qi) :dZddlZddlZddlZddlmZddlm Z ddl m Z dZ defdZ defd Zdefd Zd ed edefd ZdededefdZdZdededefdZdedededefdZdedededefdZdedededefdZd ededededef d!Zdedededefd"Zdedefd#Zy)$zAudio utility functions for Pipecat. This module provides common audio processing utilities including mixing, format conversion, volume calculation, and codec transformations for various audio formats used in Pipecat pipelines. N)BaseAudioResamplerSOXRAudioResamplerSOXRStreamAudioResamplerreturnc ddl}|j5|jd|jdtddddt di|S#1swYxYw)aCreate a default audio resampler instance. .. deprecated:: 0.0.74 This function is deprecated and will be removed in a future version. Use `create_stream_resampler` for real-time processing scenarios or `create_file_resampler` for batch processing of complete audio files. Args: **kwargs: Additional keyword arguments passed to the resampler constructor. Returns: A configured SOXRAudioResampler instance. rNalwaysz`create_default_resampler` is deprecated. Use `create_stream_resampler` for real-time processing scenarios or `create_file_resampler` for batch processing of complete audio files.) stacklevel)warningscatch_warnings simplefilterwarnDeprecationWarningr)kwargsrs E/opt/pipecat/venv/lib/python3.12/site-packages/pipecat/audio/utils.pycreate_default_resamplerrse  " h'  T      ' ''  s *AAc tdi|S)zCreate an audio resampler instance for batch processing of complete audio files. Args: **kwargs: Additional keyword arguments passed to the resampler constructor. Returns: A configured SOXRAudioResampler instance. rrrs rcreate_file_resamplerr8s  ' ''c tdi|S)zCreate a stream audio resampler instance. Args: **kwargs: Additional keyword arguments passed to the resampler constructor. Returns: A configured SOXRStreamAudioResampler instance. rrrs rcreate_stream_resamplerrDs $ -f --raudio1audio2ctj|tj}tj|tj}tt |t |}tj |d|t |z fd}tj |d|t |z fd}|j tj|j tjz}tj|ddj tj}|j tjjS)aMix two audio streams together by adding their samples. Both audio streams are assumed to be 16-bit signed integer PCM data. If the streams have different lengths, the shorter one is zero-padded to match the longer stream. Args: audio1: First audio stream as raw bytes (16-bit signed integers). audio2: Second audio stream as raw bytes (16-bit signed integers). Returns: Mixed audio data as raw bytes with samples clipped to 16-bit range. dtyperconstant)modeii) np frombufferint16maxlenpadastypeint32cliptobytes)rrdata1data2 max_lengthpadded1padded2 mixed_audios r mix_audior4Ps MM& 1E MM& 1ESZU,JffUQ SZ 78zJGffUQ SZ 78zJG..*W^^BHH-EEK''+vu5<os ==288 4D MM+RXX 6ESYE +J   D +: E __dE] +F == " * * ,,rcH||z ||z z }tdtd|}|S)a*Normalize a value to the range [0, 1] and clamp it to bounds. Args: value: The value to normalize. min_value: The minimum value of the input range. max_value: The maximum value of the input range. Returns: Normalized value clamped to the range [0, 1]. r)r'r8)value min_value max_value normalizednormalized_clampeds rnormalize_valuerFs2)# I(=>JQAz 23 raudio sample_ratectj|tj}|jtj}|j |z }t j||}|j|}t|dd}|S)aCalculate the loudness level of audio data using EBU R128 standard. Uses the pyloudnorm library to calculate integrated loudness according to the EBU R128 recommendation, then normalizes the result to [0, 1]. Args: audio: Audio data as raw bytes (16-bit signed integers). sample_rate: Sample rate of the audio in Hz. Returns: Normalized loudness value between 0 (quiet) and 1 (loud). r ) block_sizeiP) r$r%r&r*float64sizepylnMeterintegrated_loudnessrF)rGrHaudio_np audio_floatrJmeterloudnesss