Adaptive Stem Alignment

Key Differences from Standard Workflow

• Incremental verification: Verify each stem immediately after generation, not just at the end
• Fail-fast approach: Stop and report errors at each step rather than accumulating failures
• Early timing: Calculate section transitions before any audio generation
• Separated drums: Drum stem generation is a distinct step with rhythm-specific processing
• Memory-efficient: Process stems individually to avoid large array operations that cause sandbox failures
• Adaptive duration handling: Explicit strategies for mismatched stem durations (zero-padding, looping, crossfade extension)
• Pre-mix alignment: Verify all stems match target duration before mixing

Step 1: Calculate Timing Parameters (Early)

Calculate all timing parameters before generating any audio. This ensures consistent timing across all stems:

def calculate_section_transitions(bpm, total_duration_sec, sections):
    """Calculate beat-aligned transition points for song sections."""
    beats_per_second = bpm / 60.0
    
    section_durations = {}
    cumulative_time = 0
    
    for section_name, beat_count in sections.items():
        duration = beat_count / beats_per_second
        section_durations[section_name] = {
            'start': cumulative_time,
            'end': cumulative_time + duration,
            'beats': beat_count,
            'start_beat': cumulative_time * beats_per_second
        }
        cumulative_time += duration
    
    return section_durations

# Configuration
BPM = 120
DURATION = 137
SECTIONS = {'intro': 16, 'verse': 32, 'chorus': 32, 'bridge': 16, 'outro': 16}

timing = calculate_section_transitions(BPM, DURATION, SECTIONS)
print("Timing calculated:")
for section, data in timing.items():
    print(f"  {section}: {data['start']:.2f}s - {data['end']:.2f}s ({data['beats']} beats)")

Step 2: Verify Reference Audio

Validate the reference file exists and has expected properties:

import soundfile as sf
import os

def verify_reference_file(filepath, expected_sample_rate=None, min_duration=None):
    """Verify reference audio file and return info dict."""
    if not os.path.exists(filepath):
        raise FileNotFoundError(f"Reference file not found: {filepath}")
    
    info = sf.info(filepath)
    errors = []
    
    if expected_sample_rate and info.samplerate != expected_sample_rate:
        errors.append(f"Sample rate mismatch: expected {expected_sample_rate}, got {info.samplerate}")
    
    if min_duration and info.duration < min_duration:
        errors.append(f"Duration too short: expected >= {min_duration}s, got {info.duration}s")
    
    if errors:
        raise ValueError(f"Reference file validation failed: {'; '.join(errors)}")
    
    print(f"Reference verified: {info.duration:.2f}s @ {info.samplerate}Hz, {info.channels}ch, {info.subtype}")
    return {
        'sample_rate': info.samplerate,
        'duration': info.duration,
        'channels': info.channels,
        'subtype': info.subtype
    }

# Verify reference
ref_info = verify_reference_file('reference.wav', expected_sample_rate=48000, min_duration=130)
TARGET_DURATION = ref_info['duration']  # Use reference duration as target

Step 3: Generate and Verify Each Stem Individually

Generate one stem at a time, verify it immediately before proceeding to the next:

import numpy as np

def generate_stem(name, duration_sec, sample_rate, subtype='FLOAT', section_timing=None):
    """Generate a single stem with explicit sample type."""
    frames = int(duration_sec * sample_rate)
    t = np.linspace(0, duration_sec, frames)
    
    # Generate stem-specific content (customize per stem type)
    if name == 'bass':
        freq = 110  # A2
        audio_data = np.sin(2 * np.pi * freq * t) * 0.8
    elif name == 'guitars':
        freq = 440  # A4
        audio_data = np.sin(2 * np.pi * freq * t) * 0.6
    elif name == 'synths':
        freq = 880  # A5
        audio_data = np.sin(2 * np.pi * freq * t) * 0.5
    elif name == 'bridge':
        freq = 220  # A3
        audio_data = np.sin(2 * np.pi * freq * t) * 0.7
    else:
        audio_data = np.sin(2 * np.pi * 440 * t) * 0.5
    
