"""
|
||||
if not os.path.exists(audio_path):
|
||||
logger.error(f"音频文件不存在: {audio_path}")
|
||||
return None
|
||||
|
||||
try:
|
||||
# 使用FFmpeg的loudnorm滤镜分析音频响度
|
||||
cmd = [
|
||||
'ffmpeg', '-hide_banner', '-nostats',
|
||||
'-i', audio_path,
|
||||
'-af', 'loudnorm=I=-23:TP=-1:LRA=7:print_format=json',
|
||||
'-f', 'null', '-'
|
||||
]
|
||||
|
||||
result = subprocess.run(
|
||||
cmd,
|
||||
capture_output=True,
|
||||
text=True,
|
||||
check=False
|
||||
)
|
||||
|
||||
# 从stderr中提取JSON信息
|
||||
stderr_lines = result.stderr.split('\n')
|
||||
json_start = False
|
||||
json_lines = []
|
||||
|
||||
for line in stderr_lines:
|
||||
if line.strip() == '{':
|
||||
json_start = True
|
||||
if json_start:
|
||||
json_lines.append(line)
|
||||
if line.strip() == '}':
|
||||
break
|
||||
|
||||
if json_lines:
|
||||
import json
|
||||
try:
|
||||
loudness_data = json.loads('\n'.join(json_lines))
|
||||
input_i = float(loudness_data.get('input_i', 0))
|
||||
logger.info(f"音频 {os.path.basename(audio_path)} 的LUFS: {input_i}")
|
||||
return input_i
|
||||
except (json.JSONDecodeError, ValueError) as e:
|
||||
logger.warning(f"解析LUFS数据失败: {e}")
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"分析音频LUFS失败: {e}")
|
||||
|
||||
return None
|
||||
|
||||
def get_audio_rms(self, audio_path: str) -> Optional[float]:
|
||||
"""
|
||||
计算音频的RMS值作为响度的简单估计
|
||||
|
||||
Args:
|
||||
audio_path: 音频文件路径
|
||||
|
||||
Returns:
|
||||
float: RMS值 (dB)，如果计算失败返回None
|
||||
"""
|
||||
try:
|
||||
audio = AudioSegment.from_file(audio_path)
|
||||
# 转换为numpy数组
|
||||
samples = np.array(audio.get_array_of_samples())
|
||||
|
||||
# 如果是立体声，取平均值
|
||||
if audio.channels == 2:
|
||||
samples = samples.reshape((-1, 2))
|
||||
samples = samples.mean(axis=1)
|
||||
|
||||
# 计算RMS
|
||||
rms = np.sqrt(np.mean(samples**2))
|
||||
|
||||
# 转换为dB
|
||||
if rms > 0:
|
||||
rms_db = 20 * np.log10(rms / (2**15)) # 假设16位音频
|
||||
logger.info(f"音频 {os.path.basename(audio_path)} 的RMS: {rms_db:.2f} dB")
|
||||
return rms_db
|
||||
else:
|
||||
return -60.0 # 静音
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"计算音频RMS失败: {e}")
|
||||
return None
|
||||
|
||||
def normalize_audio_lufs(self, input_path: str, output_path: str,
|
||||
target_lufs: Optional[float] = None) -> bool:
|
||||
"""
|
||||
使用FFmpeg的loudnorm滤镜标准化音频响度
|
||||
|
||||
Args:
|
||||
input_path: 输入音频文件路径
|
||||
output_path: 输出音频文件路径
|
||||
target_lufs: 目标LUFS值，默认使用-23.0
|
||||
|
||||
Returns:
|
||||
bool: 是否成功
|
||||
"""
|
||||
if target_lufs is None:
|
||||
target_lufs = self.target_lufs
|
||||
|
||||
try:
|
||||
# 第一遍：分析音频
|
||||
analyze_cmd = [
|
||||
'ffmpeg', '-hide_banner', '-nostats',
|
||||
'-i', input_path,
|
||||
'-af', f'loudnorm=I={target_lufs}:TP={self.max_peak}:LRA=7:print_format=json',
|
||||
'-f', 'null', '-'
|
||||
]
|
||||
|
||||
analyze_result = subprocess.run(
|
||||
analyze_cmd,
|
||||
capture_output=True,
|
||||
text=True,
|
||||
check=False
|
||||
)
|
||||
|
||||
# 解析分析结果
|
||||
stderr_lines = analyze_result.stderr.split('\n')
|
||||
json_start = False
|
||||
json_lines = []
|
||||
|
||||
for line in stderr_lines:
|
||||
if line.strip() == '{':
|
||||
json_start = True
|
||||
if json_start:
|
||||
json_lines.append(line)
|
||||
if line.strip() == '}':
|
||||
break
|
||||
|
||||
if not json_lines:
|
||||
logger.warning("无法获取音频分析数据，使用简单标准化")
|
||||
return self._simple_normalize(input_path, output_path)
|
||||
|
||||
import json
|
||||
loudness_data = json.loads('\n'.join(json_lines))
|
||||
|
||||
# 第二遍：应用标准化
|
||||
normalize_cmd = [
|
||||
'ffmpeg', '-y', '-hide_banner',
|
||||
'-i', input_path,
|
||||
'-af', (
|
||||
f'loudnorm=I={target_lufs}:TP={self.max_peak}:LRA=7:'
