I want to make datasets for medicine! Give me datasets code with comma. I need datasets in txt with comma. And don't need python. Only need datasets. pip install gtts pydub
from gtts import gTTS
from pydub import AudioSegment
from pydub.playback import play
import os
import random
# Function to generate text-to-speech
def text_to_speech(text, output_file="output.mp3", lang="en", slow=False):
# Generate TTS using gTTS
tts = gTTS(text=text, lang=lang, slow=slow)
tts.save(output_file)
print(f"Text-to-speech saved to {output_file}")
# Function to add light breathing sounds
def add_breathing_sounds(audio_file, breathing_file="breathing.wav", output_file="output_with_breathing.mp3"):
# Load the TTS audio
audio = AudioSegment.from_mp3(audio_file)
# Load the breathing sound
breathing = AudioSegment.from_wav(breathing_file)
breathing = breathing - 10 # Reduce volume of breathing sound by 10 dB
# Randomly insert breathing sounds into the audio
final_audio = AudioSegment.empty()
chunk_length = 2000 # Split audio into 2-second chunks
overlap = 100 # Overlap between chunks for smooth transitions
for i in range(0, len(audio), chunk_length):
chunk = audio[i:i + chunk_length]
final_audio += chunk
# Randomly add breathing sound (30% chance)
if random.random() < 0.3 and len(final_audio) > 1000: # Ensure breathing isn't added at the very start
final_audio = final_audio.append(breathing, crossfade=overlap)
# Export the final audio
final_audio.export(output_file, format="mp3")
print(f"Audio with breathing saved to {output_file}")
# Main function
def main():
# Input text
text = input("Enter the text you want to convert to speech: ")
# Generate TTS
tts_output = "tts_output.mp3"
text_to_speech(text, output_file=tts_output, lang="en", slow=False)
# Add breathing sounds
final_output = "final_output.mp3"
add_breathing_sounds(tts_output, output_file=final_output)
# Play the final audio
play(AudioSegment.from_mp3(final_output))
# Clean up temporary files
os.remove(tts_output)
if __name__ == "__main__":
main()
Comments
Post a Comment