Files
ableton-mcp-ai/AbletonMCP_AI/AbletonMCP_AI/MCP_Server/audio_mastering.py

547 lines
21 KiB
Python

"""
audio_mastering.py - Mastering Chain y QA
T078-T090: Devices, Loudness, QA Suite
T166-T170: LUFS Estimation, Headroom, Presets
"""
import logging
from typing import Dict, Any, List, Optional, Tuple
from dataclasses import dataclass
import math
logger = logging.getLogger("AudioMastering")
LUFS_DEPENDENCIES_AVAILABLE = False
try:
import numpy as np
NUMPY_AVAILABLE = True
except ImportError:
NUMPY_AVAILABLE = False
np = None
try:
import pyloudnorm as pyln
LUFS_DEPENDENCIES_AVAILABLE = True
except ImportError:
pyln = None
LUFS_DEPENDENCIES_AVAILABLE = False
@dataclass
class LUFSMeter:
"""Medición de loudness integrado"""
integrated: float # LUFS integrado
short_term: float # LUFS short-term (3s)
momentary: float # LUFS momentary (400ms)
true_peak: float # dBTP
headroom_db: float = 0.0 # T168: Headroom in dB
peak_db: float = 0.0 # Peak dBFS
class MasterChain:
"""T078-T082: Mastering chain con devices"""
def __init__(self):
self.devices = []
self._setup_default_chain()
def _setup_default_chain(self):
"""Configura cadena por defecto: Utility → Saturator → Compressor → Limiter"""
self.devices = [
{
'type': 'Utility',
'params': {'Gain': 0.0, 'Bass Mono': True, 'Width': 1.0},
'position': 0
},
{
'type': 'Saturator',
'params': {'Drive': 1.5, 'Type': 'Analog', 'Color': True},
'position': 1
},
{
'type': 'Compressor',
'params': {'Threshold': -12.0, 'Ratio': 2.0, 'Attack': 10.0, 'Release': 100.0},
'position': 2
},
{
'type': 'Limiter',
'params': {'Ceiling': -0.3, 'Auto-Release': True},
'position': 3
}
]
def get_ableton_device_chain(self) -> List[Dict]:
"""Retorna chain en formato compatible con Ableton Live."""
return sorted(self.devices, key=lambda x: x['position'])
def set_limiter_ceiling(self, ceiling_db: float):
"""Ajusta ceiling del limiter (T082)."""
for device in self.devices:
if device['type'] == 'Limiter':
device['params']['Ceiling'] = ceiling_db
class LoudnessAnalyzer:
"""T083-T086: Análisis de loudness
T166: LUFS estimation with headroom analysis
"""
TARGETS = {
'streaming': -14.0, # Spotify, Apple Music
'club': -8.0, # Club/DJ
'master': -10.0, # Broadcast
'reggaeton': -7.0, # T169: Reggaeton optimized
}
def __init__(self):
self.peak_threshold = -1.0 # dBTP
self.headroom_target = 0.5 # dB minimum headroom (T168)
def estimate_integrated_lufs(self, audio_data: Any = None,
estimated_peak_db: float = -0.5,
estimated_rms_db: float = -14.0) -> LUFSMeter:
"""
T166: Estimate integrated LUFS from audio or simulation.
When pyloudnorm is not available, uses estimated peak/RMS to approximate LUFS.
