Create mixing.py

pipeline/mixing.py

@@ -0,0 +1,11 @@
+from pydub import AudioSegment
+
+def mix_speech_with_background(original_audio_path: str, speech_segments: list) -> str:
+    background = AudioSegment.from_wav(original_audio_path)
+    output = background
+    for seg in speech_segments:
+        speech = AudioSegment.from_wav(seg["file"])
+        output = output.overlay(speech, position=seg["start_ms"])
+    final_audio = "final_audio.wav"
+    output.export(final_audio, format="wav")
+    return final_audio