Python Voice Lab - Text-to-Speech + 10 Voice Effects (Audio Processing Project)

import pyttsx3
from pydub import AudioSegment
import tempfile
import os
import winsound


# Initialize text-to-speech engine
engine = pyttsx3.init()

voices = engine.getProperty('voices')

print('Available system voices:')

for i, voice in enumerate(voices):
    print(f'{i}: {voice.name} - {voice.languages}')


voice_index = int(input('Select voice number: '))

voice = voices[voice_index]

engine.setProperty('voice', voice.id)


text = input('Enter text for speech generation: ')


# Create temporary WAV file
with tempfile.NamedTemporaryFile(delete=False, suffix='.wav') as file:
    temp_file = file.name


engine.save_to_file(text, temp_file)
engine.runAndWait()


# Load generated audio
audio = AudioSegment.from_wav(temp_file)


print('\nSelect voice effect:')
print('1 - Robot')
print('2 - Cartoon')
print('3 - Low narrator')
print('4 - Deep cinematic')
print('5 - Electronic')
print('6 - Metallic robot')
print('7 - Room echo')
print('8 - High cartoon')
print('9 - AM/FM radio')
print('10 - Computer assistant')


effect = input('Choose effect (1-10): ')


# Apply selected effect

if effect == '1':
    audio = audio._spawn(
        audio.raw_data,
        overrides={'frame_rate': int(audio.frame_rate * 1.1)}
    )

elif effect == '2':
    audio = audio._spawn(
        audio.raw_data,
        overrides={'frame_rate': int(audio.frame_rate * 1.6)}
    )

elif effect == '3':
    audio = audio._spawn(
        audio.raw_data,
        overrides={'frame_rate': int(audio.frame_rate * 0.85)}
    )

elif effect == '4':
    audio = audio._spawn(
        audio.raw_data,
        overrides={'frame_rate': int(audio.frame_rate * 0.65)}
    )

elif effect == '5':
    audio = audio.high_pass_filter(800).low_pass_filter(3000)

elif effect == '6':
    shifted = audio._spawn(
        audio.raw_data,
        overrides={'frame_rate': int(audio.frame_rate * 1.2)}
    )

    audio = audio.overlay(shifted, position=10)

elif effect == '7':
    echo = audio - 10
    audio = audio.overlay(echo, position=200)

elif effect == '8':
    audio = audio._spawn(
        audio.raw_data,
        overrides={'frame_rate': int(audio.frame_rate * 2.0)}
    )

elif effect == '9':
    audio = audio.high_pass_filter(200)
    audio = audio.low_pass_filter(3000)
    audio = audio.apply_gain(-5)

elif effect == '10':
    audio = audio._spawn(
        audio.raw_data,
        overrides={'frame_rate': int(audio.frame_rate * 1.05)}
    )

    echo = audio - 12
    audio = audio.overlay(echo, position=120)


# Export final audio

output_file = 'voice_output.wav'

audio.export(output_file, format='wav')


print(f'\nAudio saved: {output_file}')


# Play generated audio

winsound.PlaySound(
    output_file,
    winsound.SND_FILENAME
)


# Remove temporary file

os.remove(temp_file)