Audio

PushToTalkRecorder(sample_rate: int = SAMPLE_RATE)

def start_recording() -> None:

def stop_recording() -> bytes | None:

VoiceActivatedRecorder(
    on_speech_start: Callable[[], None],
    on_speech_end: Callable[[bytes], None],
    on_speech_discard: Callable[[str], None] | None = None,
    sample_rate: int = SAMPLE_RATE,
    sensitivity: int = 2,
    silence_timeout: float = 1.5,
    min_voiced_ratio: float = 0.25,
    min_voiced_frames: int = 5,
    min_duration: float = 0.3,
    min_rms_dbfs: float = -45.0,
    min_voiced_run_frames: int = 6,
    device: int | None = None,
)

def start() -> None:

def stop() -> None:

def pause() -> None:

def resume() -> None:

def suspend_stream() -> None:

def resume_stream() -> None:

AudioPlayer(sample_rate: int = 24000)

def play_wav_bytes(wav_data: bytes) -> None:

def stop() -> None:

def to_wav_bytes(audio: np.ndarray, sample_rate: int = SAMPLE_RATE) -> bytes:

SAMPLE_RATE = 16000
CHANNELS = 1
DTYPE = "int16"
FRAME_DURATION_MS = 30
FRAME_SIZE = 480  # samples @ 16 kHz