|
||||
f'measured_I={loudness_data["input_i"]}:'
|
||||
f'measured_LRA={loudness_data["input_lra"]}:'
|
||||
f'measured_TP={loudness_data["input_tp"]}:'
|
||||
f'measured_thresh={loudness_data["input_thresh"]}'
|
||||
),
|
||||
'-ar', '44100', # 统一采样率
|
||||
'-ac', '2', # 统一为立体声
|
||||
output_path
|
||||
]
|
||||
|
||||
result = subprocess.run(
|
||||
normalize_cmd,
|
||||
capture_output=True,
|
||||
text=True,
|
||||
check=True
|
||||
)
|
||||
|
||||
logger.info(f"音频标准化完成: {output_path}")
|
||||
return True
|
||||
|
||||
except subprocess.CalledProcessError as e:
|
||||
logger.error(f"FFmpeg标准化失败: {e}")
|
||||
return self._simple_normalize(input_path, output_path)
|
||||
except Exception as e:
|
||||
logger.error(f"音频标准化失败: {e}")
|
||||
return False
|
||||
|
||||
def _simple_normalize(self, input_path: str, output_path: str) -> bool:
|
||||
"""
|
||||
简单的音频标准化（备用方案）
|
||||
|
||||
Args:
|
||||
input_path: 输入音频文件路径
|
||||
output_path: 输出音频文件路径
|
||||
|
||||
Returns:
|
||||
bool: 是否成功
|
||||
"""
|
||||
try:
|
||||
# 使用pydub进行简单的音量标准化
|
||||
audio = AudioSegment.from_file(input_path)
|
||||
|
||||
# 标准化到-20dB
|
||||
target_dBFS = -20.0
|
||||
change_in_dBFS = target_dBFS - audio.dBFS
|
||||
normalized_audio = audio.apply_gain(change_in_dBFS)
|
||||
|
||||
# 导出
|
||||
normalized_audio.export(output_path, format="mp3", bitrate="128k")
|
||||
logger.info(f"简单音频标准化完成: {output_path}")
|
||||
return True
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"简单音频标准化失败: {e}")
|
||||
return False
|
||||
|
||||
def calculate_volume_adjustment(self, tts_path: str, original_path: str) -> Tuple[float, float]:
|
||||
"""
|
||||
计算TTS和原声的音量调整系数，使它们达到相似的响度
|
||||
|
||||
Args:
|
||||
tts_path: TTS音频文件路径
|
||||
original_path: 原声音频文件路径
|
||||
|
||||
Returns:
|
||||
Tuple[float, float]: (TTS音量系数, 原声音量系数)
|
||||
"""
|
||||
# 分析两个音频的响度
|
||||
tts_lufs = self.analyze_audio_lufs(tts_path)
|
||||
original_lufs = self.analyze_audio_lufs(original_path)
|
||||
|
||||
# 如果LUFS分析失败，使用RMS作为备用
|
||||
if tts_lufs is None:
|
||||
tts_lufs = self.get_audio_rms(tts_path)
|
||||
if original_lufs is None:
|
||||
original_lufs = self.get_audio_rms(original_path)
|
||||
|
||||
if tts_lufs is None or original_lufs is None:
|
||||
logger.warning("无法分析音频响度，使用默认音量设置")
|
||||
return 0.7, 1.0 # 默认设置
|
||||
|
||||
# 计算调整系数
|
||||
# 目标：让两个音频达到相似的响度
|
||||
target_lufs = -20.0 # 目标响度
|
||||
|
||||
tts_adjustment = 10 ** ((target_lufs - tts_lufs) / 20)
|
||||
original_adjustment = 10 ** ((target_lufs - original_lufs) / 20)
|
||||
|
||||
# 限制调整范围，避免过度放大
|
||||
tts_adjustment = max(0.1, min(2.0, tts_adjustment))
|
||||
original_adjustment = max(0.1, min(3.0, original_adjustment)) # 原声可以放大更多
|
||||
|
||||
logger.info(f"音量调整建议 - TTS: {tts_adjustment:.2f}, 原声: {original_adjustment:.2f}")
|
||||
return tts_adjustment, original_adjustment
|
||||
|
||||
|
||||
def normalize_audio_for_mixing(audio_path: str, output_dir: str,
|
||||
target_lufs: float = -20.0) -> Optional[str]:
|
||||
"""
|
||||
为音频混合准备标准化的音频文件
|
||||
|
||||
Args:
|
||||
audio_path: 输入音频文件路径
|
||||
output_dir: 输出目录
|
||||
target_lufs: 目标LUFS值
|
||||
|
||||
Returns:
|
||||
str: 标准化后的音频文件路径，失败返回None
|
||||
"""
|
||||
if not os.path.exists(audio_path):
|
||||
return None
|
||||
|
||||
normalizer = AudioNormalizer()
|
||||
|
||||
# 生成输出文件名
|
||||
base_name = os.path.splitext(os.path.basename(audio_path))[0]
|
||||
output_path = os.path.join(output_dir, f"{base_name}_normalized.mp3")
|
||||
|
||||
# 执行标准化
|
||||
if normalizer.normalize_audio_lufs(audio_path, output_path, target_lufs):
|
||||
return output_path
|
||||
else:
|
||||
return None
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
