Upload any ( i think ) audio file to discord as a voice-message

main.py

from fake_useragent import UserAgent    # pip install fake-useragent or fake_useragent
from consts import TOKEN                # Make a consts.py file in same dir and put your token there ( TOKEN = "YOUR TOKEN" )
import requests                         # pip install requests

import os, json, base64, subprocess     # Comes pre installed

# User inputs
channel_id = int(input("Enter a Channel ID to send the message: "))
voice_uri = input("Enter the Audio File path: ").strip()

# Validate file path
if not os.path.exists(voice_uri):
    raise FileNotFoundError(f"File Not Found: {voice_uri}")

# Convert MP3 to OGG (Opus) using ffmpeg
ogg_filename = "voice-message.ogg"
try:
    subprocess.run([
        "ffmpeg",
        '-hide_banner',
        "-y",
        "-i", voice_uri,
        "-c:a", "libopus",
        "-b:a", "64k",
        "-ar", "48000",
        ogg_filename
    ], check=True, stderr=subprocess.DEVNULL, stdout=subprocess.DEVNULL)

    # Extract metadata using ffprobe
    def get_audio_metadata(file_path):
        """ Extracts audio duration and waveform data using ffprobe. """
        # Get duration
        cmd = [
            "ffprobe", "-v", "error", '-hide_banner',
            "-select_streams", "a:0",
            "-show_entries", "format=duration",
            "-of", "json",
            file_path
        ]
        result = subprocess.run(cmd, capture_output=True, text=True)
        duration = float(json.loads(result.stdout)["format"]["duration"])

        # Generate a simple waveform (instead of real analysis)
        waveform = base64.b64encode(os.urandom(256)).decode('utf-8')

        return round(duration), waveform

    # Get required metadata
    duration, waveform = get_audio_metadata(ogg_filename)
    file_size = os.path.getsize(ogg_filename)

    # Step 1: Request an upload URL
    url = f"https://discord.com/api/v10/channels/{channel_id}/attachments"
    headers = {
        "Authorization": TOKEN,
        "Content-Type": "application/json",
        "User-Agent": UserAgent().random
    }
    payload = {
        "files": [{
            "filename": "voice-message.ogg",
            "file_size": file_size,
            "id": 0
        }]
    }
    response = requests.post(url, headers=headers, json=payload)

    if response.status_code != 200:
        print("Failed to get upload URL:", response.text)
        exit()

    upload_data = response.json()["attachments"][0]
    upload_url = upload_data["upload_url"]
    uploaded_filename = upload_data["upload_filename"]

    # Step 2: Upload the audio file
    with open(ogg_filename, "rb") as file:
        upload_response = requests.put(upload_url, headers={"Content-Type": "audio/ogg"}, data=file)

    if upload_response.status_code != 200:
        print("Failed to upload file:", upload_response.text)
        exit()

    # Step 3: Send the voice message
    message_url = f"https://discord.com/api/v10/channels/{channel_id}/messages"
    message_payload = {
        "flags": 8192,  # IS_VOICE_MESSAGE
        "attachments": [{
            "id": "0",
            "filename": "voice-message.ogg",
            "uploaded_filename": uploaded_filename,
            "duration_secs": duration,
            "waveform": waveform
        }]
    }

    message_response = requests.post(message_url, headers=headers, json=message_payload)

    print(message_response.status_code, f"Error Response: \n{json.dumps(message_response.text, indent=4, ensure_ascii=False)}" if message_response.status_code != 200 else "Upload Succesfull!")
finally:
    if os.path.exists(ogg_filename): os.remove(ogg_filename)