edge-tts.py

import tkinter as tk
from tkinter import messagebox, ttk
import threading
import os
import asyncio
import edge_tts
from playsound3 import playsound

os.makedirs("tts_outputs", exist_ok=True)

VOICE_DATA = {
    "Arabic - Zariyah": "ar-SA-ZariyahNeural",
    "Arabic - Hamed": "ar-SA-HamedNeural",
    "English (US) - Guy": "en-US-GuyNeural",
    "English (US) - Ava": "en-US-AvaNeural",
    "English (UK) - Sonia": "en-GB-SoniaNeural",
    "English (UK) - Ryan": "en-GB-RyanNeural",
    "German (Germany) - Katja": "de-DE-KatjaNeural",
    "German (Germany) - Conrad": "de-DE-ConradNeural",
    "Spanish (Spain) - Elvira": "es-ES-ElviraNeural",
    "Spanish (Spain) - Alvaro": "es-ES-AlvaroNeural",
    "Hindi (India) - Swara": "hi-IN-SwaraNeural",
    "Hindi (India) - Madhur": "hi-IN-MadhurNeural",
    "Turkish (Turkey) - Emel": "tr-TR-EmelNeural",
    "Turkish (Turkey) - Ahmet": "tr-TR-AhmetNeural",
    "Russian (Russia) - Svetlana": "ru-RU-SvetlanaNeural",
    "Russian (Russia) - Dmitry": "ru-RU-DmitryNeural",
}

class EdgeTTSApp:
    def __init__(self, root):
        self.root = root
        self.root.title("Advanced Edge TTS - Professional")
        self.root.geometry("650x650")
        self.root.configure(bg="#f2f4f7")
        self.root.resizable(False, False)
        self.setup_ui()

    def setup_ui(self):
        title_label = tk.Label(
            self.root, text="Edge-TTS Voice Generator",
            font=("Arial", 20, "bold"), fg="#1A73E8", bg="#f2f4f7"
        )
        title_label.pack(pady=20)

        tk.Label(self.root, text="Enter your text below:", font=("Arial", 11, "bold"), bg="#f2f4f7").pack(anchor="w", padx=40)
        self.text_input = tk.Text(self.root, height=10, width=70, font=("Arial", 11), relief="solid", bd=1)
        self.text_input.pack(pady=10, padx=40)

        settings_frame = tk.Frame(self.root, bg="#f2f4f7")
        settings_frame.pack(pady=10, fill="x", padx=40)

        tk.Label(settings_frame, text="Select Voice:", font=("Arial", 10, "bold"), bg="#f2f4f7").grid(row=0, column=0, sticky="w")
        self.voice_var = tk.StringVar(value="Arabic (Egypt) - Salma")
        self.voice_menu = ttk.Combobox(settings_frame, textvariable=self.voice_var, values=list(VOICE_DATA.keys()), state="readonly", width=30)
        self.voice_menu.grid(row=1, column=0, pady=5, padx=(0, 20))

        tk.Label(settings_frame, text="Speed (Rate):", font=("Arial", 10, "bold"), bg="#f2f4f7").grid(row=0, column=1, sticky="w")
        self.speed_var = tk.StringVar(value="+0%")
        self.speed_menu = ttk.Combobox(settings_frame, textvariable=self.speed_var, values=["-50%", "-25%", "+0%", "+25%", "+50%"], state="readonly", width=10)
        self.speed_menu.grid(row=1, column=1, pady=5)

        self.convert_button = tk.Button(
            self.root, text="Generate & Play Speech",
            command=self.start_conversion,
            font=("Arial", 13, "bold"), bg="#4CAF50", fg="white",
            padx=30, pady=12, relief="raised", cursor="hand2"
        )
        self.convert_button.pack(pady=30)

        footer = tk.Label(
            self.root, text="Free Unlimited Neural TTS | No API Key Required",
            font=("Arial", 9, "italic"), fg="#777", bg="#f2f4f7"
        )
        footer.pack(side="bottom", pady=20)

    async def _generate_audio_task(self, text, voice, rate, output_path):
        communicate = edge_tts.Communicate(text, voice, rate=rate)
        await communicate.save(output_path)

    def process_conversion(self):
        text = self.text_input.get("1.0", tk.END).strip()
        if not text:
            messagebox.showwarning("Warning", "Please enter some text first!")
            return

        selected_voice_name = self.voice_var.get()
        voice_id = VOICE_DATA[selected_voice_name]
        speed = self.speed_var.get()
        
        output_path = os.path.join("tts_outputs", "final_output.mp3")

        try:
            asyncio.run(self._generate_audio_task(text, voice_id, speed, output_path))
            playsound(output_path)
            messagebox.showinfo("Success", f"Audio generated successfully using {selected_voice_name}!")
        
        except Exception as e:
            messagebox.showerror("Error", f"An error occurred: {str(e)}")

    def start_conversion(self):
        threading.Thread(target=self.process_conversion, daemon=True).start()

if __name__ == "__main__":
    root = tk.Tk()
    app = EdgeTTSApp(root)
    root.mainloop()