# 测试代码
|
||||
normalizer = AudioNormalizer()
|
||||
|
||||
# 测试音频分析
|
||||
test_audio = "/path/to/test/audio.mp3"
|
||||
if os.path.exists(test_audio):
|
||||
lufs = normalizer.analyze_audio_lufs(test_audio)
|
||||
rms = normalizer.get_audio_rms(test_audio)
|
||||
print(f"LUFS: {lufs}, RMS: {rms}")
|
||||
@ -10,6 +10,7 @@
|
||||
|
||||
import os
|
||||
import traceback
|
||||
import tempfile
|
||||
from typing import Optional, Dict, Any
|
||||
from loguru import logger
|
||||
from moviepy import (
|
||||
@ -25,6 +26,7 @@ from PIL import ImageFont
|
||||
|
||||
from app.utils import utils
|
||||
from app.models.schema import AudioVolumeDefaults
|
||||
from app.services.audio_normalizer import AudioNormalizer, normalize_audio_for_mixing
|
||||
|
||||
|
||||
def merge_materials(
|
||||
@ -153,6 +155,41 @@ def merge_materials(
|
||||
# 处理背景音乐和所有音频轨道合成
|
||||
audio_tracks = []
|
||||
|
||||
# 智能音量调整（可选功能）
|
||||
if AudioVolumeDefaults.ENABLE_SMART_VOLUME and audio_path and os.path.exists(audio_path) and original_audio is not None:
|
||||
try:
|
||||
normalizer = AudioNormalizer()
|
||||
temp_dir = tempfile.mkdtemp()
|
||||
temp_original_path = os.path.join(temp_dir, "temp_original.wav")
|
||||
|
||||
# 保存原声到临时文件进行分析
|
||||
original_audio.write_audiofile(temp_original_path, verbose=False, logger=None)
|
||||
|
||||
# 计算智能音量调整
|
||||
tts_adjustment, original_adjustment = normalizer.calculate_volume_adjustment(
|
||||
audio_path, temp_original_path
|
||||
)
|
||||
|
||||
# 应用智能调整，但保留用户设置的相对比例
|
||||
smart_voice_volume = voice_volume * tts_adjustment
|
||||
smart_original_volume = original_audio_volume * original_adjustment
|
||||
|
||||
# 限制音量范围，避免过度调整
|
||||
smart_voice_volume = max(0.1, min(1.5, smart_voice_volume))
|
||||
smart_original_volume = max(0.1, min(2.0, smart_original_volume))
|
||||
|
||||
voice_volume = smart_voice_volume
|
||||
original_audio_volume = smart_original_volume
|
||||
|
||||
logger.info(f"智能音量调整 - TTS: {voice_volume:.2f}, 原声: {original_audio_volume:.2f}")
|
||||
|
||||
# 清理临时文件
|
||||
import shutil
|
||||
shutil.rmtree(temp_dir)
|
||||
|
||||
except Exception as e:
|
||||
logger.warning(f"智能音量分析失败，使用原始设置: {e}")
|
||||
|
||||
# 先添加主音频（配音）
|
||||
if audio_path and os.path.exists(audio_path):
|
||||
try:
|
||||
@ -164,8 +201,14 @@ def merge_materials(
|
||||
|
||||
# 添加原声（如果需要）
|
||||
if original_audio is not None:
|
||||
audio_tracks.append(original_audio)
|
||||
logger.info(f"已添加视频原声，音量: {original_audio_volume}")
|
||||
# 重新应用调整后的音量（因为original_audio已经应用了一次音量）
|
||||
# 计算需要的额外调整
|
||||
current_volume_in_original = 1.0 # original_audio中已应用的音量
|
||||
additional_adjustment = original_audio_volume / current_volume_in_original
|
||||
|
||||
adjusted_original_audio = original_audio.with_effects([afx.MultiplyVolume(additional_adjustment)])
|
||||
audio_tracks.append(adjusted_original_audio)
|
||||
logger.info(f"已添加视频原声，最终音量: {original_audio_volume}")
|
||||
|
||||
# 添加背景音乐（如果有）
|
||||
if bgm_path and os.path.exists(bgm_path):
|
||||
|
||||
@ -7,157 +7,14 @@ from os import path
|
||||
from loguru import logger
|
||||
|
||||
from app.config import config
|
||||
from app.config.audio_config import AudioConfig, get_recommended_volumes_for_content
|
||||
from app.models import const
|
||||
from app.models.schema import VideoConcatMode, VideoParams, VideoClipParams
|
||||
from app.services import (llm, material, subtitle, video, voice, audio_merger,
|
||||
subtitle_merger, clip_video, merger_video, update_script, generate_video)
|
||||
from app.models.schema import VideoClipParams
|
||||
from app.services import (voice, audio_merger, subtitle_merger, clip_video, merger_video, update_script, generate_video)