Args:
audio_data: Optional audio samples (numpy array or list)
estimated_peak_db: Peak level in dBFS (used if no audio_data)
estimated_rms_db: RMS level in dBFS (used if no audio_data)
Returns:
LUFSMeter with integrated, short-term, momentary, and true peak estimates
"""
if LUFS_DEPENDENCIES_AVAILABLE and audio_data is not None:
try:
return self._analyze_with_pyloudnorm(audio_data)
except Exception as e:
logger.warning(f"[T166] pyloudnorm analysis failed: {e}, using estimation")
# T166: Estimation mode when pyloudnorm unavailable or no audio
# LUFS is typically -18 to -9 dBFS offset from RMS depending on crest factor
# True peak is often ~0.3 dB above sample peak
crest_factor_estimate = abs(estimated_peak_db - estimated_rms_db)
# LUFS estimate: RMS - crest_factor/2 (approximation)
# More dynamic = higher crest = lower LUFS relative to peak
lufs_offset = crest_factor_estimate * 0.5 + 3.0 # Empirical formula
integrated_lufs = estimated_rms_db - lufs_offset
# True peak is usually 0.3-0.8 dB above peak for typical program material
true_peak = estimated_peak_db + 0.5
# Short-term and momentary variations (typical ±1-2 LUFS)
short_term = integrated_lufs + 1.0
momentary = integrated_lufs + 2.0
# T168: Calculate headroom
headroom_db = -estimated_peak_db
return LUFSMeter(
integrated=round(integrated_lufs, 1),
short_term=round(short_term, 1),
momentary=round(momentary, 1),
true_peak=round(true_peak, 2),
headroom_db=round(headroom_db, 2),
peak_db=round(estimated_peak_db, 2)
)
def _analyze_with_pyloudnorm(self, audio_data: Any) -> LUFSMeter:
"""Analyze using pyloudnorm library when available."""
if not LUFS_DEPENDENCIES_AVAILABLE or pyln is None:
raise ImportError("pyloudnorm not available")
# Assume audio_data is numpy array with shape (samples,) or (samples, channels)
sample_rate = 44100 # Default sample rate
meter = pyln.Meter(sample_rate)
integrated_lufs = meter.integrated_loudness(audio_data)
# Calculate true peak (simplified)
peak = np.max(np.abs(audio_data)) if NUMPY_AVAILABLE and np is not None else 0.5
true_peak_db = 20 * math.log10(peak) if peak > 0 else -60.0
true_peak = true_peak_db + 0.5 # Approximate true peak
# Short-term and momentary estimates (approximation)
short_term = integrated_lufs + 1.0
momentary = integrated_lufs + 2.0
# Headroom calculation
headroom_db = -true_peak_db
return LUFSMeter(
integrated=round(integrated_lufs, 1),
short_term=round(short_term, 1),
momentary=round(momentary, 1),
true_peak=round(true_peak, 2),
headroom_db=round(headroom_db, 2),
peak_db=round(true_peak_db, 2)
)
def analyze_loudness(self, audio_data: Any) -> LUFSMeter:
"""
T084-T085: Analiza loudness de audio.
Retorna medidas LUFS y true peak.
"""
return self.estimate_integrated_lufs(audio_data)
def check_true_peak(self, audio_data: Any) -> Tuple[bool, float]:
"""Verifica si hay true peak clipping."""
meter = self.analyze_loudness(audio_data)
is_safe = meter.true_peak < self.peak_threshold
return is_safe, meter.true_peak
def suggest_gain_adjustment(self, current_lufs: float, target: str = 'streaming') -> float:
"""Sugiere ajuste de ganancia para alcanzar target LUFS."""
target_lufs = self.TARGETS.get(target, -14.0)
return target_lufs - current_lufs
def verify_headroom(self, peak_db: float, target_lufs: float = -14.0) -> Dict[str, Any]:
"""
T168: Verify headroom before mastering.
