Creating Dynamic Audio Narratives: A Guide to Combining Text-to-Speech and Music Using Python

pip install pydub gtts

from gtts import gTTS
from pydub import AudioSegment
import os

def text_to_speech(input_file_path, output_file_path, silence_duration_ms=1000, start_silence_ms=2000, end_silence_ms=2000):
    try:
        # Read the text from the input file
        with open(input_file_path, 'r', encoding='utf-8') as file:
            text = file.read()

        # Convert text to speech
        tts = gTTS(text, lang='ru' if any(c in text for c in 'АБВГДЕЁЖЗИИЙКЛМНОПРСТУФХЦЧШЩЬЫЭЮЯ') else 'en')

        # Save the converted speech to a temporary MP3 file
        temp_file_path = 'temp.mp3'
        tts.save(temp_file_path)

        # Load the audio file
        audio = AudioSegment.from_mp3(temp_file_path)

        # Create silence segments
        silence_segment = AudioSegment.silent(duration=silence_duration_ms)
        start_silence = AudioSegment.silent(duration=start_silence_ms)
        end_silence = AudioSegment.silent(duration=end_silence_ms)

        # Split the text by periods
        segments = text.split('.')

        # Create and combine audio segments
        audio_segments = []
        for i, segment in enumerate(segments):
            if segment.strip() == '':
                continue
            segment_tts = gTTS(segment.strip(), lang='ru' if any(c in segment for c in 'АБВГДЕЁЖЗИИЙКЛМНОПРСТУФХЦЧШЩЬЫЭЮЯ') else 'en')
            temp_segment_file = f'temp_segment_{i}.mp3'
            segment_tts.save(temp_segment_file)
            segment_audio = AudioSegment.from_mp3(temp_segment_file)
            audio_segments.append(segment_audio)
            if i < len(segments) - 1:
                audio_segments.append(silence_segment)
            os.remove(temp_segment_file)

        # Combine all segments
        final_audio = start_silence + sum(audio_segments, AudioSegment.empty()) + end_silence
        final_audio.export(output_file_path, format='mp3')
        os.remove(temp_file_path)
        print(f"Speech successfully saved to {output_file_path}")

    except Exception as e:
        print(f"An error occurred: {e}")

from pydub import AudioSegment
import os

def mix_audio_with_music(speech_file_path, music_file_path, output_file_path, volume_reduction_percent=50, fade_duration_ms=3000):
    try:
        # Load the speech and music files
        speech = AudioSegment.from_mp3(speech_file_path)
        music = AudioSegment.from_mp3(music_file_path)

        # Adjust the volume of the music
        volume_reduction = (volume_reduction_percent / 100.0)
        music = music - (10 * volume_reduction)

        # Fade-out the music if it's longer than the speech
        if len(music) > len(speech):
            music = music[:len(speech)]
            music = music.fade_out(fade_duration_ms)

        # Ensure the length of music matches the length of speech
        if len(music) < len(speech):
            repeats = int(len(speech) / len(music)) + 1
            music = music * repeats
            music = music[:len(speech)]

        # Mix the audio files
        mixed_audio = speech.overlay(music)
        mixed_audio.export(output_file_path, format='mp3')

        print(f"Mixed audio saved to {output_file_path}")

    except Exception as e:
        print(f"An error occurred: {e}")

if __name__ == "__main__":
    # Define file paths
    input_file = 'stories/story_2.txt'
    output_file = 'output/converted_speech.mp3'

    # Create output directory if it doesn't exist
    os.makedirs(os.path.dirname(output_file), exist_ok=True)

    # Convert text to speech
    text_to_speech(input_file, output_file, silence_duration_ms=2000, start_silence_ms=3000, end_silence_ms=3000)

    speech_file = 'output/converted_speech.mp3'
    music_file = 'music/FIVE_OF_A_KIND_Density_Time.mp3'
    final_output_file = 'output/converted_speech_with_music.mp3'

    # Mix the audio with music
    mix_audio_with_music(speech_file, music_file, final_output_file, volume_reduction_percent=60, fade_duration_ms=3000)