openvoice_app.py

import os
import torch
import argparse
import gradio as gr
import requests
from email.mime.text import MIMEText
from email.mime.multipart import MIMEMultipart
from email.mime.application import MIMEApplication
from openvoice import se_extractor
from openvoice.api import BaseSpeakerTTS, ToneColorConverter
from dotenv import load_dotenv
from openai import OpenAI
from elevenlabs.client import ElevenLabs
from elevenlabs import play, save
import time

# Load environment variables
load_dotenv()

# Argument parsing
parser = argparse.ArgumentParser()
parser.add_argument("--share", action='store_true', default=False, help="make link public")
args = parser.parse_args()

# Initialize ElevenLabs client
client = ElevenLabs(api_key=os.environ.get("ELEVENLABS_API_KEY"))
device = 'cuda' if torch.cuda.is_available() else 'cpu'
output_dir = 'outputs'
os.makedirs(output_dir, exist_ok=True)

api_key = os.environ.get("ELEVENLABS_API_KEY")
supported_languages = ['zh', 'en']

# Mailgun configuration
MAILGUN_DOMAIN = "sandbox3785301d5591459ca8b5b5cd121edfb8.mailgun.org"
MAILGUN_API_KEY = os.environ.get("MAILGUN_API_KEY")

# Function to send email with downloadable file using Mailgun
def send_email_with_file(recipient_email, file_path, subject, body):
    try:
        # Prepare the MIME message
        message = MIMEMultipart()
        message['From'] = f"Your App <mailgun@{MAILGUN_DOMAIN}>"
        message['To'] = recipient_email
        message['Subject'] = subject
        
        # Attach the text body
        message.attach(MIMEText(body))
        
        # Attach the file
        with open(file_path, "rb") as file:
            part = MIMEApplication(file.read(), Name=os.path.basename(file_path))
        part['Content-Disposition'] = f'attachment; filename="{os.path.basename(file_path)}"'
        message.attach(part)
        
        # Send the email using Mailgun API
        response = requests.post(
            f"https://api.mailgun.net/v3/{MAILGUN_DOMAIN}/messages",
            auth=("api", MAILGUN_API_KEY),
            files=[("attachment", (os.path.basename(file_path), open(file_path, "rb").read()))],
            data={
                "from": f"Your App <mailgun@{MAILGUN_DOMAIN}>",
                "to": recipient_email,
                "subject": subject,
                "text": body,
            }
        )
        
        if response.status_code == 200:
            print("Email sent successfully")
            return True
        else:
            print(f"Failed to send email. Status code: {response.status_code}")
            print(f"Response: {response.text}")
            return False
        
    except Exception as e:
        print(f"An error occurred while sending email: {e}")
        return False

# Predict function
def predict(prompt, style, audio_file_pth, voice_name, customer_email):
    text_hint = 'Your file will only be saved for 24 hours.\n'
    if len(prompt) < 2:
        text_hint += "[ERROR] Please provide a longer prompt text.\n"
        return text_hint, None, None
    if len(prompt) > 200:
        text_hint += "[ERROR] Text length limited to 200 characters. Please try shorter text.\n"
        return text_hint, None, None
    
    print(audio_file_pth)
    voice = client.clone(
        name=voice_name,
        description="A trial voice model for testing",
        files=[audio_file_pth],
    )
    # Generate audio from text
    audio = client.generate(text=prompt, voice=voice)
    save_path = f'{output_dir}/output.wav'
    save(audio, save_path)
    
    # Send email with downloadable file
    subject = "Your Voice Clone File"
    body = "Thank you for using our Voice Clone service. Your file is attached."
    if send_email_with_file(customer_email, save_path, subject, body):
        text_hint += "Email sent successfully with the voice file.\n"
    else:
        text_hint += "Failed to send email with the voice file. Please try again later.\n"

    return text_hint, save_path, audio_file_pth

# Gradio interface setup
with gr.Blocks(gr.themes.Glass()) as demo:
    with gr.Row():
        with gr.Column():
            input_text_gr = gr.Textbox(
                label="Create This",
                info="One or two sentences at a time is better. Up to 200 text characters.",
                value="He hoped there would be stew for dinner, turnips and carrots and bruised potatoes and fat mutton pieces to be ladled out in thick, peppered, flour-fattened sauce.",
            )
            style_gr = gr.Dropdown(
                label="Style",
                choices=['default', 'whispering', 'cheerful', 'terrified', 'angry', 'sad', 'friendly'],
                info="Please upload a reference audio file that is at least 1 minute long. For best results, ensure the audio is clear. You can use Adobe Podcast Enhance(https://podcast.adobe.com/enhance) to improve the audio quality before uploading.",
                max_choices=1,
                value="default",
            )
            ref_gr = gr.Audio(
                label="Original Audio",
                type="filepath",
                sources=["upload"],  # Allow only upload
            )
            voice_name_gr = gr.Textbox(
                label="Your name and Product you bought",
                value="Sam"
            )
            customer_email_gr = gr.Textbox(
                label="Your Email",
                info="We'll send you a downloadable file to this email address."
            )
            tts_button = gr.Button("Start", elem_id="send-btn", visible=True)

        with gr.Column():
            out_text_gr = gr.Text(label="Info")
            audio_gr = gr.Audio(label="Replicated Sound", autoplay=True)
            ref_audio_gr = gr.Audio(label="Original Audio Used ")

            tts_button.click(predict, [input_text_gr, style_gr, ref_gr, voice_name_gr, customer_email_gr], outputs=[out_text_gr, audio_gr, ref_audio_gr])

    demo.queue()
    demo.launch(debug=True, show_api=False, share=args.share)

# Hide Gradio footer and record button
css = """
footer {visibility: hidden}
audio .btn-container {display: none}
"""

demo.add_css(css)