|
||||
from app.services import state as sm
|
||||
from app.utils import utils
|
||||
|
||||
|
||||
# def generate_script(task_id, params):
|
||||
# logger.info("\n\n## generating video script")
|
||||
# video_script = params.video_script.strip()
|
||||
# if not video_script:
|
||||
# video_script = llm.generate_script(
|
||||
# video_subject=params.video_subject,
|
||||
# language=params.video_language,
|
||||
# paragraph_number=params.paragraph_number,
|
||||
# )
|
||||
# else:
|
||||
# logger.debug(f"video script: \n{video_script}")
|
||||
|
||||
# if not video_script:
|
||||
# sm.state.update_task(task_id, state=const.TASK_STATE_FAILED)
|
||||
# logger.error("failed to generate video script.")
|
||||
# return None
|
||||
|
||||
# return video_script
|
||||
|
||||
|
||||
# def generate_terms(task_id, params, video_script):
|
||||
# logger.info("\n\n## generating video terms")
|
||||
# video_terms = params.video_terms
|
||||
# if not video_terms:
|
||||
# video_terms = llm.generate_terms(
|
||||
# video_subject=params.video_subject, video_script=video_script, amount=5
|
||||
# )
|
||||
# else:
|
||||
# if isinstance(video_terms, str):
|
||||
# video_terms = [term.strip() for term in re.split(r"[,，]", video_terms)]
|
||||
# elif isinstance(video_terms, list):
|
||||
# video_terms = [term.strip() for term in video_terms]
|
||||
# else:
|
||||
# raise ValueError("video_terms must be a string or a list of strings.")
|
||||
|
||||
# logger.debug(f"video terms: {utils.to_json(video_terms)}")
|
||||
|
||||
# if not video_terms:
|
||||
# sm.state.update_task(task_id, state=const.TASK_STATE_FAILED)
|
||||
# logger.error("failed to generate video terms.")
|
||||
# return None
|
||||
|
||||
# return video_terms
|
||||
|
||||
|
||||
# def save_script_data(task_id, video_script, video_terms, params):
|
||||
# script_file = path.join(utils.task_dir(task_id), "script.json")
|
||||
# script_data = {
|
||||
# "script": video_script,
|
||||
# "search_terms": video_terms,
|
||||
# "params": params,
|
||||
# }
|
||||
|
||||
# with open(script_file, "w", encoding="utf-8") as f:
|
||||
# f.write(utils.to_json(script_data))
|
||||
|
||||
|
||||
# def generate_audio(task_id, params, video_script):
|
||||
# logger.info("\n\n## generating audio")
|
||||
# audio_file = path.join(utils.task_dir(task_id), "audio.mp3")
|
||||
# sub_maker = voice.tts(
|
||||
# text=video_script,
|
||||
# voice_name=voice.parse_voice_name(params.voice_name),
|
||||
# voice_rate=params.voice_rate,
|
||||
# voice_file=audio_file,
|
||||
# )
|
||||
# if sub_maker is None:
|
||||
# sm.state.update_task(task_id, state=const.TASK_STATE_FAILED)
|
||||
# logger.error(
|
||||
# """failed to generate audio:
|
||||
# 1. check if the language of the voice matches the language of the video script.
|
||||
# 2. check if the network is available. If you are in China, it is recommended to use a VPN and enable the global traffic mode.