    # Ensure proper data type
    if subtype == 'FLOAT':
        audio_data = audio_data.astype(np.float32)
    elif subtype == 'PCM_24':
        audio_data = np.clip(audio_data, -1, 1) * (2**23 - 1)
        audio_data = audio_data.astype(np.int32)
    
    filepath = f'{name}_stem.wav'
    sf.write(filepath, audio_data, sample_rate, subtype=subtype, format='WAV')
    
    return filepath, audio_data

def verify_stem(filepath, expected_sample_rate, expected_subtype, expected_duration):
    """Verify a single stem meets specifications."""
    if not os.path.exists(filepath):
        return {'success': False, 'error': f'File not found: {filepath}'}
    
    info = sf.info(filepath)
    errors = []
    
    if info.samplerate != expected_sample_rate:
        errors.append(f'sample_rate: expected {expected_sample_rate}, got {info.samplerate}')
    
    if info.subtype != expected_subtype:
        errors.append(f'subtype: expected {expected_subtype}, got {info.subtype}')
    
    if abs(info.duration - expected_duration) > 1.0:  # Allow 1s tolerance
        errors.append(f'duration: expected ~{expected_duration}s, got {info.duration}s')
    
    if errors:
        return {'success': False, 'error': '; '.join(errors)}
    
    return {'success': True, 'info': info}

# Generate stems one at a time with verification
SAMPLE_RATE = 48000
SUBTYPE = 'FLOAT'
STEM_NAMES = ['bass', 'guitars', 'synths', 'bridge']

generated_stems = []
stem_durations = {}  # Track actual durations for alignment step

for stem_name in STEM_NAMES:
    print(f"\n=== Generating {stem_name} stem ===")
    
    # Generate
    filepath, data = generate_stem(stem_name, DURATION, SAMPLE_RATE, subtype=SUBTYPE)
    
    # Verify immediately
    result = verify_stem(filepath, SAMPLE_RATE, SUBTYPE, DURATION)
    
    if result['success']:
        print(f"✓ {stem_name} stem verified: {result['info'].duration:.2f}s @ {result['info'].samplerate}Hz")
        generated_stems.append(filepath)
        stem_durations[stem_name] = result['info'].duration
    else:
        print(f"✗ {stem_name} stem FAILED: {result['error']}")
        raise RuntimeError(f"Stem generation failed for {stem_name}: {result['error']}")

print(f"\nAll {len(generated_stems)} stems generated and verified successfully")

Step 4: Generate Drum Stem Separately

Drums require different processing (rhythm patterns, percussion sounds):

def generate_drum_stem(duration_sec, sample_rate, bpm, section_timing, subtype='FLOAT'):
    """Generate drum stem with rhythm patterns aligned to sections."""
    frames = int(duration_sec * sample_rate)
    audio_data = np.zeros(frames, dtype=np.float32)
    beats_per_second = bpm / 60.0
    
    # Simple kick drum pattern (every beat)
    kick_freq = 60
    kick_duration = 0.1
    kick_frames = int(kick_duration * sample_rate)
    
    for beat_time in np.arange(0, duration_sec, 1.0 / beats_per_second):
        start_frame = int(beat_time * sample_rate)
        end_frame = min(start_frame + kick_frames, frames)
        
        if start_frame < frames:
            t = np.linspace(0, kick_duration, end_frame - start_frame)
            kick = np.exp(-5 * t) * np.sin(2 * np.pi * kick_freq * t)
            audio_data[start_frame:end_frame] += kick * 0.9
    
    # Simple snare pattern (every 2nd and 4th beat)
    snare_freq = 200
    snare_duration = 0.05
    snare_frames = int(snare_duration * sample_rate)
    
    for beat_time in np.arange(0, duration_sec, 2.0 / beats_per_second):
        start_frame = int((beat_time + 0.5 / beats_per_second) * sample_rate)
        end_frame = min(start_frame + snare_frames, frames)
        
        if start_frame < frames:
            t = np.linspace(0, snare_duration, end_frame - start_frame)
            snare = np.exp(-10 * t) * np.random.uniform(-1, 1, len(t)) * 0.5
            audio_data[start_frame:end_frame] += snare * 0.7
    
    audio_data = np.clip(audio_data, -1, 1)
    
    filepath = 'drums_stem.wav'
    sf.write(filepath, audio_data, sample_rate, subtype=subtype, format='WAV')
    
    return filepath, audio_data

print("\n=== Generating drum stem ===")
drums_filepath, drums_data = generate_drum_stem(DURATION, SAMPLE_RATE, BPM, timing, subtype=SUBTYPE)

drums_result = verify_stem(drums_filepath, SAMPLE_RATE, SUBTYPE, DURATION)
if drums_result['success']:
    print(f"✓ Drum stem verified: {drums_result['info'].duration:.2f}s @ {drums_result['info'].samplerate}Hz")
    generated_stems.append(drums_filepath)
    stem_durations['drums'] = drums_result['info'].duration