o i) @sTdZddlZddlZddlZddlmZddlm Z ddl m Z dZ defdd Z defd d Zdefd d ZdededefddZdededefddZddZdededefddZdedededefdd Zd!ed"ed#ed$efd%d&Zd'ed"ed#ed$efd(d)Zd*ed"ed#ed$edef d+d,Zd'ed"ed#ed$efd-d.Zd'edefd/d0ZdS)1zAudio 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)BaseAudioResamplerSOXRAudioResamplerSOXRStreamAudioResamplerreturncKsXddl}||d|jdtddWdn1s wYtdi|S)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)kwargsr r r G/home/ubuntu/.local/lib/python3.10/site-packages/pipecat/audio/utils.pycreate_default_resamplers   rcKtdi|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. Nr rrr r rcreate_file_resampler8 rcKr)zCreate a stream audio resampler instance. Args: **kwargs: Additional keyword arguments passed to the resampler constructor. Returns: A configured SOXRStreamAudioResampler instance. Nr rrr r rcreate_stream_resamplerDrraudio1audio2cCstj|tjd}tj|tjd}tt|t|}tj|d|t|fdd}tj|d|t|fdd}|tj|tj}t|ddtj}|tj S)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_audior r r mix_audioPsr0 left_audio right_audiocCshtj|tjd}tj|tjd}tt|t|}|d|}|d|}t||f}|tjS)a Interleave left and right mono audio channels into stereo audio. Takes two mono audio streams and combines them into a single stereo stream by interleaving the samples (L, R, L, R, ...). If the channels have different lengths, both are truncated to the shorter length. Args: left_audio: Left channel audio as raw bytes (16-bit signed integers). right_audio: Right channel audio as raw bytes (16-bit signed integers). Returns: Interleaved stereo audio data as raw bytes. rN)r r!r"minr$ column_stackr&r))r1r2leftright min_lengthstereor r rinterleave_stereo_audioos  r9cCs$||||}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#r3)value min_value max_value normalizednormalized_clampedr r rnormalize_values r@audio sample_ratecCsNtj|tjd}|tj}|j|}tj||d}||}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_loudnessr@)rArBaudio_np audio_floatrCmeterloudnessr r rcalculate_audio_volumes    rNr; prev_valuefactorcCs||||S)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 )r;rOrPr r r exp_smoothingsrQ ulaw_bytesin_rateout_rate resamplerc&t|d}||||IdH}|S)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)rRrSrTrU in_pcm_bytes out_pcm_bytesr r r ulaw_to_pcm r\ pcm_bytesc&||||IdH}t|d}|S)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 )rYrWlin2ulaw)r^rSrTrUrZout_ulaw_bytesr r r pcm_to_ulaw rb alaw_bytescrV)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)rWalaw2linrY)rdrSrTrUrZr[r r r alaw_to_pcmr]rfcr_)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 )rYrWlin2alaw)r^rSrTrUrZout_alaw_bytesr r r pcm_to_alaw rcricCs&tj|tjd}t|}|tkS)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)r^ audio_datar=r r r is_silencesrm)__doc__rWnumpyr pyloudnormrG-pipecat.audio.resamplers.base_audio_resamplerr'pipecat.audio.resamplers.soxr_resamplerr.pipecat.audio.resamplers.soxr_stream_resamplerrrkrrrbytesr0r9r@intfloatrNrQr\rbrfriboolrmr r r rsN