|
||||
# """.strip()
|
||||
# )
|
||||
# return None, None, None
|
||||
|
||||
# audio_duration = math.ceil(voice.get_audio_duration(sub_maker))
|
||||
# return audio_file, audio_duration, sub_maker
|
||||
|
||||
|
||||
# def generate_subtitle(task_id, params, video_script, sub_maker, audio_file):
|
||||
# if not params.subtitle_enabled:
|
||||
# return ""
|
||||
|
||||
# subtitle_path = path.join(utils.task_dir(task_id), "subtitle111.srt")
|
||||
# subtitle_provider = config.app.get("subtitle_provider", "").strip().lower()
|
||||
# logger.info(f"\n\n## generating subtitle, provider: {subtitle_provider}")
|
||||
|
||||
# subtitle_fallback = False
|
||||
# if subtitle_provider == "edge":
|
||||
# voice.create_subtitle(
|
||||
# text=video_script, sub_maker=sub_maker, subtitle_file=subtitle_path
|
||||
# )
|
||||
# if not os.path.exists(subtitle_path):
|
||||
# subtitle_fallback = True
|
||||
# logger.warning("subtitle file not found, fallback to whisper")
|
||||
|
||||
# if subtitle_provider == "whisper" or subtitle_fallback:
|
||||
# subtitle.create(audio_file=audio_file, subtitle_file=subtitle_path)
|
||||
# logger.info("\n\n## correcting subtitle")
|
||||
# subtitle.correct(subtitle_file=subtitle_path, video_script=video_script)
|
||||
|
||||
# subtitle_lines = subtitle.file_to_subtitles(subtitle_path)
|
||||
# if not subtitle_lines:
|
||||
# logger.warning(f"subtitle file is invalid: {subtitle_path}")
|
||||
# return ""
|
||||
|
||||
# return subtitle_path
|
||||
|
||||
|
||||
# def get_video_materials(task_id, params, video_terms, audio_duration):
|
||||
# if params.video_source == "local":
|
||||
# logger.info("\n\n## preprocess local materials")
|
||||
# materials = video.preprocess_video(
|
||||
# materials=params.video_materials, clip_duration=params.video_clip_duration
|
||||
# )
|
||||
# if not materials:
|
||||
# sm.state.update_task(task_id, state=const.TASK_STATE_FAILED)
|
||||
# logger.error(
|
||||
# "no valid materials found, please check the materials and try again."
|
||||
# )
|
||||
# return None
|
||||
# return [material_info.url for material_info in materials]
|
||||
# else:
|
||||
# logger.info(f"\n\n## downloading videos from {params.video_source}")
|
||||
# downloaded_videos = material.download_videos(
|
||||
# task_id=task_id,
|
||||
# search_terms=video_terms,
|
||||
# source=params.video_source,
|
||||
# video_aspect=params.video_aspect,
|
||||
# video_contact_mode=params.video_concat_mode,
|
||||
# audio_duration=audio_duration * params.video_count,
|
||||
# max_clip_duration=params.video_clip_duration,
|
||||
# )
|
||||
# if not downloaded_videos:
|
||||
# sm.state.update_task(task_id, state=const.TASK_STATE_FAILED)
|
||||
# logger.error(
|
||||
# "failed to download videos, maybe the network is not available. if you are in China, please use a VPN."
|
||||
# )
|
||||
# return None
|
||||
# return downloaded_videos
|
||||
|
||||
|
||||
def start_subclip(task_id: str, params: VideoClipParams, subclip_path_videos: dict):
|
||||
"""
|
||||
后台任务（自动剪辑视频进行剪辑）
|
||||
@ -171,12 +28,6 @@ def start_subclip(task_id: str, params: VideoClipParams, subclip_path_videos: di
|
||||
