WLED_Audio_Bridge_LMS/bridge.py

import os
import sys
import time
import socket
import struct
import numpy as np

# Network settings
UDP_IP = os.environ.get("UDP_IP", "239.0.0.1")
UDP_PORT = int(os.environ.get("UDP_PORT", "11988"))

# Audio stream constants
SAMPLE_RATE = 44100
CHUNK_SIZE = 1024
CHUNK_DURATION = CHUNK_SIZE / SAMPLE_RATE
FRAME_BYTES = CHUNK_SIZE * 4
MAX_SILENT_FRAMES = 43  # ~1 second of silence at 43.06 FPS

# DSP tuning environment overrides
FREQ_MIN = float(os.environ.get("FREQ_MIN", "150.0"))
FREQ_MAX = float(os.environ.get("FREQ_MAX", "6000.0"))
GAIN_MULT = float(os.environ.get("GAIN_MULT", "3500.0"))
SILENCE_THRESHOLD = float(os.environ.get("SILENCE_THRESHOLD", "0.5"))

sock = socket.socket(socket.AF_INET, socket.SOCK_DGRAM, socket.IPPROTO_UDP)
sock.setsockopt(socket.IPPROTO_IP, socket.IP_MULTICAST_TTL, 2)

# Pre-compute Hanning window to save CPU cycles inside the loop
HANNING_WINDOW = np.hanning(CHUNK_SIZE).astype(np.float32)

# Compute 16 logarithmic frequency bands
FREQ_EDGES = np.logspace(np.log10(FREQ_MIN), np.log10(FREQ_MAX), 17)
fft_freqs = np.fft.rfftfreq(CHUNK_SIZE, 1.0 / SAMPLE_RATE)

bins_idx = []
for i in range(16):
    low = FREQ_EDGES[i]
    high = FREQ_EDGES[i + 1]
    idx = np.where((fft_freqs >= low) & (fft_freqs < high) & (fft_freqs > 0))[0]
    if len(idx) == 0:
        non_zero_bins = np.where(fft_freqs > 0)[0]
        closest = non_zero_bins[np.argmin(np.abs(fft_freqs[non_zero_bins] - low))]
        idx = [closest]
    bins_idx.append(idx)

sample_smth = 0.0
silence_frames = 0
STRUCT_FMT_V2 = "<6s2xffB3x16sd"

start_time = None
frames_processed = 0

while True:
    raw_data = sys.stdin.buffer.read(FRAME_BYTES)
    if not raw_data or len(raw_data) < FRAME_BYTES:
        break

    now = time.perf_counter()
    
    # Start the master hardware clock the exact millisecond the first audio byte arrives
    if start_time is None:
        start_time = now

    # Do the DSP math
    audio = np.frombuffer(raw_data, dtype=np.int16).astype(np.float32)
    left = audio[0::2]
    right = audio[1::2]
    mono = (left + right) * (1.0 / 65536.0)

    raw_mag = float(np.max(np.abs(mono)) * 255.0)
    sample_smth = 0.7 * sample_smth + 0.3 * raw_mag
    sample_peak = 1 if raw_mag > (sample_smth * 1.5 + 20) else 0

    if raw_mag < SILENCE_THRESHOLD:
        silence_frames += 1
    else:
        silence_frames = 0

    if silence_frames <= MAX_SILENT_FRAMES:
        windowed = mono * HANNING_WINDOW
        fft_vals = np.abs(np.fft.rfft(windowed)) * (2.0 / CHUNK_SIZE)

        fft_result = bytearray(16)
        for i in range(16):
            energy = float(np.mean(fft_vals[bins_idx[i]])) * GAIN_MULT
            fft_result[i] = min(255, int(np.clip(energy, 0, 255)))

        payload = struct.pack(
            STRUCT_FMT_V2,
            b"00002\x00",
            float(raw_mag),
            float(sample_smth),
            sample_peak,
            bytes(fft_result),
            float(raw_mag)
        )

        try:
            sock.sendto(payload, (UDP_IP, UDP_PORT))
        except Exception:
            pass

    # PERFECT METRONOME PACING
    frames_processed += 1
    target_time = start_time + (frames_processed * CHUNK_DURATION)
    sleep_time = target_time - time.perf_counter()
    
    if sleep_time > 0:
        time.sleep(sleep_time)
    elif sleep_time < -2.0:
        # Only snap the clock if the container actually suspended or froze 
        # for over 2 seconds so we don't spam a million packets at once.
        start_time = time.perf_counter()
        frames_processed = 0