import sounddevice as sd
import soundfile as sf
import whisper
from gtts import gTTS
import os

# Load the Whisper model
model = whisper.load_model("base")  # You can use other versions like "small", "medium", or "large"

# Function to record audio using sounddevice and save it as a .wav file
def record_audio(filename, sec=5, sr=44100):
    print("Recording...")
    # Record the audio from the microphone (mono channel)
    audio_data = sd.rec(int(sec * sr), samplerate=sr, channels=1, dtype='int16')
    sd.wait()  # Wait until recording is done
    
    # Save the audio data to a file using soundfile
    sf.write(filename, audio_data, sr)
    print(f"Audio saved as {filename}")

# Function to transcribe audio using Whisper
def transcribe_audio(filename):
    print("Transcribing audio...")
    result = model.transcribe(filename)
    text = result['text']
    print(f"Transcription: {text}")
    return {"text": text}

# Function to save text as an audio file using gTTS (Google Text-to-Speech)
def save_text_as_audio(text, audio_filename):
    print("Converting text to speech...")
    tts = gTTS(text=text, lang='en', slow=False)
    tts.save(audio_filename)
    print(f"Audio saved as {audio_filename}")

# Function to play audio using the system's default audio player
def play_audio(filename):
    print("Playing audio...")
    os.system(f"start {filename}")  # For Windows; for Linux/macOS, use `os.system(f"mpg321 {filename}")`