rcalculate_audio_volumerUsm}}U"((3H//"**-K,J JJ{z :E((5Hxb1H OrrA prev_valuefactorc||||z zzS)aApply exponential smoothing to a value. Exponential smoothing is used to reduce noise in time-series data by giving more weight to recent values while still considering historical data. Args: value: The new value to incorporate. prev_value: The previous smoothed value. factor: Smoothing factor between 0 and 1. Higher values give more weight to the new value. Returns: The exponentially smoothed value. r)rArVrWs r exp_smoothingrYs %*"45 55r ulaw_bytesin_rateout_rate resamplerctKtj|d}|j|||d{}|S7w)uConvert μ-law encoded audio to PCM and optionally resample. Args: ulaw_bytes: μ-law encoded audio data as raw bytes. in_rate: Original sample rate of the μ-law audio in Hz. out_rate: Desired output sample rate in Hz. resampler: Audio resampler instance for rate conversion. Returns: PCM audio data as raw bytes at the specified output rate. r N)audioopulaw2linresample)rZr[r\r] in_pcm_bytes out_pcm_bytess r ulaw_to_pcmrd?##J2L$,,\7HMMM N -868 pcm_bytesctK|j|||d{}tj|d}|S7w)uConvert PCM audio to μ-law encoding and optionally resample. Args: pcm_bytes: PCM audio data as raw bytes (16-bit signed integers). in_rate: Original sample rate of the PCM audio in Hz. out_rate: Desired output sample rate in Hz. resampler: Audio resampler instance for rate conversion. Returns: μ-law encoded audio data as raw bytes at the specified output rate. Nr )rar_lin2ulaw)rgr[r\r]rbout_ulaw_bytess r pcm_to_ulawrk?#++IwIIL%%lA6N  J 868 alaw_bytesctKtj|d}|j|||d{}|S7w)aConvert A-law encoded audio to PCM and optionally resample. Args: alaw_bytes: A-law encoded audio data as raw bytes. in_rate: Original sample rate of the A-law audio in Hz. out_rate: Desired output sample rate in Hz. resampler: Audio resampler instance for rate conversion. Returns: PCM audio data as raw bytes at the specified output rate. r N)r_alaw2linra)rnr[r\r]rbrcs r alaw_to_pcmrqrerfctK|j|||d{}tj|d}|S7w)aConvert PCM audio to A-law encoding and optionally resample. Args: pcm_bytes: PCM audio data as raw bytes (16-bit signed integers). in_rate: Original sample rate of the PCM audio in Hz. out_rate: Desired output sample rate in Hz. resampler: Audio resampler instance for rate conversion. Returns: A-law encoded audio data as raw bytes at the specified output rate. Nr )rar_lin2alaw)rgr[r\r]rbout_alaw_bytess r pcm_to_alawru rlrmctj|tj}tj|j }|t kS)u-Determine if an audio sample contains silence by checking amplitude levels. This function analyzes raw PCM audio data to detect silence by comparing the maximum absolute amplitude against a predefined threshold. The audio is expected to be clean speech or complete silence without background noise. Args: pcm_bytes: Raw PCM audio data as bytes (16-bit signed integers). Returns: bool: True if the audio sample is considered silence (below threshold), False otherwise. Note: Normal speech typically produces amplitude values between ±500 to ±5000, depending on factors like loudness and microphone gain. The threshold (SPEAKING_THRESHOLD) is set well below typical speech levels to reliably detect silence vs. speech. r )r$r%r&absr'SPEAKING_THRESHOLD)rg audio_datarCs r is_silencerzs?*y9Jz"&&(I * **r)__doc__r_numpyr$ pyloudnormrN-pipecat.audio.resamplers.base_audio_resamplerr'pipecat.audio.resamplers.soxr_resamplerr.pipecat.audio.resamplers.soxr_stream_resamplerrrxrrrbytesr4r>rFintfloatrUrYrdrkrqruboolrzrrrrsjLFS(*<(8 ('9 ( .); .2e2U2u2>--E-e-4  %ce666E656U6$ #/2?Q.Pb* #/2?Q .Pb*+%+D+r