from fastrtc_whisper_cpp import get_stt_model, load_audio

model = get_stt_model(model="base.en")

audio_data = load_audio("test.wav")

text = model.stt(audio_data)

print(f'Transcription: {text}')

from fastrtc import (ReplyOnPause, Stream, get_tts_model)
from fastrtc_whisper_cpp import get_stt_model
from openai import OpenAI


client = OpenAI()

stt_model = get_stt_model()
tts_model = get_tts_model()

def echo(audio):
    prompt = stt_model.stt(audio)
    response = client.chat.completions.create(
        model="gpt-4o",
        messages=[{"role": "user", "content": prompt}],
        max_tokens=200,
    )
    prompt = response.choices[0].message.content
    for audio_chunk in tts_model.stream_tts_sync(prompt):
        yield audio_chunk

stream = Stream(ReplyOnPause(echo), modality="audio", mode="send-receive")

stream.ui.launch()