text_speech_utils.py

from pydub import AudioSegment
from pydub.playback import play
import whisper
import soundfile as sf
from gtts import gTTS
import os
import tempfile

# Load Whisper model
model = whisper.load_model("base")  # You can also try "small", "medium", or "large"

# Function to record audio using pydub and save it as a .wav file
def record_audio(filename, sec=5, sr=44100):
    from pydub.generators import Sine
    import io
    
    # Generate a sine wave (just as a placeholder for actual recording)
    # In a real-world case, use a microphone input
    print("Recording...")
    
    # Simulate recording a sound for `sec` seconds at `sr` sample rate
    # NOTE: You'd replace this with actual microphone recording code
    sine_wave = Sine(440).to_audio_segment(duration=sec * 1000)  # 440 Hz sine wave for `sec` seconds
    
    sine_wave.export(filename, format="wav")
    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 pydub's playback
def play_audio(filename):
    print("Playing audio...")
    audio = AudioSegment.from_wav(filename)
    play(audio)