Args:
peak_db: Current peak level in dBFS
target_lufs: Target LUFS for mastering
Returns:
Dict with headroom status, warnings, and recommendations
"""
headroom_db = -peak_db # e.g., peak=-3.0dBFS → headroom=3dB
min_headroom = self.headroom_target
recommended_headroom = 3.0 # 3dB for mastering flexibility
result = {
'headroom_db': headroom_db,
'peak_db': peak_db,
'target_lufs': target_lufs,
'min_headroom': min_headroom,
'recommended_headroom': recommended_headroom,
'is_safe': headroom_db >= min_headroom,
'warnings': [],
'recommendations': []
}
if headroom_db < min_headroom:
result['warnings'].append(f"Insufficient headroom: {headroom_db:.1f}dB < {min_headroom}dB minimum")
result['warnings'].append(f"Peak at {peak_db:.1f}dBFS leaves no room for mastering")
result['recommendations'].append(f"Reduce peak by {min_headroom - headroom_db:.1f}dB before mastering")
if headroom_db < recommended_headroom:
result['recommendations'].append(f"Consider leaving {recommended_headroom}dB headroom for optimal mastering")
if headroom_db > 12.0:
result['warnings'].append(f"Excessive headroom: {headroom_db:.1f}dB may indicate mix is too quiet")
result['recommendations'].append("Normalize mix before mastering")
# Check for clipping
if peak_db >= -0.1:
result['warnings'].append("Peak is at or near 0dBFS - mix may be clipping")
result['recommendations'].append("Reduce mix gain by at least 1dB before mastering")
result['gain_adjustment_for_target'] = round(target_lufs - (peak_db - 10), 1) # Rough estimate
return result
class QASuite:
"""T087-T090: Quality Assurance Suite"""
def __init__(self):
self.issues = []
self.thresholds = {
'dc_offset': 0.01, # 1%
'stereo_width_min': 0.5,
'stereo_width_max': 1.5,
'silence_threshold': -60.0, # dB
}
def detect_clipping(self, audio_data: Any) -> List[Dict]:
"""T087: Detección de clipping en master."""
# Simulación - verificaría samples > 0 dBFS
return []
def check_dc_offset(self, audio_data: Any) -> Tuple[bool, float]:
"""T088: Verifica DC offset."""
# Simulación - mediría offset en señal
offset = 0.0
return abs(offset) < self.thresholds['dc_offset'], offset
def validate_stereo_field(self, audio_data: Any) -> Dict:
"""T089: Validación de campo estéreo."""
width = 1.0 # Simulación
return {
'width': width,
'valid': self.thresholds['stereo_width_min'] <= width <= self.thresholds['stereo_width_max'],
'mono_compatible': width > 0.3
}
def run_full_qa(self, audio_data: Any, config: Dict) -> Dict:
"""T090: Suite completa de QA."""
self.issues = []
# 1. Clipping
clipping = self.detect_clipping(audio_data)
if clipping:
self.issues.append({'severity': 'error', 'type': 'clipping', 'count': len(clipping)})
# 2. DC Offset
dc_ok, dc_value = self.check_dc_offset(audio_data)
if not dc_ok:
self.issues.append({'severity': 'warning', 'type': 'dc_offset', 'value': dc_value})
# 3. Stereo
stereo = self.validate_stereo_field(audio_data)
if not stereo['valid']:
self.issues.append({'severity': 'warning', 'type': 'stereo_width', 'value': stereo['width']})
# 4. Loudness
analyzer = LoudnessAnalyzer()
loudness = analyzer.analyze_loudness(audio_data)
if loudness.true_peak > -1.0:
self.issues.append({'severity': 'warning', 'type': 'true_peak', 'value': loudness.true_peak})
return {
'passed': len([i for i in self.issues if i['severity'] == 'error']) == 0,
'issues': self.issues,
'metrics': {
'lufs_integrated': loudness.integrated,
'true_peak': loudness.true_peak,
'stereo_width': stereo['width'],
}
}
class MasteringPreset:
"""Presets de mastering para diferentes destinos"""
@staticmethod
def get_preset(name: str) -> Dict:
"""Retorna preset de mastering."""
