improve audio resampling by switching from resampy to soxr

CHANGELOG.md

@@ -16,6 +16,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 - Fixed a type error when using `voice_settings` in `ElevenLabsHttpTTSService`.
 
+### Performance
+
+- Replaced audio resampling library `resampy` with `soxr`.
+
 ## [0.0.53] - 2025-01-18
 
 ### Added

pyproject.toml

@@ -32,7 +32,7 @@ dependencies = [
     "protobuf~=5.29.3",
     "pydantic~=2.10.5",
     "pyloudnorm~=0.1.1",
-    "resampy~=0.4.3"
+    "soxr~=0.5.0"
 ]
 
 [project.urls]

src/pipecat/audio/utils.py

@@ -8,14 +8,14 @@ import audioop
 
 import numpy as np
 import pyloudnorm as pyln
-import resampy
+import soxr
 
 
 def resample_audio(audio: bytes, original_rate: int, target_rate: int) -> bytes:
     if original_rate == target_rate:
         return audio
     audio_data = np.frombuffer(audio, dtype=np.int16)
-    resampled_audio = resampy.resample(audio_data, original_rate, target_rate)
+    resampled_audio = soxr.resample(audio_data, original_rate, target_rate)
     return resampled_audio.astype(np.int16).tobytes()