webrtcvad

import webrtcvad import struct # WebRTC VAD requires 16-bit mono PCM audio at specific sample rates # and frame durations (10, 20, or 30 ms). sample_rate = 16000 # Hz frame_duration_ms = 30 # ms bytes_per_sample = 2 # 16-bit audio # Calculate frame size in bytes frame_size_bytes = int(sample_rate * (frame_duration_ms / 1000.0) * bytes_per_sample) # Create a VAD instance with an aggressiveness mode (0-3) # 0: least aggressive, 3: most aggressive vad = webrtcvad.Vad(3) # Create a silent audio frame (16-bit mono PCM) silence_frame = b'\x00\x00' * int(frame_size_bytes / bytes_per_sample) # Create a mock speech-like frame (simple sine wave for demonstration) # In a real application, this would come from an audio input. speech_frame = b'' for i in range(int(frame_size_bytes / bytes_per_sample)): # Simple sine wave approximation for a speech-like signal amplitude = 10000 # Max 32767 for 16-bit value = int(amplitude * (i % 30 < 15) - amplitude * (i % 30 >= 15)) # Square wave approximation speech_frame += struct.pack('<h', value) print(f"Processing frame of {frame_duration_ms} ms at {sample_rate} Hz") # Test with silence is_speech_silence = vad.is_speech(silence_frame, sample_rate) print(f"Silence frame contains speech: {is_speech_silence}") # Test with speech-like audio is_speech_mock = vad.is_speech(speech_frame, sample_rate) print(f"Mock speech frame contains speech: {is_speech_mock}") # You can also set the mode after initialization vad.set_mode(1) print(f"VAD aggressiveness set to 1.")