Mixing Polly with Audip Clip

generatePollyMix.py

def generatePollyMix(polly, text, voice, backgroundSFX, format='mp3'):
    resp = polly.synthesize_speech(OutputFormat=format, Text=text, VoiceId=voice)
    soundfile = open(f"/tmp/sound.mp3", 'wb')
    soundBytes = resp['AudioStream'].read()
    soundfile.write(soundBytes)
    soundfile.close()

    audio = MP3("/tmp/sound.mp3")
    audio_length = audio.info.length

    sox_cmd = f"/tmp/sox -m {backgroundSFX} /tmp/sound.mp3 -C 48.01 /tmp/output.mp3 rate 22050 gain -l 16 trim 0 {audio_length + 4}"

    sox_cmd_output = subprocess.run([sox_cmd], shell=True, stderr=subprocess.STDOUT, stdout=subprocess.PIPE)

    return sox_cmd_output.returncode