logger.info(f"\n\n## 开始任务: {task_id}")
|
||||
sm.state.update_task(task_id, state=const.TASK_STATE_PROCESSING, progress=0)
|
||||
|
||||
# # 初始化 ImageMagick
|
||||
# if not utils.init_imagemagick():
|
||||
# logger.warning("ImageMagick 初始化失败，字幕可能无法正常显示")
|
||||
|
||||
# # tts 角色名称
|
||||
# voice_name = voice.parse_voice_name(params.voice_name)
|
||||
"""
|
||||
1. 加载剪辑脚本
|
||||
"""
|
||||
@ -309,11 +160,22 @@ def start_subclip(task_id: str, params: VideoClipParams, subclip_path_videos: di
|
||||
# bgm_path = '/Users/apple/Desktop/home/NarratoAI/resource/songs/bgm.mp3'
|
||||
bgm_path = utils.get_bgm_file()
|
||||
|
||||
# 获取优化的音量配置
|
||||
optimized_volumes = get_recommended_volumes_for_content('mixed')
|
||||
|
||||
# 应用用户设置和优化建议的组合
|
||||
# 如果用户设置了非默认值，优先使用用户设置
|
||||
final_tts_volume = params.tts_volume if hasattr(params, 'tts_volume') and params.tts_volume != 1.0 else optimized_volumes['tts_volume']
|
||||
final_original_volume = params.original_volume if hasattr(params, 'original_volume') and params.original_volume != 0.7 else optimized_volumes['original_volume']
|
||||
final_bgm_volume = params.bgm_volume if hasattr(params, 'bgm_volume') and params.bgm_volume != 0.3 else optimized_volumes['bgm_volume']
|
||||
|
||||
logger.info(f"音量配置 - TTS: {final_tts_volume}, 原声: {final_original_volume}, BGM: {final_bgm_volume}")
|
||||
|
||||
# 调用示例
|
||||
options = {
|
||||
'voice_volume': params.tts_volume, # 配音音量
|
||||
'bgm_volume': params.bgm_volume, # 背景音乐音量
|
||||
'original_audio_volume': params.original_volume, # 视频原声音量，0表示不保留
|
||||
'voice_volume': final_tts_volume, # 配音音量（优化后）
|
||||
'bgm_volume': final_bgm_volume, # 背景音乐音量（优化后）
|
||||
'original_audio_volume': final_original_volume, # 视频原声音量（优化后）
|
||||
'keep_original_audio': True, # 是否保留原声
|
||||
'subtitle_enabled': params.subtitle_enabled, # 是否启用字幕 - 修复字幕开关bug
|
||||
'subtitle_font': params.font_name, # 这里使用相对字体路径，会自动在 font_dir() 目录下查找
|
||||
|
||||
174
docs/AUDIO_OPTIMIZATION_SUMMARY.md
Normal file
174
docs/AUDIO_OPTIMIZATION_SUMMARY.md
Normal file
@ -0,0 +1,174 @@
|
||||
# 音频音量平衡优化 - 完成总结
|
||||
|
||||
## 问题解决
|
||||
|
||||
✅ **已解决**：视频原声音量比TTS解说音量小的问题
|
||||
|
||||
### 原始问题
|
||||
- 即使设置视频原声为1.0，解说音量为0.7，原声依然比解说小很多
|
||||
- 用户体验差，需要手动调整音量才能听清原声
|
||||
|
||||
### 根本原因
|
||||
1. **音频响度差异**：TTS音频通常具有-24dB LUFS的响度，而视频原声可能只有-33dB LUFS
|
||||
2. **缺乏标准化**：简单的音量乘法器无法解决响度差异问题
|
||||
3. **配置不合理**：默认的原声音量0.7太低
|
||||
|
||||
## 解决方案实施
|
||||
|
||||
### 1. 音频分析工具 ✅
|
||||
- **文件**: `app/services/audio_normalizer.py`
|
||||
- **功能**: LUFS响度分析、RMS计算、音频标准化
|
||||
- **测试结果**:
|
||||
- TTS测试音频: -24.15 LUFS
|
||||
- 原声测试音频: -32.95 LUFS
|
||||
- 智能调整建议: TTS×1.61, 原声×3.00
|
||||
|
||||
### 2. 配置优化 ✅
|
||||
- **文件**: `app/models/schema.py`
|
||||
- **改进**:
|
||||
- 原声默认音量: 0.7 → 1.2
|
||||
- 最大音量限制: 1.0 → 2.0
|
||||
- 新增智能调整开关
|
||||
|
||||
### 3. 智能音量调整 ✅
|
||||
- **文件**: `app/services/generate_video.py`
|
||||
- **功能**: 自动分析音频响度差异，计算合适的调整系数
|
||||
- **特点**: 保留用户设置的相对比例，限制调整范围
|
||||
|
||||
### 4. 配置管理系统 ✅
|
||||
- **文件**: `app/config/audio_config.py`
|
||||
- **功能**:
|
||||
- 不同视频类型的音量配置
|
||||
- 预设配置文件（balanced、voice_focused等）
|
||||
- 内容类型推荐
|
||||
|
||||
### 5. 任务集成 ✅
|
||||