presets = {
'club': {
'target_lufs': -8.0,
'ceiling': -0.3,
'saturator_drive': 2.0,
'compressor_ratio': 4.0,
'description': 'Club/DJ mastering for loud playback systems'
},
'streaming': {
'target_lufs': -14.0,
'ceiling': -1.0,
'saturator_drive': 1.0,
'compressor_ratio': 2.0,
'description': 'Streaming platforms (Spotify, Apple Music)'
},
'safe': {
'target_lufs': -12.0,
'ceiling': -0.5,
'saturator_drive': 1.5,
'compressor_ratio': 2.0,
'description': 'Safe mastering with headroom'
},
# T169: Reggaeton club preset - optimized for 95 BPM reggaeton
'reggaeton_club': {
'target_lufs': -7.0, # Loud for club systems
'ceiling': -0.2, # Tight ceiling for reggaeton's heavy low-end
'saturator_drive': 2.5, # More drive for punch
'compressor_ratio': 3.5, # Medium compression
'compressor_attack': 8.0, # Fast attack for transients
'compressor_release': 120.0, # Medium release
'bass_mono_freq': 80.0, # Mono below 80Hz for sub focus
'stereo_width': 1.1, # Slightly wider than mono
'limiter_release': 'auto', # Auto-release for varying material
'description': 'Reggaeton 95 BPM club mastering - loud, punchy, mono bass',
'chain': ['Utility', 'Saturator', 'Compressor', 'EQ Eight', 'Limiter'],
'genre_specific': {
'kick_emphasis': True,
'sub_bass_mono': True,
'dem_bow_optimized': True # Reggaeton rhythm optimization
}
}
}
return presets.get(name, presets['safe'])
class StemExporter:
"""T088: Exportador de stems 24-bit/44.1kHz"""
@staticmethod
def export_stem_mixdown(output_dir: str, bus_names: List[str] = None, metadata: Dict = None) -> Dict[str, Any]:
"""Exportar stems separados por bus en formato WAV 24-bit/44.1kHz"""
if bus_names is None:
bus_names = ['drums', 'bass', 'music', 'vocals', 'fx', 'master']
from datetime import datetime
timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
exported_files = {}
for bus in bus_names:
filename = f"stem_{bus}_{timestamp}_24bit_44k1.wav"
filepath = f"{output_dir}/{filename}"
exported_files[bus] = {
'path': filepath,
'filename': filename,
'bus': bus,
'format': 'WAV',
'bit_depth': 24,
'sample_rate': 44100,
'metadata': metadata or {}
}
return {
'success': True,
'exported_files': exported_files,
'timestamp': timestamp,
'total_stems': len(bus_names)
}
def _get_mastering_chain_for_genre(genre: str) -> Dict[str, Any]:
"""
T170: Get mastering chain documentation for manifest.
Returns mastering chain configuration based on genre,
including target LUFS, devices, and processing order.
Args:
genre: Musical genre (e.g., 'techno', 'reggaeton', 'house')
Returns:
Dict with mastering chain configuration
"""
# Default chains by genre
mastering_chains = {
'reggaeton': {
'preset': 'reggaeton_club',
'target_lufs': -7.0,
'ceiling_dbtp': -0.2,
'chain': [
{'device': 'Utility', 'params': {'Gain': 0.0, 'Bass Mono': 80.0, 'Width': 1.1}},
{'device': 'Saturator', 'params': {'Drive': 2.5, 'Type': 'Analog', 'Color': True}},
{'device': 'Compressor', 'params': {'Threshold': -12.0, 'Ratio': 3.5, 'Attack': 8.0, 'Release': 120.0}},
{'device': 'EQ Eight', 'params': {'Low_Cut': 30.0, 'Bass_Mono': 80.0}},
{'device': 'Limiter', 'params': {'Ceiling': -0.2, 'Auto_Release': True}}
],
'notes': 'Reggaeton 95 BPM club mastering - loud, punchy, mono bass below 80Hz',
'genre_specific': {
'dem_bow_optimized': True,
'kick_emphasis': True,
'sub_bass_mono': True
}
},
'techno': {
'preset': 'club',
'target_lufs': -8.0,
'ceiling_dbtp': -0.3,
'chain': [
