Update text_speech_utils.py

text_speech_utils.py

@@ -1,21 +1,28 @@
-import sounddevice as sd
-import soundfile as sf
+from pydub import AudioSegment
+from pydub.playback import play
 import whisper
+import soundfile as sf
 from gtts import gTTS
 import os
+import tempfile
 
-# Load the Whisper model
-model = whisper.load_model("base")  # You can use other versions like "small", "medium", or "large"
+# Load Whisper model
+model = whisper.load_model("base")  # You can also try "small", "medium", or "large"
 
-# Function to record audio using sounddevice and save it as a .wav file
+# 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...")
-    # 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)
+    # 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
@@ -33,7 +40,8 @@ def save_text_as_audio(text, audio_filename):
     tts.save(audio_filename)
     print(f"Audio saved as {audio_filename}")
 
-# Function to play audio using the system's default audio player
+# Function to play audio using pydub's playback
 def play_audio(filename):
     print("Playing audio...")
-    os.system(f"start {filename}")  # For Windows; for Linux/macOS, use `os.system(f"mpg321 {filename}")`
+    audio = AudioSegment.from_wav(filename)
+    play(audio)