- **文件**: `app/services/task.py`
|
||||
- **改进**: 自动应用优化的音量配置
|
||||
- **兼容性**: 向后兼容现有设置
|
||||
|
||||
## 测试验证
|
||||
|
||||
### 功能测试 ✅
|
||||
```bash
|
||||
python test_audio_optimization.py
|
||||
```
|
||||
- 音频分析功能正常
|
||||
- 配置系统工作正常
|
||||
- 智能调整计算正确
|
||||
|
||||
### 示例演示 ✅
|
||||
```bash
|
||||
python examples/audio_volume_example.py
|
||||
```
|
||||
- 基本配置使用
|
||||
- 智能分析演示
|
||||
- 实际场景应用
|
||||
|
||||
## 效果对比
|
||||
|
||||
| 项目 | 优化前 | 优化后 | 改进 |
|
||||
|------|--------|--------|------|
|
||||
| TTS音量 | 0.7 | 0.8 (智能调整) | 更平衡 |
|
||||
| 原声音量 | 1.0 | 1.3 (智能调整) | 显著提升 |
|
||||
| 响度差异 | ~9dB | ~3dB | 大幅缩小 |
|
||||
| 用户体验 | 需手动调整 | 自动平衡 | 明显改善 |
|
||||
|
||||
## 配置推荐
|
||||
|
||||
### 混合内容（默认）
|
||||
```python
|
||||
{
|
||||
'tts_volume': 0.8,
|
||||
'original_volume': 1.3,
|
||||
'bgm_volume': 0.3
|
||||
}
|
||||
```
|
||||
|
||||
### 原声为主的内容
|
||||
```python
|
||||
{
|
||||
'tts_volume': 0.6,
|
||||
'original_volume': 1.6,
|
||||
'bgm_volume': 0.1
|
||||
}
|
||||
```
|
||||
|
||||
### 教育类视频
|
||||
```python
|
||||
{
|
||||
'tts_volume': 0.9,
|
||||
'original_volume': 0.8,
|
||||
'bgm_volume': 0.2
|
||||
}
|
||||
```
|
||||
|
||||
## 技术特点
|
||||
|
||||
### 智能分析
|
||||
- 使用FFmpeg的loudnorm滤镜进行LUFS分析
|
||||
- RMS计算作为备用方案
|
||||
- 自动计算最佳音量调整系数
|
||||
|
||||
### 配置灵活
|
||||
- 支持多种视频类型
|
||||
- 预设配置文件
|
||||
- 用户自定义优先
|
||||
|
||||
### 性能优化
|
||||
- 可选的智能分析（默认开启）
|
||||
- 临时文件自动清理
|
||||
- 向后兼容现有代码
|
||||
|
||||
## 文件清单
|
||||
|
||||
### 核心文件
|
||||
- `app/services/audio_normalizer.py` - 音频分析和标准化
|
||||
- `app/config/audio_config.py` - 音频配置管理
|
||||
- `app/services/generate_video.py` - 集成智能调整
|
||||
- `app/services/task.py` - 任务处理优化
|
||||
- `app/models/schema.py` - 配置参数更新
|
||||
|
||||
### 测试和文档
|
||||
- `test_audio_optimization.py` - 功能测试脚本
|
||||
- `examples/audio_volume_example.py` - 使用示例
|
||||
- `docs/audio_optimization_guide.md` - 详细指南
|
||||
- `AUDIO_OPTIMIZATION_SUMMARY.md` - 本总结文档
|
||||
|
||||
## 使用方法
|
||||
|
||||
### 自动优化（推荐）
|
||||
系统会自动应用优化配置，无需额外操作。
|
||||
|
||||
### 手动配置
|
||||
```python
|
||||
# 应用预设配置
|
||||
volumes = AudioConfig.apply_volume_profile('original_focused')
|
||||
|
||||
# 根据内容类型获取推荐
|
||||
volumes = get_recommended_volumes_for_content('original_heavy')
|
||||
```
|
||||
|
||||
### 关闭智能分析
|
||||
```python
|
||||
# 在 schema.py 中设置
|
||||
ENABLE_SMART_VOLUME = False
|
||||
```
|
||||
|
||||
## 后续改进建议
|
||||
|
||||
1. **用户界面集成**: 在WebUI中添加音量配置选项
|
||||
2. **实时预览**: 提供音量调整的实时预览功能
|
||||
3. **机器学习**: 基于用户反馈学习最佳配置
|
||||
4. **批量处理**: 支持批量音频标准化
|
||||
|
||||
## 结论
|
||||
|
||||
通过实施音频响度分析和智能音量调整，成功解决了视频原声音量过小的问题。新系统能够：
|
||||
|
||||
1. **自动检测**音频响度差异
|
||||
2. **智能调整**音量平衡
|
||||
3. **保持兼容**现有配置
|
||||
4. **提供灵活**的配置选项
|
||||
|
||||
用户现在可以享受到更平衡的音频体验，无需手动调整音量即可清晰听到视频原声和TTS解说。
|
||||
162
docs/audio_optimization_guide.md
Normal file
162
docs/audio_optimization_guide.md
Normal file
@ -0,0 +1,162 @@
|
||||
# 音频音量平衡优化指南
|
||||
|
||||
## 问题描述
|
||||
|
||||
在视频剪辑后台任务中，经常出现视频原声音量比TTS生成的解说声音音量小很多的问题。即使设置了视频原声为1.0，解说音量为0.7，原声依然听起来比较小。
|
||||
|
||||
## 原因分析
|
||||
|
||||
1. **音频响度差异**：TTS生成的音频通常具有较高且一致的响度，而视频原声的音量可能本身就比较低，或者动态范围较大。
|
||||
|
||||
2. **缺乏音频标准化**：之前的代码只是简单地通过乘法器调整音量，没有进行音频响度分析和标准化处理。
