Audio Splitter - split audio into chunks based on silence using pydub

audio-splitter.py

import os
import aiohttp
import asyncio
import tempfile
from pydub import AudioSegment
from pydub.silence import split_on_silence


async def split_audio_on_silence_and_save(audio_url: str, output_dir: str):
    # Create output directory if it doesn't exist
    os.makedirs(output_dir, exist_ok=True)

    # Download the audio file
    async with aiohttp.ClientSession() as session:
        async with session.get(audio_url) as response:
            if response.status != 200:
                raise Exception(f"Failed to download audio: HTTP {response.status}")
            audio_data = await response.read()

    # Save the audio data to a temporary file
    with tempfile.NamedTemporaryFile(delete=False, suffix=".mp3") as temp_file:
        temp_file.write(audio_data)
        temp_file_path = temp_file.name

    try:
        # Load the audio data from the temporary file
        audio = AudioSegment.from_file(temp_file_path)

        # Split on silence
        chunks = split_on_silence(
            audio,
            min_silence_len=500,  # minimum silence length of 500ms
            silence_thresh=-40,  # consider it silent if quieter than -40 dBFS
            keep_silence=300,  # keep 300ms of silence at the beginning and end of each chunk
        )

        # Save chunks to disk
        for i, chunk in enumerate(chunks):
            output_path = os.path.join(output_dir, f"chunk_{i+1}.wav")
            chunk.export(output_path, format="wav")
            print(f"Saved chunk {i+1} to {output_path}")

        print(f"Total chunks created: {len(chunks)}")

    finally:
        # Clean up the temporary file
        os.unlink(temp_file_path)


# Example usage
async def main():
    audio_url = "https://cdn-aditya-dev.enparadigmtech.com/audio-files/hindi/hindi_sample4.mp3"
    output_dir = "audio_chunks"
    await split_audio_on_silence_and_save(audio_url, output_dir)


if __name__ == "__main__":
    asyncio.run(main())