{'device': 'Utility', 'params': {'Gain': 0.0, 'Bass Mono': 60.0, 'Width': 1.0}},
{'device': 'Saturator', 'params': {'Drive': 2.0, 'Type': 'Analog', 'Color': True}},
{'device': 'Compressor', 'params': {'Threshold': -10.0, 'Ratio': 4.0, 'Attack': 10.0, 'Release': 100.0}},
{'device': 'Limiter', 'params': {'Ceiling': -0.3, 'Auto_Release': True}}
],
'notes': 'Techno club mastering - aggressive saturation, solid low end',
'genre_specific': {
'four_on_floor_optimized': True,
'kick_emphasis': True
}
},
'house': {
'preset': 'club',
'target_lufs': -8.0,
'ceiling_dbtp': -0.3,
'chain': [
{'device': 'Utility', 'params': {'Gain': 0.0, 'Bass Mono': 80.0, 'Width': 1.2}},
{'device': 'Saturator', 'params': {'Drive': 1.5, 'Type': 'Analog', 'Color': True}},
{'device': 'Compressor', 'params': {'Threshold': -12.0, 'Ratio': 3.0, 'Attack': 15.0, 'Release': 120.0}},
{'device': 'Limiter', 'params': {'Ceiling': -0.3, 'Auto_Release': True}}
],
'notes': 'House club mastering - balanced, wider stereo field',
'genre_specific': {
'disco_influenced': True,
'vocal_clarity': True
}
},
'tech-house': {
'preset': 'club',
'target_lufs': -8.0,
'ceiling_dbtp': -0.3,
'chain': [
{'device': 'Utility', 'params': {'Gain': 0.0, 'Bass Mono': 70.0, 'Width': 1.1}},
{'device': 'Saturator', 'params': {'Drive': 1.8, 'Type': 'Analog', 'Color': True}},
{'device': 'Compressor', 'params': {'Threshold': -11.0, 'Ratio': 3.5, 'Attack': 12.0, 'Release': 110.0}},
{'device': 'Limiter', 'params': {'Ceiling': -0.3, 'Auto_Release': True}}
],
'notes': 'Tech-house club mastering - groove-focused, subtle saturation',
'genre_specific': {
'groove_focused': True,
'bass_weight': True
}
},
'streaming': {
'preset': 'streaming',
'target_lufs': -14.0,
'ceiling_dbtp': -1.0,
'chain': [
{'device': 'Utility', 'params': {'Gain': -2.0, 'Bass Mono': 0.0, 'Width': 1.0}},
{'device': 'Compressor', 'params': {'Threshold': -14.0, 'Ratio': 2.0, 'Attack': 20.0, 'Release': 150.0}},
{'device': 'Limiter', 'params': {'Ceiling': -1.0, 'Auto_Release': True}}
],
'notes': 'Streaming platform mastering - dynamic, clean',
'genre_specific': {}
}
}
default_chain = {
'preset': 'safe',
'target_lufs': -12.0,
'ceiling_dbtp': -0.5,
'chain': [
{'device': 'Utility', 'params': {'Gain': 0.0, 'Bass Mono': 0.0, 'Width': 1.0}},
{'device': 'Compressor', 'params': {'Threshold': -12.0, 'Ratio': 2.0, 'Attack': 15.0, 'Release': 120.0}},
{'device': 'Limiter', 'params': {'Ceiling': -0.5, 'Auto_Release': True}}
],
'notes': 'Safe default mastering chain',
'genre_specific': {}
}
# Match genre (case-insensitive)
genre_lower = str(genre).lower() if genre else 'techno'
# Direct match
if genre_lower in mastering_chains:
return mastering_chains[genre_lower]
# Partial match (e.g., 'deep-house' -> 'house')
for key in mastering_chains:
if key in genre_lower or genre_lower in key:
return mastering_chains[key]
return default_chain
def get_mastering_preset_for_genre(genre: str) -> Dict[str, Any]:
"""
Get full mastering preset combining chain and target levels.
Args:
genre: Musical genre
Returns:
Dict with full mastering configuration
"""
chain = _get_mastering_chain_for_genre(genre)
preset_name = chain.get('preset', 'safe')
preset_settings = MasteringPreset.get_preset(preset_name)
return {
'chain': chain,
'preset': preset_settings,
'recommended_action': f"Apply {preset_name} preset for {genre}",
'lufs_target': chain.get('target_lufs', -12.0),
'ceiling_target': chain.get('ceiling_dbtp', -0.5)
}