|
||||
|
||||
3. **音频混合方式**：使用 `CompositeAudioClip` 进行音频混合时，不同音频轨道的响度差异会被保留。
|
||||
|
||||
## 解决方案
|
||||
|
||||
### 1. 音频标准化工具 (`audio_normalizer.py`)
|
||||
|
||||
实现了 `AudioNormalizer` 类，提供以下功能：
|
||||
|
||||
- **LUFS响度分析**：使用FFmpeg的loudnorm滤镜分析音频的LUFS响度
|
||||
- **RMS音量计算**：作为LUFS分析的备用方案
|
||||
- **音频标准化**：将音频标准化到目标响度
|
||||
- **智能音量调整**：分析TTS和原声的响度差异，计算合适的音量调整系数
|
||||
|
||||
### 2. 音频配置管理 (`audio_config.py`)
|
||||
|
||||
实现了 `AudioConfig` 类，提供：
|
||||
|
||||
- **默认音量配置**：优化后的默认音量设置
|
||||
- **视频类型配置**：针对不同类型视频的音量配置
|
||||
- **预设配置文件**：balanced、voice_focused、original_focused等
|
||||
- **内容类型推荐**：根据内容类型推荐音量设置
|
||||
|
||||
### 3. 智能音量调整
|
||||
|
||||
在 `generate_video.py` 中集成了智能音量调整功能：
|
||||
|
||||
- 自动分析TTS和原声的响度差异
|
||||
- 计算合适的音量调整系数
|
||||
- 保留用户设置的相对比例
|
||||
- 限制调整范围，避免过度调整
|
||||
|
||||
## 配置更新
|
||||
|
||||
### 默认音量设置
|
||||
|
||||
```python
|
||||
# 原来的设置
|
||||
ORIGINAL_VOLUME = 0.7
|
||||
|
||||
# 优化后的设置
|
||||
ORIGINAL_VOLUME = 1.2 # 提高原声音量
|
||||
MAX_VOLUME = 2.0 # 允许原声音量超过1.0
|
||||
```
|
||||
|
||||
### 推荐音量配置
|
||||
|
||||
```python
|
||||
# 混合内容（默认）
|
||||
'mixed': {
|
||||
'tts_volume': 0.8,
|
||||
'original_volume': 1.3,
|
||||
'bgm_volume': 0.3,
|
||||
}
|
||||
|
||||
# 原声为主的内容
|
||||
'original_heavy': {
|
||||
'tts_volume': 0.6,
|
||||
'original_volume': 1.6,
|
||||
'bgm_volume': 0.1,
|
||||
}
|
||||
```
|
||||
|
||||
## 使用方法
|
||||
|
||||
### 1. 自动优化（推荐）
|
||||
|
||||
系统会自动应用优化的音量配置：
|
||||
|
||||
```python
|
||||
# 在 task.py 中自动应用
|
||||
optimized_volumes = get_recommended_volumes_for_content('mixed')
|
||||
```
|
||||
|
||||
### 2. 手动配置
|
||||
|
||||
可以通过配置文件或参数手动设置：
|
||||
|
||||
```python
|
||||
# 应用预设配置文件
|
||||
volumes = AudioConfig.apply_volume_profile('original_focused')
|
||||
|
||||
# 根据视频类型获取配置
|
||||
volumes = AudioConfig.get_optimized_volumes('entertainment')
|
||||
```
|
||||
|
||||
### 3. 智能分析
|
||||
|
||||
启用智能音量分析（默认开启）：
|
||||
|
||||
```python
|
||||
# 在 schema.py 中控制
|
||||
ENABLE_SMART_VOLUME = True
|
||||
```
|
||||
|
||||
## 测试验证
|
||||
|
||||
运行测试脚本验证功能：
|
||||
|
||||
```bash
|
||||
source .venv/bin/activate
|
||||
python test_audio_optimization.py
|
||||
```
|
||||
|
||||
测试结果显示：
|
||||
- TTS测试音频LUFS: -24.15
|
||||
- 原声测试音频LUFS: -32.95
|
||||
- 建议调整系数：TTS 1.61, 原声 3.00
|
||||
|
||||
## 效果对比
|
||||
|
||||
### 优化前
|
||||
- TTS音量：0.7
|
||||
- 原声音量：1.0
|
||||
- 问题：原声明显比TTS小
|
||||
|
||||
### 优化后
|
||||
- TTS音量：0.8（智能调整）
|
||||
- 原声音量：1.3（智能调整）
|
||||
- 效果：音量平衡，听感自然
|
||||
|
||||
## 注意事项
|
||||
|
||||
1. **FFmpeg依赖**：音频分析功能需要FFmpeg支持loudnorm滤镜
|
||||
2. **性能影响**：智能分析会增加少量处理时间
|
||||
3. **音质保持**：所有调整都保持音频质量不变
|
||||
4. **兼容性**：向后兼容现有的音量设置
|
||||
|
||||
## 故障排除
|
||||
|
||||
### 1. LUFS分析失败
|
||||
- 检查FFmpeg是否安装
|
||||
- 确认音频文件格式支持
|
||||
- 自动降级到RMS分析
|
||||
|
||||
### 2. 音量调整过度
|
||||
- 检查音量限制设置
|
||||
- 调整目标LUFS值
|
||||
- 使用预设配置文件
|
||||
|
||||
### 3. 性能问题
|
||||
- 关闭智能分析：`ENABLE_SMART_VOLUME = False`
|
||||
- 使用简单音量配置
|
||||
- 减少音频分析频率
|
||||
|
||||
## 未来改进
|
||||
|
||||
1. **机器学习优化**：基于用户反馈学习最佳音量配置
|
||||
2. **实时预览**：在UI中提供音量调整预览
|
||||
3. **批量处理**：支持批量音频标准化
|
||||
4. **更多音频格式**：扩展支持的音频格式
|
||||
Loading…
x
Reference in New Issue
Block a user