from RealtimeSTT import AudioToTextRecorder
from RealtimeTTS import TextToAudioStream, KokoroEngine

if __name__ == '__main__':
    print("Wait until it says 'speak now'")
    recorder = AudioToTextRecorder()

    engine = KokoroEngine()
    stream = TextToAudioStream(engine)
    engine.set_voice('jf_alpha')

    def process_text(text):
        stream.feed(text).play()
        print(text)

    while True:
        recorder.text(process_text)

python3 3.11.9 버전에서 테스트 했음.
3.12 이상은 지원하지 않는다고 하니 주의.