app.py

import gradio as gr
from gtts import gTTS
import numpy as np
import io
import base64
import os

def text_to_speech(text, language='en'):
    tts = gTTS(text=text, lang=language)
    fp = io.BytesIO()
    tts.write_to_fp(fp)
    fp.seek(0)
    return fp

def generate_sound(frequency, duration):
    # Generate a simple sine wave
    t = np.linspace(0, duration, int(44100 * duration), False)
    audio = np.sin(2 * np.pi * frequency * t)
    return (44100, audio.astype(np.float32))

def generate_voiceover(text, language):
    audio_fp = text_to_speech(text, language)
    return audio_fp

def generate_sound_effect(frequency, duration):
    return generate_sound(frequency, duration)

# Gradio interface
iface = gr.Interface(
    fn=[generate_voiceover, generate_sound_effect],
    inputs=[
        gr.Textbox(label="Enter text for speech generation"),
        gr.Dropdown(choices=["en", "es", "fr", "de", "it"], label="Select Language", value="en"),
        gr.Number(label="Frequency (Hz)", value=440),
        gr.Number(label="Duration (seconds)", value=1)
    ],
    outputs=[
        gr.Audio(label="Generated Speech"),
        gr.Audio(label="Generated Sound Effect")
    ],
    title="Simple Text-to-Speech and Sound Generation Tool",
    description="Generate speech from text and create simple sound effects."
)

iface.launch()